Pattern recognition by cooperating neural networks

The study of connectionist models for pattern recognition is mainly motivated by their presumed simultaneous feature selection and classification. Character recognition is a common test case to illustrate the feature extraction and classification characteristics of neural networks. Most of the variability concerning size and rotation can be handled easily, while acquisition conditions are usually controlled. Many examples of neural character recognition applications were presented where the most successful results for optical character recognition (OCR) with image inputs were reported on a layered network (LeCun et al., 1990) integrating feature selection and invariance notions introduced earlier in neocognitron networks. Previously, we have presented a supervised learning algorithm, based on Kohonen's self- organizing feature maps, and its applications to image and speech processing (Midenet et al., 1991). From pattern recognition point of view, the first network performs local feature extraction while the second does a global statistical template matching. We describe these models and their comparative results when applied to a common French handwritten zip-code database. We discuss possible cooperation schemes and show that the performances obtained by these networks working in parallel exceed those of the networks working separately. We conclude by the possible extensions of this work for automatic document processing systems.

[1]  Y. Lee.  Handwritten digit recognition using k nearest neighbour radial-basis function, and backpropagation , 1991 .

[2]  James A. Pittman,et al.  Recognizing Hand-Printed Letters and Digits Using Backpropagation Learning , 1991, Neural Computation.

[3]  Kevin J. Lang.  A time delay neural network architecture for speech recognition , 1989 .

[4]  Sylvie Thiria,et al.  Multi-Module Neural Networks for Classification , 1990 .

[5]  eon BottouAT.  Stochastic Gradient Learning in Neural Networks , 2022 .

[6]  Françoise Fogelman-Soulié,et al.  Speaker-independent isolated digit recognition: Multilayer perceptrons vs. Dynamic time warping , 1990, Neural Networks.

[7]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[8]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[9]  Patrick Gallinari,et al.  Learning vector quantization, multi layer perceptron and dynamic programming: comparison and cooperation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[10]  R. Chevallier,et al.  Complementary aspects of topological maps and time delay neural networks for character recognition , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[11]  Geoffrey E. Hinton,et al.  A time-delay neural network architecture for isolated word recognition , 1990, Neural Networks.

[12]  R. Chevallier,et al.  Comparative Study of Neural Networks and Non Parametric Statistical Methods for Off-Line Handwritten Character Recognition , 1992 .

[13]  S. Midenet,et al.  Supervised Learning Based on Kohonen’s Self-Organising Feature Maps , 1990 .

[14]  Kunihiko Fukushima,et al.  Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position , 1982, Pattern Recognit..