Skip to main content
queried at the retrieval stage. The query and database images are 8-bit grayscale images (256 gray levels). Brand sketches are com-Horacio Legal Ayala
This paper introduces a novel descriptor technique denoted as Contour-Point Signature (CPS) useful to find correspondences of points selected from the outer contours of two arbitrary shapes, and to establish a relationship to map an... more
This paper introduces a novel descriptor technique denoted as Contour-Point Signature (CPS) useful to find correspondences of points selected from the outer contours of two arbitrary shapes, and to establish a relationship to map an ordered sequence of contour points from one shape to another. The proposal has proved to be invariant, to translation, scaling and rotation, it also induces a measure which is proved to be non-negative, unique, symmetric and identity-preserving. Experimental tests were performed in shape detection under noise, with image retrieval from a MPEG-7 database and letter recognition. Numerical results show that the proposal is robust for noise perturbation, as well as, having adequate accuracy and hit rate, even with coarse tuning for its parameters. This makes the method attractive to a wide range of applications.
Research Interests:
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS;... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS; which is a point descriptor that allows to achieve a better matching of points between two figures and obtain a transformation between them. With this descriptor, we can achieve more accurate shape features and implement more efficient retrieval under multi-resolution. In addition, CPS is robust to rigid translation, scaling, rotation and independent of the origin point. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also presented.
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two problems arise: identify when two articulated objects in different stances are in the same class of objects, and differentiate the distinct positions of the same object. In both cases, it is necessary to know how correspond the different points or regions of such objects standing in different attitudes. This article presents the Contour-Point Signature; a point descriptor that allows to establish a method to achieve the better matching of points between two figures, and to thus obtain a transformation which relates them. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also defined.
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS;... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS; which is a point descriptor that allows to achieve a better matching of points between two figures and obtain a transformation between them. With this descriptor, we can achieve more accurate shape features and implement more efficient retrieval under multi-resolution. In addition, CPS is robust to rigid translation, scaling, rotation and independent of the origin point. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also presented.
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS;... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions, which can be used in human-computer interaction. This article analyzes a new descriptor, the Contour-Point Signature-CPS; which is a point descriptor that allows to achieve a better matching of points between two figures and obtain a transformation between them. With this descriptor, we can achieve more accurate shape features and implement more efficient retrieval under multi-resolution. In addition, CPS is robust to rigid translation, scaling, rotation and independent of the origin point. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also presented.
Research Interests:
Research Interests:
Computer Vision, Robot Vision, Object Recognition (Computer Vision), Image Recognition (Computer Vision), Machine Vision, and 34 more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two problems arise: identify when two articulated objects in different stances are in the same class of objects, and differentiate the distinct positions of the same object. In both cases, it is necessary to know how correspond the different points or regions of such objects standing in different attitudes. This article presents the Contour-Point Signature; a point descriptor that allows to establish a method to achieve the better matching of points between two figures, and to thus obtain a transformation which relates them. With this descriptor, we can achieve more accurate shape features and implement more efficient retrieval under multi-resolution. In addition, CPS is robust to rigid translation, scaling, rotation and independent of the origin point. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also presented.
Research Interests:
Computer Vision, Robot Vision, Object Recognition (Computer Vision), Image Recognition (Computer Vision), Machine Vision, and 34 more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two... more
A research area in Computer Vision focuses on the identification of articulated objects, such as human actions and movements of the hand, which can be used in human-computer interaction, surveillance, and other tracking systems. Two problems arise: identify when two articulated objects in different stances are in the same class of objects, and differentiate the distinct positions of the same object. In both cases, it is necessary to know how correspond the different points or regions of such objects standing in different attitudes. This article presents the Contour-Point Signature; a point descriptor that allows to establish a method to achieve the better matching of points between two figures, and to thus obtain a transformation which relates them. A measure of dissimilarity between two figures for classifying various human postures in a video sequence is also defined.
Research Interests:
Computer Vision, Robot Vision, Object Recognition (Computer Vision), Image Recognition (Computer Vision), Machine Vision, and 34 more
Research Interests:
Research Interests:
Research Interests:
Research Interests: