The Experts below are selected from a list of 22656 Experts worldwide ranked by ideXlab platform

Stephan Olariu - One of the best experts on this subject based on the ideXlab platform.

Feiyun Cong - One of the best experts on this subject based on the ideXlab platform.

  • symmetrical singular value decomposition Representation for pattern recognition
    Neurocomputing, 2016
    Co-Authors: Yuhui Chen, Shuiguang Tong, Feiyun Cong
    Abstract:

    This paper proposes a novel and powerful pattern recognition method named symmetrical singular value decomposition Representation (SSVDR) and presents its application to face recognition. The SSVDR method is based on singular value decomposition (SVD) and symmetry prior. In this method, the given image is firstly decomposed into a composition of a set of base images by the singular value decomposition technique. Then, the first few base images (which can be proved to be the low-frequency asymmetrical base images) are turned into symmetrical base images according to facial symmetry. Finally, a new Representation of the original image is reestablished for the final recognition. For evaluating the performance of the SSVDR method, some experiments are conducted in two famous face databases: extended Yale B and CMU-PIE database. The experiment results show the proposed SSVDR method can reestablish a new Homogeneous Representation of the original image and has an encouraging performance on face recognition compared with the current state-of-the-art methods. A new method based on singular value decomposition (SVD) and symmetry prior for face recognition is proposed.More Homogeneous image Representation of the original image can be reestablished by our method.The non-uniformity is only deflated on the lower-frequency components of the original image.A significantly experiment performance compared with the current state-of-the-art methods.

Masayuki Fujita - One of the best experts on this subject based on the ideXlab platform.

Laurent Wendling - One of the best experts on this subject based on the ideXlab platform.

  • Color Object Recognition Based on Spatial Relations between Image Layers
    2015
    Co-Authors: Michaël Clément, Mickaël Garnier, Camille Kurtz, Laurent Wendling
    Abstract:

    The recognition of complex objects from color images is a challenging task, which is considered as a key-step in image analysis. Classical methods usually rely on structural or statistical descriptions of the object content, summarizing different image features such as outer contour, inner structure, or texture and color effects. Recently, a descriptor relying on the spatial relations between regions structuring the objects has been proposed for gray-level images. It integrates in a single Homogeneous Representation both shape information and relative spatial information about image layers. In this paper, we introduce an extension of this descriptor for color images. Our first contribution is to consider a segmentation algorithm coupled to a clustering strategy to extract the potentially disconnected color layers from the images. Our second contribution relies on the proposition of new strategies for the comparison of these descriptors, based on structural layers alignments and shape matching. This extension enables to recognize structured objects extracted from color images. Results obtained on two datasets of color images suggest that our method is efficient to recognize complex objects where the spatial organization is a discriminative feature.

  • VISAPP (1) - Color Object Recognition based on Spatial Relations between Image Layers
    Proceedings of the 10th International Conference on Computer Vision Theory and Applications, 2015
    Co-Authors: Michaël Clément, Mickaël Garnier, Camille Kurtz, Laurent Wendling
    Abstract:

    The recognition of complex objects from color images is a challenging task, which is considered as a key-step in image analysis. Classical methods usually rely on structural or statistical descriptions of the object content, summarizing different image features such as outer contour, inner structure, or texture and color effects. Recently, a descriptor relying on the spatial relations between regions structuring the objects has been proposed for gray-level images. It integrates in a single Homogeneous Representation both shape information and relative spatial information about image layers. In this paper, we introduce an extension of this descriptor for color images. Our first contribution is to consider a segmentation algorithm coupled to a clustering strategy to extract the potentially disconnected color layers from the images. Our second contribution relies on the proposition of new strategies for the comparison of these descriptors, based on structural layers alignments and shape matching. This extension enables to recognize structured objects extracted from color images. Results obtained on two datasets of color images suggest that our method is efficient to recognize complex objects where the spatial organization is a discriminative feature.

  • Object Description Based on Spatial Relations between Level-Sets
    2012
    Co-Authors: Mickaël Garnier, Thomas Hurtut, Laurent Wendling
    Abstract:

    Object recognition methods usually rely on either structural or statistical description. These methods aim at describing different types of information such as the outer contour, the inner structure or texture effects. Comparing two objects then comes down to averaging different data Representations which may be a tricky issue. In this paper, we introduce an object descriptor based on the spatial relations that structures object content. This descriptor integrates in a single Homogeneous Representation both shape information and relative spatial information about the object under consideration. We use this description in the context of image retrieval and show results on a butterfly image database compared with both GFD and SIFT descriptors.

  • DICTA - Object Description Based on Spatial Relations between Level-Sets
    2012 International Conference on Digital Image Computing Techniques and Applications (DICTA), 2012
    Co-Authors: Mickaël Garnier, Thomas Hurtut, Laurent Wendling
    Abstract:

    Object recognition methods usually rely on either structural or statistical description. These methods aim at describing different types of information such as the outer contour, the inner structure or texture effects. Comparing two objects then comes down to averaging different data Representations which may be a tricky issue. In this paper, we introduce an object descriptor based on the spatial relations that structures object content. This descriptor integrates in a single Homogeneous Representation both shape information and relative spatial information about the object under consideration. We use this description in the context of image retrieval and show results on a butterfly image database compared with both GFD and SIFT descriptors. These results show that our method is more efficient to distinguish the objects where the spatial organization is a discriminative feature.

Víctor M. Verdejo - One of the best experts on this subject based on the ideXlab platform.

  • Determinability of Perception as Homogeneity of Representation
    Review of Philosophy and Psychology, 2018
    Co-Authors: Víctor M. Verdejo
    Abstract:

    Recent philosophical and empirical contributions strongly suggest that perception attributes determinable properties to its objects. But a characterisation of determinability via attributed properties is restricted to the level of content and does not capture the difference between perceptual belief and perception on this score. In this paper, I propose a formal way of cashing out the difference between determinable belief and perception. On the view presented here, determinability in perception distinctively involves Homogeneous Representation or Representation that exhibits special sorts of formal type variability. This formal characterisation, I suggest, goes beyond traditional approaches to analog Representation and parallels a baseline notion of analog computation.