liu.seSearch for publications in DiVA
Change search
Refine search result
123 101 - 140 of 140
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 101.
    Schwende, Isabel
    et al.
    University of Aizu, Japan/University of Greifswald, Germany.
    Pham, Tuan D
    University of Aizu, Japan.
    Pattern recognition and probabilistic measures in alignment-free sequence analysis2014In: Briefings in Bioinformatics, ISSN 1467-5463, E-ISSN 1477-4054, Vol. 15, no 3, p. 354-368Article in journal (Refereed)
    Abstract [en]

    With the massive production of genomic and proteomic data, the number of available biological sequences in databases has reached a level that is not feasible anymore for exact alignments even when just a fraction of all sequences is used. To overcome this inevitable time complexity, ultrafast alignment-free methods are studied. Within the past two decades, a broad variety of nonalignment methods have been proposed including dissimilarity measures on classical representations of sequences like k-words or Markov models. Furthermore, articles were published that describe distance measures on alternative representations such as compression complexity, spectral time series or chaos game representation. However, alignments are still the standard method for real world applications in biological sequence analysis, and the time efficient alignment-free approaches are usually applied in cases when the accustomed algorithms turn out to fail or be too inconvenient.

  • 102.
    Schwende, Isabel
    et al.
    University of Aizu, Japan.
    Pham, Tuan D
    The Aizu Research Cluster for Medical Engineering and Informatics (ARC-Medical), Research Center for Advanced Information Science and Technology, The University of Aizu, Japan.
    Pattern recognition and probabilistic measures in alignment-free sequence analysis2013In: Briefings in Bioinformatics, ISSN 1467-5463, E-ISSN 1477-4054, Vol. 15, no 3, p. 354-368Article in journal (Refereed)
    Abstract [en]

    With the massive production of genomic and proteomic data, the number of available biological sequences in databases has reached a level that is not feasible anymore for exact alignments even when just a fraction of all sequences is used. To overcome this inevitable time complexity, ultrafast alignment-free methods are studied. Within the past two decades, a broad variety of nonalignment methods have been proposed including dissimilarity measures on classical representations of sequences like k-words or Markov models. Furthermore, articles were published that describe distance measures on alternative representations such as compression complexity, spectral time series or chaos game representation. However, alignments are still the standard method for real world applications in biological sequence analysis, and the time efficient alignment-free approaches are usually applied in cases when the accustomed algorithms turn out to fail or be too inconvenient.

  • 103.
    Su, R.
    et al.
    Tianjin University, Peoples R China.
    Zhang, C.
    CSIRO Data61, Australia; University of New South Wales, Australia.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Davey, R.
    CSIRO Food and Nutr, Australia.
    Bischof, L.
    CSIRO Data61, Australia.
    Vallotton, P.
    CSIRO Data61, Australia; ETH, Switzerland.
    Lovell, D.
    CSIRO Data61, Australia; Queensland University of Technology, Australia.
    Hope, S.
    CSIRO Food and Nutr, Australia.
    Schmoelzl, S.
    CSIRO Food and Nutr, Australia.
    Sun, C.
    CSIRO Data61, Australia.
    Detection of tubule boundaries based on circular shortest path and polar-transformation of arbitrary shapes2016In: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 264, no 2, p. 127-142Article in journal (Refereed)
    Abstract [en]

    In studies of germ cell transplantation, counting cells and measuring tubule diameters from different populations using labelled antibodies are important measurement processes. However, it is slow and sanity grinding to do these tasks manually. This paper proposes a way to accelerate these processes using a new image analysis framework based on several novel algorithms: centre points detection of tubules, tubule shape classification, skeleton-based polar-transformation, boundary weighting of polar-transformed image, and circular shortest path smoothing. The framework has been tested on a dataset consisting of 27 images which contain a total of 989 tubules. Experiments show that the detection results of our algorithm are very close to the results obtained manually and the novel approach can achieve a better performance than two existing methods. Lay description In studies of germ cell transplantation, counting cells and measuring tubule diameters from different populations using labelled antibodies are important measurement processes. However, it is slow and sanity grinding to do these tasks manually. This paper proposes a way to accelerate these processes using a new image analysis framework based on several novel algorithms: center points detection of tubules, tubule shape classification, skeleton based polar-transformation, boundary weighting of polar-transformed image, and circular shortest path smoothing. The framework has been tested on a dataset consisting of 27 images which contain a total of 989 tubules. Experiments show that the detection results of our algorithm are very close to the results obtained manually and the novel approach can achieve a better performance than two existing methods.

  • 104.
    Su, Ran
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT 2600, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW 1670, Australia.
    Pham, Tuan D
    The University of Aizu, Aizu-Wakamatsu, Fukushima 965-8580, Japan.
    Junction detection for linear structures2011Conference paper (Refereed)
    Abstract [en]

    This paper presents a method for detecting junctions in an image with linear structures. The candidate junction points are selected through the combination of correlation matrix and Hessian information; then the branches of the junctions are found according to the intensity information and the correlation value between intensity profile of cross sections and a Gaussian‐shaped template. Junction detection results for neurite images are provided.

  • 105.
    Sun, Changming
    et al.
    Digital Productivity Flagship, CSIRO .
    Bednarz, Tomasz
    Digital Productivity Flagship, CSIRO .
    Pham, Tuan D
    The University of Aizu .
    Vallotton, Pascal
    Digital Productivity Flagship, CSIRO .
    Wang, Dadong
    Digital Productivity Flagship, CSIRO .
    Signal and Image Analysis for Biomedical and Life Sciences2015Book (Other academic)
    Abstract [en]

    With an emphasis on applications of computational models for solving modern challenging problems in biomedical and life sciences, this book aims to bring collections of articles from biologists, medical/biomedical and health science researchers together with computational scientists to focus on problems at the frontier of biomedical and life sciences. The goals of this book are to build interactions of scientists across several disciplines and to help industrial users apply advanced computational techniques for solving practical biomedical and life science problems. This book is for users in the fields of biomedical and life sciences who wish to keep abreast with the latest techniques in signal and image analysis. The book presents a detailed description to each of the applications. It can be used by those both at graduate and specialist levels.

  • 106.
    Sun, Changming
    et al.
    Digital Productivity Flagship, CSIRO .
    Bednarz, Tomasz
    Digital Productivity Flagship, CSIRO .
    Pham, Tuan D
    The University of Aizu, Fukushima, Japan.
    Vallotton, Pascal
    Digital Productivity Flagship, CSIRO .
    Wang, Dadong
    Digital Productivity Flagship, CSIRO .
    Signal and Image Analysis for Biomedical and Life Sciences Preface: Emphasis on applications of computational models2015Book (Other academic)
    Abstract [en]

    With an emphasis on applications of computational models for solving modern challenging problems in biomedical and life sciences, this book aims to bring collections of articles from biologists, medical/biomedical and health science researchers together with computational scientists to focus on problems at the frontier of biomedical and life sciences. The goals of this book are to build interactions of scientists across several disciplines and to help industrial users apply advanced computational techniques for solving practical biomedical and life science problems. This book is for users in the fields of biomedical and life sciences who wish to keep abreast with the latest techniques in signal and image analysis. The book presents a detailed description to each of the applications. It can be used by those both at graduate and specialist levels.

  • 107.
    Tan, Xiao
    et al.
    Department of Computer Science, University of Hong Kong, Hong Kong.
    Sun, Changming
    CSIRO Digital Productivity, Sydney, NSW, Australia.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Edge-aware filtering with local polynomial approximation and rectangle based weighting2016In: IEEE Transactions on Cybernetics, ISSN 2168-2267, E-ISSN 2168-2275, Vol. 46, no 12, p. 2693-2705Article in journal (Refereed)
    Abstract [en]

    This paper presents a novel method for performing guided image filtering using local polynomial approximation (LPA) with range guidance. In our method, the LPA is introduced into a multipoint framework for reliable model regression and better preservation on image spatial variation which usually contains the essential information in the input image. In addition, we develop a weighting scheme which has the spatial flexibility during the filtering process. All components in our method are efficiently implemented and a constant computation complexity is achieved. Compared with conventional filtering methods, our method provides clearer boundaries and performs especially better in recovering spatial variation from noisy images. We conduct a number of experiments for different applications: depth image upsampling, joint image denoising, details enhancement, and image abstraction. Both quantitative and qualitative comparisons demonstrate that our method outperforms state-of-the-art methods.

  • 108.
    Tan, Xiao
    et al.
    The University of New South Wales, Canberra, ACT 2600, Australia; CSIRO Computational Informatics, Locked Bag 17, North Ryde, NSW 1670, Australia.
    Sun, Changming
    CSIRO Computational Informatics, Locked Bag 17, North Ryde, NSW 1670, Australia.
    Sirault, Xavier
    CSIRO Agriculture Flagship, Clunies Ross Street, Canberra, ACT 2601, Australia.
    Furbank, Robert
    CSIRO Agriculture Flagship, Clunies Ross Street, Canberra, ACT 2601, Australia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, The University of Aizu, Fukushima 965-8580, Japan.
    Feature matching in stereo images encouraging uniform spatial distribution2015In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 48, no 8, p. 2530-2542Article in journal (Refereed)
    Abstract [en]

    Finding feature correspondences between a pair of stereo images is a key step in computer vision for 3D reconstruction and object recognition. In practice, a larger number of correct correspondences and a higher percentage of correct matches are beneficial. Previous researches show that the spatial distribution of correspondences are also very important especially for fundamental matrix estimation. So far, no existing feature matching method considers the spatial distribution of correspondences. In our research, we develop a new algorithm to find good correspondences in all the three aspects mentioned, i.e., larger number of correspondences, higher percentage of correct correspondences, and better spatial distribution of correspondences. Our method consists of two processes: an adaptive disparity smoothing filter to remove false correspondences based on the disparities of neighboring correspondences and a matching exploration algorithm to find more correspondences according to the spatial distribution of correspondences so that the correspondences are as uniformly distributed as possible in the images. To find correspondences correctly and efficiently, we incorporate the cheirality constraint under an epipole polar transformation together with the epipolar constraint to predict the potential location of matching point. Experiments demonstrate that our method performs very well on both the number of correct correspondences and the percentage of correct correspondences; and the obtained correspondences are also well distributed over the image space.

  • 109.
    Tan, Xiao
    et al.
    SEIT of UNSW Canberra Canberra, ACT, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW, Australia.
    Sirault, Xavier
    CSIRO Plant Industry, Canberra, ACT, Australia.
    Furbank, Robert
    CSIRO Plant Industry, Canberra, ACT, Australia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, The University of Aizu, Aizu-Wakamatsu Fukushima, Japan.
    Tree structural watershed for stereo matching2012In: IVCNZ '12,  Proceedings of the 27th Conference on Image and Vision Computing New Zealand, ACM Digital Library, 2012, p. 340-345Conference paper (Other academic)
    Abstract [en]

    We present a new method for dense stereo matching based on a tree structural cost volume watershed (TSCVW) and a region combination (RC) process. Given a cost volume as the data cost and an initial segmentation result, the proposed TSCVW method reliably estimates the disparities in a segment by using energy optimization to control plane segmentation and plane fitting. Then the disparities in the incorrectly fitted and occluded regions are refined using our RC process. Experimental results show that our method is very robust to different initial segmentation results and the shape of a segment. The comparison between our algorithm and the current state-of-the-art algorithms on the Middlebury website shows that our algorithm is very competitive.

  • 110.
    Tan, Xiao
    et al.
    The University of Hong Kong, Pokfulam, Hong Kong.
    Sun, Changming
    CSIRO Computational Informatics, North Ryde, NSW, Australia.
    Wong, Kwan-YeeK.
    The University of Hong Kong, Pokfulam, Hong Kong.
    Pham, Tuan
    Aizu Research Cluster for Medical Engineering and Informatics, The University of Aizu, Fukushima, Japan.
    Guided image completion by confidence propagation2016In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 50, p. 210-222Article in journal (Refereed)
    Abstract [en]

    This paper presents a new guided image completion method which fills any missing values by considering information from a guidance image. We develop a confidence propagation scheme that allows the filling process to be carried out simultaneously without the need of deciding the filling order. We conduct experiments in several applications where the problem can be formulated into a guided image completion problem, such as interactive segmentation and colorization. The experimental results show that our method provides good results and succeeds in situations where conventional methods fail. In addition, as all building blocks are parallel processes, our method is much suitable for hardware acceleration.

  • 111.
    Thang, Truong Cong
    et al.
    University of Aizu, Aizuwakamatsu, Japan.
    Tran, Huyen T
    Hanoi University of Science and Technology, Hanoi, Vietnam.
    Trong, Vo D
    Vietnam Academy of Science and Technology, Hanoi, Vietnam.
    Nguyen, Duc V
    University of Aizu, Aizuwakamatsu, Japan.
    Le, Hung T
    University of Aizu, Aizuwakamatsu, Japan.
    Pham, Tuan D
    University of Aizu, Aizuwakamatsu, Japan.
    Design and implementation of an e-Health system for depression detection2015Conference paper (Refereed)
    Abstract [en]

    We present the design and implementation of a cost-effective e-Health system for automatic depression detection. The system is based on a client-server architecture, where clients are popular mobile devices. For practical deployment, various factors that affect the accuracy and speed of depression detection are discussed and evaluated with extensive experiments.

  • 112.
    To, Cuong C
    et al.
    ADFA School of Information Technology and Electrical Engineering, The University of New South Wales, Canberra, ACT, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    Analysis of cancer data using evolutionary computation2009In: Computational Biology: Issues and Applications in Oncology / [ed] Tuan Pham, Springer-Verlag New York, 2009, p. 125-147Chapter in book (Refereed)
    Abstract [en]

    We present several methods based on evolutionary computation for classification of oncology data. The results in comparisons with other existing techniques show that our evolutionary computation-based methods are superior in most cases. Evolutionary computation is effective in this study because it can offer efficiency in searching in high-dimension space, particularly in nonlinear optimization and hard optimization problems. The first part of this chapter is the review of some previous work on cancer classification. The second part is an overview of evolutionary computation. The third part focuses on methods based on evolutionary computation and their applications on oncology data. Finally, this chapter concludes with some remarks and suggestions for further investigation.

  • 113.
    To, Cuong C
    et al.
    The University of New South Wales ADFA, Canberra ACT 2600 .
    Pham, Tuan D
    The University of New South Wales ADFA, Canberra ACT 2600 .
    Understanding predictability of bio-signals using genetic algorithms and sample entropy2009In: Proceedings of the 2nd WSEAS international conference on Biomedical electronics and biomedical informatics, 2009, p. 47-51Conference paper (Refereed)
    Abstract [en]

    Entropy methods (approximate and sample entropy) have been studied to measure the complexity or predictability of finite length time series. The identification of parameters of this entropy family is indispensable task to enable the measure of predictability of time-series data. So far, there have been no general rules to select these parameters; they rather depend on particular problems. In this paper, we introduce a genetic-algorithm based entropy method which optimally selects these parameters in the sense that the discrimination between healthy and pathologic group’s entropy is maximized.

  • 114.
    Tran, Dat T
    et al.
    School of Information Sciences and Engineering University of CanberraC ACT 2601 AUSTRALIA.
    Pham, Tuan D
    Bioinformatics Applications Research Centre School of Information Technology James Cook University Townsville, Australia.
    A combined Markov and noise clustering modeling method for cell phase classification2006In: WSEAS Transactions on Biology and Biomedicine, ISSN 1109-9518, E-ISSN 2224-2902, Vol. 3, no 3, p. 161-166Article in journal (Refereed)
    Abstract [en]

    This paper proposes a classification method of cell nuclei in different mitotic phases using a combined Markov and noise clustering modeling technique. The method was tested with the data set containing 379519 cells in 892 cell sequences for 5 phases extracted from real image sequences recorded at every fifteen minutes with a time-lapse fluorescence microscopy. Experimental results showed that the proposed method performed better than the k-means modeling method.

  • 115.
    Tran, Dat T
    et al.
    University of Canberra, Canberra, ACT, Australia .
    Pham, Tuan D
    Discipline of Information Technology, James Cook University, Australia.
    Recent advances in cell classification for cancer research and drug discovery2009In: Computational Biology: Issues and Applications in Oncology / [ed] Tuan Pham, Springer-Verlag New York, 2009, p. 205-226Chapter in book (Refereed)
    Abstract [en]

    Drug effects on cancer cells are investigated through measuring cell cycle progression in individual cells as a function of time. This investigation requires the processing and analysis of huge amounts of image data obtained in time-lapse microscopy. Manual image analysis is very time consuming thus costly, potentially inaccurate, and poorly reproducible. Stages of an automated cellular imaging analysis consist of segmentation, feature extraction, classification, and tracking of individual cells in a dynamic cellular population. The feature extraction and classification of cell phases are considered the most difficult tasks of such analysis. We review several techniques for feature extraction and classification. We then present our work on an automated feature weighting technique for feature selection and combine this technique with cellular phase modeling techniques for classification. These combined techniques perform the two most difficult tasks at the same time and enhance the classification performance. Experimental results have shown that the combined techniques are effective and have potential for higher performance.

  • 116.
    Wang, Bing
    et al.
    MRI-based age prediction using hidden Markov models.
    Pham, Tuan D
    Bioinformatics Research Group, School of Engineering and Information Technology, The University of New South Wales, Canberra ACT 2600, Australia.
    MRI-based age prediction using hidden Markov models2011In: Journal of Neuroscience Methods, ISSN 0165-0270, E-ISSN 1872-678X, Vol. 199, no 1, p. 140-145Article in journal (Refereed)
    Abstract [en]

    Cortical thinning and intracortical gray matter volume losses are widely observed in normal ageing, while the decreasing rate of the volume loss in subjects withneurodegenerative disorders such as Alzheimer's disease is reported to be faster than the average speed. Therefore, neurodegenerative disease is considered as accelerated ageing. Accurate detection of accelerated ageing based on the magnetic resonance imaging (MRI) of the brain is a relatively new direction of research in computational neuroscience as it has the potential to offer positive clinical outcome through early intervention. In order to capture the faster structural alterations in the brain with ageing, we propose in this paper a computational approach for modelling the MRI-based structure of the brain using the framework of hidden Markov models, which can be utilized for age prediction. Experiments were carried out on healthy subjects to validate its accuracy and its robustness. The results have shown its ability of predicting the brain age with an average normalized age-gap error of two to three years, which is superior to several recently developed methods for brain age prediction.

  • 117.
    Wang, Yulin
    et al.
    Wuhan University, China.
    Pham, TuanLinköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.Vozenilek, VitPalacký Univ. Olomouc, Czech Republic.Zhang, DavidHong Kong Polytechnic University .Xie, YiWuhan University, China.
    Volume 10225. Eighth International Conference on Graphic and Image Processing (ICGIP 2016)2017Conference proceedings (editor) (Refereed)
  • 118.
    Xiao, Yi
    et al.
    Bioinformatics Research Group School of Engineering and Information Technology The University of New South Wales Canberra, ACT 2600, Australia.
    Pham, Tuan D
    Bioinformatics Research Group School of Engineering and Information Technology The University of New South Wales Canberra, ACT 2600, Australia.
    Chang, Jeff
    Pathology Department Center for Biotechnology and Bioinformatics The Methodist Hospital Research Institute Weill Cornell Medical College Houston, TX 77030, USA.
    Zhou, Xiaobo
    Pathology Department Center for Biotechnology and Bioinformatics The Methodist Hospital Research Institute Weill Cornell Medical College Houston, TX 77030, USA.
    Symmetry-based presentation for stem-cell image segmentation2011Conference paper (Refereed)
    Abstract [en]

    Cancer stem cells have been isolated from many tumors, including breast, brain, colon, head and neck, lung, pancreas, and prostate tumors. Advances in stem cell biology and animal models help better characterization of cancer stem cells, including the cells of origin, molecular and cellular properties, functions in cancer initiation and development, treatment response, and drug resistance. An important and challenging task in image analysis of stem cells is the image segmentation. A difficulty is to segment aggregated cells that are deformed and occluded. Watershed transform and multiscale morphological operation are the common methods for this purpose, as they are robust against arbitrary shaping and the occlusion of cells. Notwithstanding their high robustness, the two methods are still limited in their applications in the cases with cells suffering perturbations and deformation during cell growth. In this paper, we propose a novel symmetry axis transformation for stem-cell image segmentation. Our algorithm was validated by its comparison with both watershed transform and multiscale morphological operation. Improved segmentation performance in terms of precision (up to 2.2% comparing to watershed; and up to 0.6% comparing to multiscale morphological operation) was achieved using 5197 cell images in which 291 cells are three mutually touching.

  • 119.
    Xiao, Yi
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT, Australia.
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT, Australia.
    Jia, Xiuping
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT, Australia.
    Zhou, Xiaobo
    Centre for Biotechnology and Informatics, The Methodist Hospital Research Institute & Cornell University, Houston, TX, USA.
    Yan, Hong
    Department of Electronic Engineering, City University of Hong Kong, Hong Kong.
    Correlation-based cluster-space transform for major adverse cardiac event prediction2010In: IEEE International Conference on Systems Man and Cybernetics (SMC), Institute of Electrical and Electronics Engineers (IEEE), 2010, p. 2003-2007Conference paper (Refereed)
    Abstract [en]

    This paper investigates the affect of variation of patterns in protein profiles to the identification of disease-specific biomarkers. A correlation-based cluster-space transform is applied to mass spectral data for predicting major adverse cardiac events (MACE). Training and testing data are transformed into cluster spaces by correlation distance based clustering, respectively. Data in the testing cluster that falls into a pair of training clusters is classified by a supervised classifier. Experiment results have shown that proteomic spectra of MACE which vary with certain patterns could be separated by the correlation-based clustering. The cluster-space transform allows better classification accuracy than single-clustered class method for separating disease and healthy samples.

  • 120.
    Xu, Jin Wei
    et al.
    Bioinformatics Research Group School of Engineering and Information Technology The University of New South Wales Canberra, ACT 2600, Australia .
    Pham, Tuan D.
    Bioinformatics Research Group School of Engineering and Information Technology The University of New South Wales Canberra, Australia .
    Zhou, Xiaobo
    The Methodist Hospital Research Institute Cornell University Houston, TX 77030, USA.
    A double thresholding method for cancer stem cell detection2011Conference paper (Refereed)
    Abstract [en]

    Image analysis of cancer cells is important for cancer diagnosis and therapy, because it recognized as the most efficient and effective way to observe its proliferation. For the purpose of adaptive and accurate cancer cell image segmentation, a double threshold segmentation method is proposed in this paper. Based on a single gray-value histogram of the RGB color space, a double threshold, the key parameters of threshold segmentation can be fixed by a fitted-curve of the RGB component histogram. As reasonable thresholds confirmed, binary segmentation dependent on two thresholds, will be put into practice and result in binary image. With the post-processing of mathematical morphology and division of whole image, the better segmentation result can be finally achieved. By the comparison with other advanced segmentation methods such as level set and active contour, the proposed double thresholding has been found as the simplest strategy with shortest processing time as well as highest accuracy. The proposed method can be effectively used in the detection and recognition of cancer stem cells in images.

  • 121.
    Xu, Jinwei
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    Pham, Tuan D
    School of Computer Science and Engineering, Research Center for Advanced Information Science and Technology, The University of Aizu, Aizu-Wakamatsu City, Fukushima, Japan.
    Robust impulse-noise filtering for biomedical images using numerical interpolation2012In: Image Analysis and Recognition: 9th International Conference, ICIAR 2012, Aveiro, Portugal, June 25-27, 2012. Proceedings, Part II / [ed] Aurélio Campilho; Mohamed Kamel, Springer Berlin/Heidelberg, 2012, p. 146-155Conference paper (Refereed)
    Abstract [en]

    Analysis of molecular and medical images is an important area of interdisciplinary research. Accurate interpretation and understanding of those images is increasingly demanding because it opens doors to accurate diagnoses of diseases and novel biomedical discovery. During the image collection, imaging devices are quite often interfered by various noise sources. Impulse noise degrades biomedical image details such as edges, contours and texture. In this paper we present a robust technique for filtering impulse-noise degraded biomedical images. The proposed filter is based on noise detector and cubic interpolation. Experimental results on several types of biomedical images and comparisons with several existing noise-filtering models have demonstrated that not only the proposed filter is effective for noise removal but also for image detail preservation.

  • 122. Xu, Jinwei
    et al.
    Pham, Tuan D
    School of Computer Science and Engineering Research Center for Advanced Information Science and Technology The University of Aizu Aizu-Wakamatsu City, Fukushima, 965-8580, Japan.
    Robust impulse-noise filtering for biomedical images using numerical interpolation2012In: Image Analysis and Recognition / [ed] Campilho, Aurélio and Kamel, Mohamed, Berlin, Heidelberg: Springer Berlin/Heidelberg, 2012, p. 146-155Chapter in book (Other academic)
    Abstract [en]

    Analysis of molecular and medical images is an important area of interdisciplinary research. Accurate interpretation and understanding of those images is increasingly demanding because it opens doors to accurate diagnoses of diseases and novel biomedical discovery. During the image collection, imaging devices are quite often interfered by various noise sources. Impulse noise degrades biomedical image details such as edges, contours and texture. In this paper we present a robust technique for filtering impulse-noise degraded biomedical images. The proposed filter is based on noise detector and cubic interpolation. Experimental results on several types of biomedical images and comparisons with several existing noise-filtering models have demonstrated that not only the proposed filter is effective for noise removal but also for image detail preservation.

  • 123.
    Yu, Donggang
    et al.
    University of Newcastle, NSW 2308, Australia.
    Jin, Jesse S
    University of Newcastle, NSW 2308, Australia.
    Luo, Suhuai
    University of Newcastle, NSW 2308, Australia.
    Lai, Wei
    University of Technology Hawthorn, VIC3122, Australia.
    Park, Mira
    University of Newcastle, NSW 2308, Australia.
    Pham, Tuan D
    The University of New South Wales Canberra,ACT2600,Australia.
    Shape analysis and recognition based on skeleton and morphological structure2010In: 5th European Conference onColour in Graphics, Imaging, and Vision12th International Symposium onMultispectral Colour Science, 2010, p. 118-123Conference paper (Refereed)
    Abstract [en]

    This paper presents a novel and effective method of shape analysis and recognition based on skeleton and morphological structure. A series of preprocessing algorithms, smooth following and liberalization are introduced, and series of morphological structural points of image contour are extracted and merged. A series of basic shapes and a main shape of object image are described and segmented based on skeleton and morphological structure. Object shape is efficiently analyzed and recognized based on the extracted series of basic shapes and main shape. Comparing with other methods, the proposed method need not sample training set. Also, the new method can be used to analyze and recognize the shape structure of any shape, and there is no any requirement for the processed image data set. The new method can be used in image analysis, intelligent recognition, techniques, applications, systems and tools.

  • 124.
    Yu, Donggang
    et al.
    University of Newcastle, NSW, Australia.
    Jin, Jesse S
    University of Newcastle, NSW, Australia.
    Luo, Suhuai
    University of Newcastle, NSW, Australia.
    Pham, Tuan D
    The University of New South Wales, Canberra, ACT, Australia.
    Lai, Wei
    Swinburne University of Technology, Hawthorn, VIC, Australia.
    Description, Recognition and Analysis of Biological Images2010In: CP1210, 2009 International Symposium on Computational Models for Life Sciences (CMLS ’09) / [ed] Tuan Pham; Xiaobo Zhou, American Institute of Physics (AIP), 2010, Vol. 1210, p. 23-42Conference paper (Other academic)
    Abstract [en]

    Description, recognition and analysis biological images plays an important role for human to describe and understand the related biological information. The color images are separated by color reduction. A new and efficient linearization algorithm is introduced based on some criteria of difference chain code. A series of critical points is got based on the linearized lines. The series of curvature angle, linearity, maximum linearity, convexity, concavity and bend angle of linearized lines are calculated from the starting line to the end line along all smoothed contours. The useful method can be used for shape description and recognition. The analysis, decision, classification of the biological images are based on the description of morphological structures, color information and prior knowledge, which are associated each other. The efficiency of the algorithms is described based on two applications. One application is the description, recognition and analysis of color flower images. Another one is related to the dynamic description, recognition and analysis of cell‐cycle images.

  • 125.
    Yu, Donggang
    et al.
    Bioinformatics Applications Research Centre, James Cook University, Australia.
    Pham, Tuan D
    Bioinformatics Applications Research Centre, James Cook University, Australia).
    Image Pattern Recognition-Based Morphological Structure and Applications2008In: Pattern recognition technologies and applications : recent advances / [ed] Brijesh Verma; Michael Blumenstein, 2008, p. 48-Chapter in book (Refereed)
    Abstract [en]

    This chapter describes a new pattern recognition method: pattern recognition-based morphological structure. First, smooth following and linearization are introduced based on difference chain codes. Second, morphological structural points are described in terms of smooth followed contours and linearized lines, and then the patterns of morphological structural points and their properties are given. Morphological structural points are basic tools for pattern recognitionbased morphological structure. Furthermore, we discuss how the morphological structure can be used to recognize and classify images. One application is document image processing and recognition, analysis and recognition of broken handwritten digits. Another one is dynamic analysis and recognition of cell-cycle screening based on morphological structures. Finally, a conclusion is given, including advantages, disadvantages, and future research.

  • 126.
    Yu, Donggang
    et al.
    James Cook University, Townsville, QLD 4811, Australia .
    Pham, Tuan D
    James Cook University, Townsville, QLD 4811, Australia .
    Yan, Hong
    City University of Hong Kong, Kowloon, Hong Kong .
    Lai, Wei
    Swinburne University of Technology, Melborne, VIC 3122, Australia .
    Crane, Denis I
    Griffith University, Nathan, Qld 4111, Australia .
    Segmentation and reconstruction of cultured neuron skeleton2007In: COMPUTATIONAL MODELS FOR LIFE SCIENCES—CMLS’07, 2007, Vol. 952, p. 21-30Conference paper (Refereed)
    Abstract [en]

    One approach to investigating neural death is through systematic studies of the changing morphology of cultured brain neurons in response to cellular challenges. Image segmentation and reconstruction methods developed to date to analyze such changes have been limited by the low contrast of cells. In this paper we present new algorithms that successfully circumvent these problems. The binary method is based on logical analysis of grey and distance difference of images. The spurious regions are detected and removed through use of a hierarchical window filter. The skeletons of binary cell images are extracted. The extension direction and connection points of broken cell skeletons are automatically determined, and broke neural skeletons are reconstructed. The spurious strokes are deleted based on cell prior knowledge. The efficacy of the developed algorithms is demonstrated here through a test of cultured brain neurons from newborn mice.

  • 127.
    Yu, Donggang
    et al.
    Bioinformatics Applications Research Centre, James Cook University Townsville, Australia.
    Pham, Tuan D
    Bioinformatics Applications Research Centre, James Cook University Townsville, Australia.
    Zhou, Xiaobo
    HCNR Centre for Bioinformatics Harvard Medical School, Boston, USA.
    Detection and Analysis of Cell Nuclear Phases2008In: Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008, Zagreb, Croatia, September 3-5, 2008, Proceedings, Part I / [ed] Ignac Lovrek, Robert J. Howlett and Lakhmi C. Jain, Springer Berlin/Heidelberg, 2008, p. 401-408Chapter in book (Refereed)
    Abstract [en]

    Automated analysis of molecular images has increasingly become an important research in computational life science. In this paper some new and efficient algorithms for detecting and analyzing cell phases of high-content screening are presented. The conceptual frameworks are based on the morphological features of cell nuclei. Furthermore, the novel detecting and analyzing strategies of feed-forward and feed-back of cell phases are proposed based on grey feature, cell shape, geometrical features and difference information of corresponding neighbor frames. Experiment results tested the efficiency of the new method.

  • 128.
    Yu, Donggang
    et al.
    School of Design, Communication and Information Technology, The University of Newcastle, Callaghan, NSW 2308, Australia.
    Pham, Tuan D
    School of Information Technology and Electrical Engineering, ADFA, The University of New South Wales, Canberra, ACT 2600, Australia.
    Zhou, Xiaobo
    HCNR Centre for Bioinformatics, Harvard Medical School, Boston, MA 02215, USA.
    Wong, Stephen TC
    HCNR Centre for Bioinformatics, Harvard Medical School, Boston, MA 02215, USA.
    Recognition and analysis of cell nuclear phases for high-content screening based on morphological features2009In: NOVA. The University of Newcastle’s Digital Repository, ISSN 0031-3203, Vol. 42, no 4, p. 498-508Article in journal (Refereed)
    Abstract [en]

    Automated analysis of molecular images has increasingly become an important research in computational life science. In this paper some new and efficient algorithms for recognizing and analyzing cell phases of high-content screening are presented. The conceptual frameworks are based on the morphological features of cell nuclei. The useful preprocessing includes: smooth following and linearization; extraction of morphological structural points; shape recognition based morphological structure; issue of touching cells for cell separation and reconstruction. Furthermore, the novel detecting and analyzing strategies of feed-forward and feed-back of cell phases are proposed based on gray feature, cell shape, geometrical features and difference information of corresponding neighbor frames. Experiment results tested the efficiency of the new method.

  • 129.
    Zhang, Bailing
    et al.
    Xi'an Jiaotong-Liverpool University .
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT 2600, Australia. A.
    Multiple features based two-stage hybrid classifier ensembles for subcellular phenotype images classification2010In: International Journal of Biometrics and Bioinformatics (IJBB), ISSN 1985-2347, Vol. 4, no 5, p. 176-193Article in journal (Refereed)
    Abstract [en]

    Subcellular localization is a key functional characteristic of proteins. As an interesting ``bio-image informatics\'\' application, an automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen systems for drug discovery or for early diagnosis of a disease. In this paper, we propose a two-stage multiple classifier system to improve classification reliability by introducing rejection option. The system is built as a cascade of two classifier ensembles. The first ensemble consists of set of binary SVMs which generalizes to learn a general classification rule and the second ensemble, which also include three distinct classifiers, focus on the exceptions rejected by the rule. A new way to induce diversity for the classifier ensembles is proposed by designing classifiers that are based on descriptions of different feature patterns. In addition to the Subcellular Location Features (SLF) generally adopted in earlier researches, three well-known texture feature descriptions have been applied to cell phenotype images, which are the local binary patterns (LBP), Gabor filtering and Gray Level Coocurrence Matrix (GLCM). The different texture feature sets can provide sufficient diversity among base classifiers, which is known as a necessary condition for improvement in ensemble performance. Using the public benchmark 2D HeLa cell images, a high classification accuracy 96% is obtained with rejection rate $21\\%$ from the proposed system by taking advantages of the complementary strengths of feature construction and majority-voting based classifiers\' decision fusions.

  • 130.
    Zhang, Bailing
    et al.
    Xi’an Jiaotong-Liverpool University, Suzhou, 215123, P.R.China.
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales.
    Phenotype recognition with combined features and random subspace classifier ensemble2011In: BMC Bioinformatics, ISSN 1471-2105, E-ISSN 1471-2105, Vol. 12, no 1, p. 1-14Article in journal (Refereed)
    Abstract [en]

    Automated, image based high-content screening is a fundamental tool for discovery in biological science. Modern robotic fluorescence microscopes are able to capture thousands of images from massively parallel experiments such as RNA interference (RNAi) or small-molecule screens. As such, efficient computational methods are required for automatic cellular phenotype identification capable of dealing with large image data sets. In this paper we investigated an efficient method for the extraction of quantitative features from images by combining second order statistics, or Haralick features, with curvelet transform. A random subspace based classifier ensemble with multiple layer perceptron (MLP) as the base classifier was then exploited for classification. Haralick features estimate image properties related to second-order statistics based on the grey level co-occurrence matrix (GLCM), which has been extensively used for various image processing applications. The curvelet transform has a more sparse representation of the image than wavelet, thus offering a description with higher time frequency resolution and high degree of directionality and anisotropy, which is particularly appropriate for many images rich with edges and curves. A combined feature description from Haralick feature and curvelet transform can further increase the accuracy of classification by taking their complementary information. We then investigate the applicability of the random subspace (RS) ensemble method for phenotype classification based on microscopy images. A base classifier is trained with a RS sampled subset of the original feature set and the ensemble assigns a class label by majority voting.

  • 131.
    Zhang, C
    et al.
    North Ryde, New South Wales 2113, Australia.
    Sun, C
    The University of New South Wales, Canberra,Australia.
    Pham, Tuan D.
    ‡Aizu Research Cluster for Medical Engineering and Informatics, Research Center for AdvancedInformation Science and Technology, The University of Aizu, Fukushima, Japan.
    Segmentation of clustered nuclei based on concave curve expansion2013In: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, ISSN 1365-2818, Vol. 251, no 1, p. 57-67Article in journal (Refereed)
    Abstract [en]

    Segmentation of nuclei from images of tissue sections is important for many biological and biomedical studies. Many existing image segmentation algorithms may lead to oversegmentation or undersegmentation for clustered nuclei images. In this paper, we proposed a new image segmentation algorithm based on concave curve expansion to correctly and accurately extract markers from the original images. Marker-controlled watershed is then used to segment the clustered nuclei. The algorithm was tested on both synthetic and real images and better results are achieved compared with some other state-of-the-art methods.

  • 132.
    Zhang, C
    et al.
    CSIRO Mathematics, Informatics and Statistics Division, North Ryde, New South Wales, Australia; School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT, Australia.
    Sun, C
    CSIRO Mathematics, Informatics and Statistics Division, North Ryde, New South Wales, Australia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu, Fukushima, Japan.
    Segmentation of clustered nuclei based on concave curve expansion2013In: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 251, no 1, p. 57-67Article in journal (Refereed)
    Abstract [en]

    Segmentation of nuclei from images of tissue sections is important for many biological and biomedical studies. Many existing image segmentation algorithms may lead to oversegmentation or undersegmentation for clustered nuclei images. In this paper, we proposed a new image segmentation algorithm based on concave curve expansion to correctly and accurately extract markers from the original images. Marker-controlled watershed is then used to segment the clustered nuclei. The algorithm was tested on both synthetic and real images and better results are achieved compared with some other state-of-the-art methods.

  • 133.
    Zhang, Chao
    et al.
    The University of New South Wales at the Australian Defence Force Academy, Canberra, Australia; CSIRO Mathematics, Informatics and Statistics, North Ryde, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, North Ryde, Australia.
    Pham, Tuan D
    The University of New South Wales at the Australian Defence Force Academy, Canberra,, Australia.
    Clustered nuclei splitting using curvature information2011Conference paper (Refereed)
    Abstract [en]

    Automated splitting of clustered nuclei from images of tissue sections is essential to many biomedical studies. Many existing image segmentation methods tend to produce over-segmented or under-segmented results for clustered nuclei images. In this paper, a new curvature information based image segmentation algorithm is proposed. Through combining curvature information with a distance map, our algorithm can extract correct markers corresponding to each nucleus. Afterwards, marker based watershed segmentation is used to segment the clustered nuclei. The algorithm is tested on both synthetic and real images. Experimental results show that our algorithm is accurate and robust to noise in segmentation of clustered nuclei.

  • 134.
    Zhang, Chao
    et al.
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW 1670, Australia /UNSW@ADFA, Canberra, ACT 2600, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW 1670, Australia.
    Pham, Tuan D
    School of Engineering and Information Technology, UNSW@ADFA, Canberra, ACT 2600, Australia.
    Vallotton, Pascal
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW 1670, Australia.
    Fenech, Michael
    CSIRO Food and Nutritional Sciences, Adelaide, SA 5000, Australia.
    Detection of nuclear buds based on ellipse fitting2010Conference paper (Refereed)
    Abstract [en]

    Assays of micronucleus are extensively used in genotoxicity testing and in monitoring of human exposure to genotoxic materials. As nuclear buds could be a new source of micronuclei formed in interphase, the assay of contents of nuclear bud in normal and comparison group is needed. In this paper, we proposed a new automatic nuclear buds detection algorithm based on ellipse fitting. Experimental results show that our algorithm is effective and efficient. We believe that this is the first report on automated nuclear bud detection for DNA damage scoring.

  • 135.
    Zhang, Chao
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia; CSIRO Computational Informatics, North Ryde, Australia.
    Sun, Changming
    CSIRO Computational Informatics, North Ryde, Australia.
    Su, Ran
    Bioinformatics Institute, Matrix, Singapore.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu, Fukushima, Japan.
    Clustered nuclei splitting via curvature information and gray-scale distance transform2015In: Journal of Microscopy, ISSN 0022-2720, E-ISSN 1365-2818, Vol. 259, no 1, p. 36-52Article in journal (Refereed)
    Abstract [en]

    Clusters or clumps of cells or nuclei are frequently observed in two dimensional images of thick tissue sections. Correct and accurate segmentation of overlapping cells and nuclei is important for many biological and biomedical applications. Many existing algorithms split clumps through the binarization of the input images; therefore, the intensity information of the original image is lost during this process. In this paper, we present a curvature information, gray scale distance transform, and shortest path splitting line-based algorithm which can make full use of the concavity and image intensity information to find out markers, each of which represents an individual object, and detect accurate splitting lines between objects using shortest path and junction adjustment. The proposed algorithm is tested on both synthetic and real nuclei images. Experiment results show that the performance of the proposed method is better than that of marker-controlled watershed method and ellipse fitting method.

  • 136.
    Zhang, Chao
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra ACT, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, North Ryde, NSW, Australia.
    Su, Ran
    School of Engineering and Information Technology, The University of New South Wales, Canberra ACT, Australia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu Aizu-Wakamatsu, Fukushima, Japan.
    Segmentation of clustered nuclei based on curvature weighting2012In: IVCNZ '12, Proceedings of the 27th Conference on Image and Vision Computing New Zealand, ACM Digital Library, 2012, p. 49-54Conference paper (Other academic)
    Abstract [en]

    Cluster of nuclei are frequently observed in thick tissue section images. It is very important to segment overlapping nuclei in many biomedical applications. Many existing methods tend to produce under segmented results when there is a high overlap rate. In this paper, we present a curvature weighting based algorithm which weights each pixel using the curvature information of its nearby boundaries to extract markers, each of which represents an object, from input images. Then we use marker-controlled watershed to obtain the final segmentation. Test results using both synthetic and real cell images are presented in the paper.

  • 137.
    Zhang, Chao
    et al.
    The University of New South Wales, Canberra, ACT, Australia .
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, NSW, Australia .
    Su, Ran
    The University of New South Wales, Canberra, ACT, Australia .
    Pham, Tuan D
    The University of Aizu, Fukushima, Japan .
    Segmentation of clustered nuclei based on curvature-weighting2012In: Proceedings of the 27th Conference on Image and Vision Computing New Zealand, 2012, p. 49-54Conference paper (Refereed)
    Abstract [en]

    Clusters of nuclei are frequently observed in thick tissue section images. It is very important to segment overlapping nuclei in many biomedical applications. Many existing methods tend to produce under segmented results when there is a high overlap rate. In this paper, we present a curvature weighting based algorithm which weights each pixel using the curvature information of its nearby boundaries to extract markers, each of which represents an object, from input images. Then we use marker-controlled watershed to obtain the final segmentation. Test results using both synthetic and real cell images are presented in the paper.

  • 138.
    Zhang, Guangyun
    et al.
    The University of New South Wales, Campbell, ACT 2600, Australia .
    Jia, Xiuping
    The University of New South Wales, Campbell, ACT 2600, Australia .
    Pham, Tuan D
    The University of New South Wales, Campbell, ACT 2600, Australia .
    Crane, Denis I
    Eskitis Institute for Cell and Molecular Therapies, and School of Biomolecular and Physical Sciences, Griffith University, Nathan Campus, QLD 4111, Australia .
    Multistage spatial property based segmentation for quantification of fluorescence distribution in cells2010Conference paper (Refereed)
    Abstract [en]

    The interpretation of the distribution of fluorescence in cells is often by simple visualization of microscope‐derived images for qualitative studies. In other cases, however, it is desirable to be able to quantify the distribution of fluorescence using digital image processing techniques. In this paper, the challenges offluorescence segmentation due to the noise present in the data are addressed. We report that intensity measurements alone do not allow separation of overlapping data between target and background. Consequently, spatial properties derived from neighborhood profile were included. Mathematical Morphological operations were implemented for cell boundary extraction and a window based contrast measure was developed for fluorescence puncta identification. All of these operations were applied in the proposed multistage processing scheme. The testing results show that the spatial measures effectively enhance the target separability.

  • 139.
    Zhong, Guoqiang
    et al.
    Ocean University of China, Qingdao, China.
    Yao, Hui
    Ocean University of China, Qingdao, China.
    Liu, Yutong
    Ocean University of China, Qingdao, China.
    Hong, Chen
    Ocean University of China, Qingdao, China.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering.
    Classification of photographed document images based on deep-learning features2017In: Eighth International Conference on Graphic and Image Processing (ICGIP 2016) / [ed] Tuan D. Pham; Vit Vozenilek; Zhu Zeng, SPIE - International Society for Optical Engineering, 2017, Vol. 10225, article id UNSP 102250XConference paper (Refereed)
    Abstract [en]

    In this paper, we propose two new problems related to classification of photographed document images, and based on deep learning methods, present the baseline solutions for these two problems. The first problem is that, for some photographed document images, which book do they belong to? The second one is, for some photographed document images, what is the type of the book they belong to? To address these two problems, we apply “AexNet” to the collected document images. Using the pre-trained “AlexNet” on the ImageNet data set directly, we obtain 92.57% accuracy for the book-name classification and 93.33% accuracy for the book-type one. After fine-tuning on the training set of the photographed document images, the accuracy of the book-name classification increases to 95.54% and that of the booktype one to 95.42%. To our best knowledge, although there exist many image classification algorithm, no previous work has targeted to these two challenging problems. In addition, the experiments demonstrate that deep-learning features outperform features extracted with traditional image descriptors on these two problems. 

  • 140.
    Zhou, Xiaowei
    et al.
    Ocean University of China, China.
    Zhong, Guoqiang
    Ocean University of China, China.
    Qi, Lin
    Ocean University of China, China.
    Dong, Junyu
    Ocean University of China, China.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Mao, Jianzhou
    Macau Univ. of Science and Technology, China.
    Surface height map estimation from a single image using convolutional neural networks2017In: Proceedings of SPIE, Eighth International Conference on Graphic and Image Processing, SPIE - International Society for Optical Engineering, 2017, Vol. 10225, article id UNSP 1022524-1Conference paper (Refereed)
123 101 - 140 of 140
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf