The Experts below are selected from a list of 360 Experts worldwide ranked by ideXlab platform

Mathieu Fauvel - One of the best experts on this subject based on the ideXlab platform.

  • Advances in Spectral-Spatial Classification of Hyperspectral Images
    Proceedings of the IEEE, 2013
    Co-Authors: Mathieu Fauvel, Yuliya Tarabalka, Jon Atli Benediktsson, Jocelyn Chanussot, James Tilton
    Abstract:

    Recent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes character- istics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three Presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods.

  • Advances in Spectral-Spatial Classification of Hyperspectral Images
    Proceedings of the IEEE, 2013
    Co-Authors: Mathieu Fauvel, Yuliya Tarabalka, Jon Atli Benediktsson, Jocelyn Chanussot, James C. Tilton
    Abstract:

    International audienceRecent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes character- istics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three Presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods

Keyvan Hashtrudi-zaad - One of the best experts on this subject based on the ideXlab platform.

  • Intra-subject Elastic Registration of 3D Ultrasound Images
    Medical Image Analysis, 2006
    Co-Authors: Pezhman Foroughi, Purang Abolmaesumi, Keyvan Hashtrudi-zaad
    Abstract:

    3D registration of ultrasound images is an important and fast-growing research area with various medical applications, such as image-guided radiotherapy and surgery. However, this registration process remains extremely challenging due to the deformation of soft tissue and the existence of speckles in these images. This paper presents a technique for intra-subject, intra-modality elastic registration of 3D ultrasound images. Using the general concept of attribute vectors, we define the corresponding voxels in the fixed and moving images. Our method does not require Presegmentation and does not employ any numerical optimization procedure. As the computational requirements are minimal, the method has potential use in real-time applications. The technique is implemented and tested on 3D ultrasound images of human liver, captured by a 3D ultrasound transducer. The results show that the method is sufficiently accurate and robust even in cases where artifacts such as shadows exist in the ultrasound data.

Hiromichi Fujisawa - One of the best experts on this subject based on the ideXlab platform.

  • 2004a). Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings
    2011
    Co-Authors: Cheng-lin Liu, Hiroshi Sako, Senior Member, Hiromichi Fujisawa
    Abstract:

    Abstract—In integrated segmentation and recognition of character strings, the underlying classifier is trained to be resistant to noncharacters. We evaluate the performance of state-of-the-art pattern classifiers of this kind. First, we build a baseline numeral string recognition system with simple but effective Presegmentation. The classification scores of the candidate patterns generated by Presegmentation are combined to evaluate the segmentation paths and the optimal path is found using the beam search strategy. Three neural classifiers, two discriminative density models, and two support vector classifiers are evaluated. Each classifier has some variations depending on the training strategy: maximum likelihood, discriminative learning both with and without noncharacter samples. The string recognition performances are evaluated on the numeral string images of the NIST Special Database 19 and the zipcode images of the CEDAR CDROM-1. The results show that noncharacter training is crucial for neural classifiers and support vector classifiers, whereas, for the discriminative density models, the regularization of parameters is important. The string recognition results compare favorably to the best ones reported in the literature though we totally ignored the geometric context. The best results were obtained using a support vector classifier, but the neural classifiers and discriminative density models show better trade-off between accuracy and computational overhead. Index Terms—Numeral string recognition, integrated segmentation and recognition, noncharacter resistance, character classification, neural classifiers, discriminative density models, support vector classifiers. æ

  • Effects of classifier structures and training regimes on integrated segmentation and recognition of handwritten numeral strings
    IEEE transactions on pattern analysis and machine intelligence, 2004
    Co-Authors: Cheng-lin Liu, Hiroshi Sako, Hiromichi Fujisawa
    Abstract:

    In integrated segmentation and recognition of character strings, the underlying classifier is trained to be resistant to noncharacters. We evaluate the performance of state-of-the-art pattern classifiers of this kind. First, we build a baseline numeral string recognition system with simple but effective Presegmentation. The classification scores of the candidate patterns generated by Presegmentation are combined to evaluate the segmentation paths and the optimal path is found using the beam search strategy. Three neural classifiers, two discriminative density models, and two support vector classifiers are evaluated. Each classifier has some variations depending on the training strategy: maximum likelihood, discriminative learning both with and without noncharacter samples. The string recognition performances are evaluated on the numeral string images of the NIST special database 19 and the zipcode images of the CEDAR CDROM-1. The results show that noncharacter training is crucial for neural classifiers and support vector classifiers, whereas, for the discriminative density models, the regularization of parameters is important. The string recognition results compare favorably to the best ones reported in the literature though we totally ignored the geometric context. The best results were obtained using a support vector classifier, but the neural classifiers and discriminative density models show better trade-off between accuracy and computational overhead.

  • A robust method for recognition of monetary amount printed by checkwriter
    Systems and Computers in Japan, 2004
    Co-Authors: Masashi Koga, Hiroshi Sako, Ryuji Mine, Tsukasa Yasue, Hiromichi Fujisawa
    Abstract:

    We propose a new method to recognize monetary amounts printed by checkwriters. We applied a character segmentation method robust to noise and a bottom-up parsing for postprocessing. In the proposed method, the input image is segmented both horizontally and vertically in the Presegmentation step. A context-free grammar describes the linguistic constraints in the monetary amounts. We devised a new bottom-up parsing technique that interprets the results of character classification. We tested the validity of the new method using 1314 images. The correct ratio was 72.7p, which is 8.4 points higher than that of the conventional method. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(7): 49–60, 2004; Published online in Wiley InterScience (). DOI 10.1002sscj.10616

  • Lexicon-driven segmentation and recognition of handwritten character strings for Japanese address reading
    IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
    Co-Authors: Cheng-lin Liu, Masashi Koga, Hiromichi Fujisawa
    Abstract:

    This paper describes a handwritten character string recognition system for Japanese mail address reading on a very large vocabulary. The address phrases are recognized as a whole because there is no extra space between words. The lexicon contains 111,349 address phrases, which are stored in a trie structure. In recognition, the text line image is matched with the lexicon entries (phrases) to obtain reliable segmentation and retrieve valid address phrases. The paper first introduces some effective techniques for text line image preprocessing and Presegmentation. In Presegmentation, the text line image is separated into primitive segments by connected component analysis and touching pattern splitting based on contour shape analysis. In lexicon matching, consecutive segments are dynamically combined into candidate character patterns. An accurate character classifier is embedded in lexicon matching to select characters matched with a candidate pattern from a dynamic category set. A beam search strategy is used to control the lexicon matching so as to achieve real-time recognition. In experiments on 3,589 live mail images, the proposed method achieved correct rate of 83.68 percent while the error rate is less than 1 percent.

Klaus Scheffler - One of the best experts on this subject based on the ideXlab platform.

  • Task-Related Edge Density (TED)-A New Method for Revealing Dynamic Network Formation in fMRI Data of the Human Brain.
    PloS one, 2016
    Co-Authors: Gabriele Lohmann, Johannes Stelzer, Tilo Buschmann, Verena Zuber, Daniel S. Margulies, Andreas Bartels, Klaus Scheffler
    Abstract:

    The formation of transient networks in response to external stimuli or as a reflection of internal cognitive processes is a hallmark of human brain function. However, its identification in fMRI data of the human brain is notoriously difficult. Here we propose a new method of fMRI data analysis that tackles this problem by considering large-scale, task-related synchronisation networks. Networks consist of nodes and edges connecting them, where nodes correspond to voxels in fMRI data, and the weight of an edge is determined via task-related changes in dynamic synchronisation between their respective times series. Based on these definitions, we developed a new data analysis algorithm that identifies edges that show differing levels of synchrony between two distinct task conditions and that occur in dense packs with similar characteristics. Hence, we call this approach “Task-related Edge Density” (TED). TED proved to be a very strong marker for dynamic network formation that easily lends itself to statistical analysis using large scale statistical inference. A major advantage of TED compared to other methods is that it does not depend on any specific hemodynamic response model, and it also does not require a Presegmentation of the data for dimensionality reduction as it can handle large networks consisting of tens of thousands of voxels. We applied TED to fMRI data of a fingertapping and an emotion processing task provided by the Human Connectome Project. TED revealed network-based involvement of a large number of brain areas that evaded detection using traditional GLM-based analysis. We show that our proposed method provides an entirely new window into the immense complexity of human brain function.

  • PRNI - Correlation bundle statistics in fMRI data
    2014 International Workshop on Pattern Recognition in Neuroimaging, 2014
    Co-Authors: Gabriele Lohmann, Johannes Stelzer, Zuber, Tilo Buschmann, Michael Erb, Klaus Scheffler
    Abstract:

    Traditionally fMRI data analysis aims at identifying brain areas in which the amplitude of the BOLD signal responds to experimental stimulations. However, since the brain acts as a network, we would expect differential effects on network topology. Therefore, the target of statistical inference should not only be individual voxels or brain areas but rather network connections. Here we introduce a new approach to correlation-based statistics in fMRI. At the heart of our approach is the concept of correlation bundles as a functional analogy to anatomical fibre bundles. Statistical tests are applied to these bundles using large-scale inference methods such as FDR. We call this approach correlation bundle statistics (CBS). In contrast to previous correlation-based approaches to fMRI statistics, CBS does not require a Presegmentation or smoothing of the data so that anatomical specificity is preserved. The result of a CBS analysis is not a set of voxels or brain regions but rather a set of correlation bundles that are found to be significantly affected by some experimental manipulation.

James C. Tilton - One of the best experts on this subject based on the ideXlab platform.

  • Advances in Spectral-Spatial Classification of Hyperspectral Images
    Proceedings of the IEEE, 2013
    Co-Authors: Mathieu Fauvel, Yuliya Tarabalka, Jon Atli Benediktsson, Jocelyn Chanussot, James C. Tilton
    Abstract:

    International audienceRecent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes character- istics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three Presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods