Hopfield neural networks for affine invariant matching

The affine transformation, which consists of rotation, translation, scaling, and shearing transformations, can be considered as an approximation to the perspective transformation. Therefore, it is very important to find an effective means for establishing point correspondences under affine transformation in many applications. In this paper, we consider the point correspondence problem as a subgraph matching problem and develop an energy formulation for affine invariant matching by a Hopfield type neural network. The fourth-order network is investigated first, then order reduction is done by incorporating the neighborhood information in the data. Thus we can use the second-order Hopfield network to perform subgraph isomorphism invariant to affine transformation, which can be applied to an affine invariant shape recognition problem. Experimental results show the effectiveness and efficiency of the proposed method.

[1]  Yehezkel Lamdan,et al.  Affine invariant model-based object recognition , 1990, IEEE Trans. Robotics Autom..

[2]  Eam Khwang Teoh,et al.  Hopfield network with constraint parameter adaptation for overlapped shape recognition , 1999, IEEE Trans. Neural Networks.

[3]  X. Xu,et al.  A generalized neural network model , 1988, Neural Networks.

[4]  Eric Mjolsness,et al.  A Lagrangian relaxation network for graph matching , 1996, IEEE Trans. Neural Networks.

[5]  Wei-Chung Lin,et al.  A Neural Network Approach to CSG-Based 3-D Object Recognition , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Stan Z. Li,et al.  Matching: Invariant to translations, rotations and scale changes , 1992, Pattern Recognit..

[7]  Tariq Samad,et al.  High-order Hopfield and Tank optimization networks , 1990, Parallel Comput..

[8]  Zhengwei Yang,et al.  Image registration and object recognition using affine invariants and convex hulls , 1999, IEEE Trans. Image Process..

[9]  Mubarak Shah,et al.  Learning affine transformations , 1999, Pattern Recognit..

[10]  Shuichi Kurogi.  Competitive neural network for affine invariant pattern recognition , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[11]  Zhengwei Yang,et al.  Invariant matching and identification of curves using B-splines curve representation , 1995, IEEE Trans. Image Process..

[12]  Robert M. Haralick,et al.  Structural Descriptions and Inexact Matching , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Nasser M. Nasrabadi,et al.  Object recognition by a Hopfield neural network , 1991, IEEE Trans. Syst. Man Cybern..

[14]  Edward J. Delp,et al.  On detecting dominant points , 1991, Pattern Recognit..

[15]  Peter Wall,et al.  Mobile robot navigation using self-similar landmarks , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[16]  Eam Khwang Teoh,et al.  Pattern recognition by graph matching using the Potts MFT neural networks , 1995, Pattern Recognit..

[17]  Colin Giles,et al.  Learning, invariance, and generalization in high-order neural networks. , 1987, Applied optics.

[18]  Ali Keyhani,et al.  Development of a neural network based saturation model for synchronous generator analysis , 1995 .

[19]  Wen-Jing Li,et al.  Object recognition by sub-scene graph matching , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[20]  Nasser M. Nasrabadi,et al.  Object recognition using multilayer Hopfield neural network , 1997, IEEE Trans. Image Process..

[21]  Mengkang Peng,et al.  Occluded object recognition by Hopfield networks , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

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

[23]  Sung H. Yoon,et al.  A robust boundary-based object recognition in occlusion environment by hybrid Hopfield neural networks , 1996, Pattern Recognit..

[24]  Wei-Chung Lin,et al.  A hierarchical multiple-view approach to three-dimensional object recognition , 1991, IEEE Trans. Neural Networks.

[25]  Tong Lee,et al.  Image registration and object recognition by affine invariant matching , 2001, Proceedings of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing. ISIMP 2001 (IEEE Cat. No.01EX489).

[26]  Zhenya He,et al.  Solving a kind of nonlinear programming problems via analog neural networks , 1998, Neurocomputing.

[27]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[28]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[29]  Wen-Jing Li,et al.  Image analysis by accumulative Hopfield matching , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[30]  Zhaohui Huang,et al.  Affine-invariant B-spline moments for curve matching , 1996, IEEE Trans. Image Process..

[31]  L. Li,et al.  Stability of a flexible link with an arbitrarily oriented tip rotor and a conservative tip load , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).