Object categorization using self-organization over visual appearance

We propose an object categorization method which utilizes a feature structure, capturing object visual appearance, and the self-organizing map (SOM). The feature structure combines a set of spatially distant local receptive field responses with a constellation model which represents spatial relationships between the responses. The receptive field responses capture local appearance information and the spatial model generates a complete description of an object. The combination allows accurate representation of objects and their deformations. By the self-organization procedure unsupervised categorization over visual appearance of objects can be constructed. In addition, the proposed feature structure provides a reconstruction property, and thus, categorization can be used to visualize modalities of visual appearance. Categorization of real objects is demonstrated with human face images.

[1]  Christoph von der Malsburg,et al.  Reconstruction from Graphs Labeled with Responses of Gabor Filters , 1996, ICANN.

[2]  Erkki Oja,et al.  PicSOM: self-organizing maps for content-based image retrieval , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[3]  Jiri Matas,et al.  XM2VTSDB: The Extended M2VTS Database , 1999 .

[4]  Michael C. Burl.  Recognition of visual object classes , 1996 .

[5]  Timor Kadir,et al.  Scale Saliency and Scene Description , 2002 .

[6]  Jouko Lampinen,et al.  Distortion tolerant pattern recognition based on self-organizing feature extraction , 1995, IEEE Trans. Neural Networks.

[7]  Joni-Kristian Kämäräinen,et al.  Simple Gabor feature space for invariant object recognition , 2004, Pattern Recognit. Lett..

[8]  Gu Ming,et al.  A SOM-wavelet networks for face identification , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[9]  Martin A. Fischler,et al.  The Representation and Matching of Pictorial Structures , 1973, IEEE Transactions on Computers.

[10]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[11]  Joni-Kristian Kämäräinen,et al.  Feature representation and discrimination based on Gaussian mixture model probability densities - Practices and algorithms , 2006, Pattern Recognit..

[12]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[13]  Miroslav Hamouz.  Feature-based affine-invariant detection and localization of faces , 2004 .

[14]  Harry Wechsler,et al.  Learning and caricaturing the face space using self-organization and Hebbian learning for face processing , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[15]  Scott Helmer.  Object Recognition with Many Local Features , 2004 .

[16]  Joni-Kristian Kämäräinen,et al.  Invariance properties of Gabor filter-based features-overview and applications , 2006, IEEE Transactions on Image Processing.

[17]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[18]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[19]  Jiri Matas,et al.  Feature-based affine-invariant localization of faces , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Josef Kittler,et al.  Object Evidence Extraction Using Simple Gabor Features and Statistical Ranking , 2005, SCIA.

[21]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..