Classifying a New Descriptor Based on Marr's Visual Theory

Descriptors are a powerful tool in digital image analysis. Performance of tasks such as image matching and object recognition is strongly dependent on the visual descriptors that are used. The dimension of the descriptor has a direct impact on the time the analysis take, and less dimensions are desirable for fast matching. In this paper we use a type of region called curvilinear region. This approach is based on Marr's visual theory. Marr supposed that every object can be divided in its constituent parts, being this parts cylinders. So, we suppose also that in every image there must be curvilinear regions that are easy to detect. We propose a very short descriptor to use with these curvilinear regions in order to classify these regions for higher visual tasks.

[1]  David G. Lowe,et al.  Towards a Computational Model for Object Recognition in IT Cortex , 2000, Biologically Motivated Computer Vision.

[2]  F. Arrebola,et al.  Corner detection by means of adaptively estimated curvature function , 2000 .

[3]  José R. Álvarez,et al.  Nature Inspired Problem-Solving Methods in Knowledge Engineering, Second International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2007, La Manga del Mar Menor, Spain, June 18-21, 2007, Proceedings, Part II , 2007, IWINAC.

[4]  Michel Vidal-Naquet,et al.  Visual features of intermediate complexity and their use in classification , 2002, Nature Neuroscience.

[5]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[6]  D. Marr,et al.  Representation and recognition of the spatial organization of three-dimensional shapes , 1978, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[7]  Axel Pinz,et al.  Computer Vision – ECCV 2006 , 2006, Lecture Notes in Computer Science.

[8]  Francisco Sandoval Hernández,et al.  Bounded irregular pyramid: a new structure for color image segmentation , 2004, Pattern Recognit..

[9]  Yan Ke,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, CVPR 2004.

[10]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[11]  Gisela Klette,et al.  A comparative discussion of distance transforms and simple deformations in digital image processing , 2003 .

[12]  Antonio Bandera,et al.  An Approach to Visual Scenes Matching with Curvilinear Regions , 2007, IWINAC.