A Coupon Classification Method Based on Adaptive Image Vector Matching

This paper describes a coupon classification system based on image vector matching. This method features following two points. (1) Extract a feature vector from a gray-scale image using a feature map which is derived from training coupon images. (2) Classify a coupon image by adaptive mask distance to cope with the recognition difficulty such as partial cutting of coupon and putting stamp on it. We have implemented this method and experimented with collected samples. It achieved 100% of recognition rates, processing speed 11.76msec/sheet to 969 images for 42 kinds of coupon samples

[1]  Hiroshi Sako,et al.  A Hierarchical Classification Method for US Bank Notes , 2005, MVA.

[2]  Atsushi Sato,et al.  Generalized Learning Vector Quantization , 1995, NIPS.

[3]  Takafumi Miyatake,et al.  Direction-invariant methodology for bill pattern recognition , 1996, Systems and Computers in Japan.

[4]  Pietro Burrascano,et al.  Learning vector quantization for the probabilistic neural network , 1991, IEEE Trans. Neural Networks.

[5]  Jianchang Mao,et al.  A system for automatically reading IATA flight coupons , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.