Discriminant Filters For Object Recognition

This paper presents a technique for using training data to design image filters for appearance-based object recognition. Rather than scanning the image with a single set of filters and using the results to test for the existence of objects, we use many sets of filters and take linear combinations of their outputs. The combining coefficients are optimized in a training phase to encourage discriminability between the filter responses for distinct parts of the object and clutter. Our experiments on three popular filter types show that by using this approach to combine sets of filters whose design parameters vary over a wide range, we can achieve detection performance competitive with that of any individual filter set. This in turn can ease the task of fine-tuning the settings for both the filters and the mechanisms that analyze their outputs.1

[1]  Alex Pentland,et al.  Probabilistic visual learning for object detection , 1995, Proceedings of IEEE International Conference on Computer Vision.

[2]  Pietro Perona,et al.  A Probabilistic Approach to Object Recognition Using Local Photometry and Global Geometry , 1998, ECCV.

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

[4]  Gregory Dudek,et al.  Local appearance for robust object recognition , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  John Krumm.  Object detection with vector quantized binary features , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Trygve Randen,et al.  Texture segmentation using filters with optimized energy separation , 1999, IEEE Trans. Image Process..

[7]  James L. Crowley,et al.  Visual Recognition Using Local Appearance , 1998, ECCV.

[8]  W. Eric L. Grimson,et al.  On the sensitivity of geometric hashing , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[9]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

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

[11]  Andrea Salgian,et al.  A Perceptual Grouping Hierarchy for Appearance-Based 3D Object Recognition , 1999, Comput. Vis. Image Underst..

[12]  Takeo Kanade,et al.  Probabilistic modeling of local appearance and spatial relationships for object recognition , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[13]  Glenn Healey,et al.  The Illumination-Invariant Recognition of 3D Objects Using Local Color Invariants , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Katsushi Ikeuchi,et al.  Detectability, Uniqueness, and Reliability of Eigen Windows for Stable Verification of Partially Occluded Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Jezekiel Ben-Arie,et al.  Iconic recognition with affine-invariant spectral signatures , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[16]  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.

[17]  William E. Higgins,et al.  Designing multiple Gabor filters for multitexture image segmentation , 1999 .

[18]  David J. Hand,et al.  Construction and Assessment of Classification Rules , 1997 .

[19]  James L. Crowley,et al.  Local appearance space for recognition of navigation landmarks , 2000, Robotics Auton. Syst..

[20]  David G. Stork,et al.  Pattern Classification , 1973 .

[21]  Anuj Mohan.  Object Detection in Images by Components , 1999 .

[22]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

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