A New Object Recognition System

This paper presents a new 2D object recognition system. The object representation used by the system is rotation, translation, scaling and reflection invariant. The system is highly robust to partial occlusion, deformation and perspective change. The last makes it applicable to 3D tasks. Color information can be ignored as well as combined with form representation. The boundary of an object to be recognized doesn’t need to be path-connected. The time demand to learn a new object doesn’t depend on the number of objects already learned. No object segmentation prior to recognition is needed. To evaluate the system the 3D object library COIL-100 was used.

[1]  A. A. Mullin,et al.  Principles of neurodynamics , 1962 .

[2]  Thomas H. Reiss,et al.  Recognizing Planar Objects Using Invariant Image Features , 1993, Lecture Notes in Computer Science.

[3]  Narendra Ahuja,et al.  Learning to Recognize 3D Objects with SNoW , 2000, ECCV.

[4]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Adam Krzyzak,et al.  A Distribution-Free Theory of Nonparametric Regression , 2002, Springer series in statistics.

[6]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[7]  Saburo Tsuji,et al.  Detection of Ellipses by a Modified Hough Transformation , 1978, IEEE Transactions on Computers.

[8]  Heinrich Niemann,et al.  A Spin-Glass Markov Random Field for 3-D Object Recognition , 2002 .

[9]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

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

[12]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).