Transinformation for active object recognition

This article develops an analogy between object recognition and the transmission of information through a channel based on the statistical representation of the appearances of 3D objects. This analogy provides a means to quantitatively evaluate the contribution of individual receptive field vectors, and to predict the performance of the object recognition process. Transinformation also provides a quantitative measure of the discrimination provided by each viewpoint, thus permitting the determination of the most discriminant viewpoints. As an application, the article develops an active object recognition algorithm which is able to resolve ambiguities inherent in a single-view recognition algorithm.

[1]  Cordelia Schmid,et al.  Combining greyvalue invariants with local constraints for object recognition , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[3]  Emanuele Trucco,et al.  Geometric Invariance in Computer Vision , 1995 .

[4]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Sameer A. Nene,et al.  Columbia Object Image Library (COIL100) , 1996 .

[6]  Kris Popat,et al.  Cluster-based probability model applied to image restoration and compression , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[7]  J. Hornegger,et al.  Statistical learning, localization, and identification of objects , 1995, Proceedings of IEEE International Conference on Computer Vision.