Integrating Iconic and Structured Matching

Several investigations [11,16,19–21] have recently been undertaken into object recognition based on matching image intensity neighborhoods rather than geometric matching of features extracted from the images. These projects have used small subwindows or complete image regions and matching has been based on the similarity of extracted descriptors to previously stored descriptors. One characteristic common to these approaches is the representation of objects as a whole, rather than as a structured ensemble. This paper describes an extension to these approaches wherein a set of related features recognized at an earlier iteration also contribute to the complete object recognition. The paper describes an iconic, or image-based, matching approach that incorporates an element of geometric matching and shows that use of the subfeatures improves matching efficiency, position accuracy and completeness.

[1]  Lawrence G. Roberts,et al.  Machine Perception of Three-Dimensional Solids , 1963, Outstanding Dissertations in the Computer Sciences.

[2]  William Grimson,et al.  Object recognition by computer - the role of geometric constraints , 1991 .

[3]  Josef Kittler,et al.  Selecting Features For Neural Networks To Aid An Iconic Search Through An Image Database , 1997 .

[4]  James T. Tippett,et al.  OPTICAL AND ELECTRO-OPTICAL INFORMATION PROCESSING, , 1965 .

[5]  Dana H. Ballard,et al.  Computer Vision , 1982 .

[6]  Bernt Schiele,et al.  Object Recognition Using Multidimensional Receptive Field Histograms , 1996, ECCV.

[7]  Mohammed Ismail,et al.  Analog VLSI Implementation of Neural Systems , 2011, The Kluwer International Series in Engineering and Computer Science.

[8]  Shree K. Nayar,et al.  An Experimental Comparison of Appearance and Geometric Model Based Recognition , 1996, Object Representation in Computer Vision.

[9]  Robert B. Fisher.  Hierarchical Matching Beats The Non-Wildcard and Interpretation Tree Model Matching Algorithms , 1993, BMVC.

[10]  Giulio Sandini,et al.  A Foveated Retina-Like Sensor Using CCD Technology , 1989, Analog VLSI Implementation of Neural Systems.

[11]  Rajesh P. N. Rao,et al.  Object indexing using an iconic sparse distributed memory , 1995, Proceedings of IEEE International Conference on Computer Vision.

[12]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[13]  Allen M. Waxman,et al.  Learning and Recognizing 3D Objects from Multiple Views in a Neural System , 1992 .

[14]  Giulio Sandini,et al.  Vision and Space-Variant Sensing , 1992 .

[15]  Robert B. Fisher,et al.  Attention in Iconic Object Matching , 1996, BMVC.

[16]  Jan Paul Siebert,et al.  Scale-space recognition based on the retino-cortical transform , 1995 .

[17]  Robert B. Fisher.  From Surfaces to Objects: Computer Vision and Three Dimensional Scene Analysis , 1989 .

[18]  Rodney A. Brooks,et al.  Symbolic Reasoning Among 3-D Models and 2-D Images , 1981, Artif. Intell..

[19]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[20]  Jezekiel Ben-Arie,et al.  Pictorial recognition using affine-invariant spectral signatures , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Massimo Tistarelli,et al.  Active/space-variant object recognition , 1995, Image Vis. Comput..

[22]  J. Feldman.  Four frames suffice: A provisional model of vision and space , 1985, Behavioral and Brain Sciences.

[23]  David A. Forsyth,et al.  Identifying nude pictures , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.