Multidimensional multistage k-NN classifiers for handwritten digit recognition

I. Soraluze1, C. Rodriguez1, F. Boto1, A. Perez1
1Computer Architecture and Technology Department, Computer Science Faculty, UPV/EHU, San Sebastian, Spain

Tóm tắt

This paper analyses the application of multistage classifiers based on the k-NN rule to the automatic classification of handwritten digits. The discriminating capacity of a k-NN classifier increases as the size and dimensionality of the reference pattern set (RPS) increases. This supposes a problem for k-NN classifiers in real applications: the high computational cost required. In order to accelerate the process of calculating the distance to each pattern of the RPS, some authors propose the use of condensing techniques. These methods try to reduce the size of the RPS without losing classification power. Our alternative proposal is based on hierarchical classifiers with rejection techniques and incremental learning that reduce the computational cost of the classifier. We have used 270,000 digits (160,000 digits for training and 110, 000 for the test) of the NIST Special Data Bases 19 and 3 (SD19 and SD3) as experimental data sets. The best non -hierarchical classifier achieves a hit rate of 99.50%. The hierarchical classifier achieves the same hit ratio, but with 24.5 times lower computational cost than best non-hierarchical classifier found in our experimentation and 6 times lower than Hart's Algorithm.

Từ khóa

#Multidimensional systems #Handwriting recognition #Computational efficiency #Acceleration #Testing #NIST #Image databases #Spatial databases #Computer architecture #Computer science

Tài liệu tham khảo

10.1109/TIT.1968.1054155 10.1016/S0031-3203(00)00043-1 garris, 1994, Nist form-based handprint recognition system, NIST Technical Report NISTIR 5469 National Institute of Standards Tecnology 10.1109/ICPR.2000.905602 devroye, 1996, A Probabilistic Theory of Pattern Recognition, 10.1007/978-1-4612-0711-5 alpaydin, 2000, Cascading multiple classifiers and representations for optical and pen-based handwritten digit recognition, Proceedings of the Seventh IWFHR, 453 ho, 1994, Decision combination in multiple classifier systems, IEEE Trans PAMI, 16, 66, 10.1109/34.273716 wilkinson, 1992, First census optical character recognition system confernce, National Institute of Standards and Technology (NIST) rodri?guez, 2000, Transformations and neighbourhood algorithms for the classification of handwritten digits: An experimental study, 5th Iberoamerican Symposium on Pattern Recognition Lisboa, 111 impedovo, 1991, Optical character recognition a survey character and handwriting recognition, World Scientific Series in Computer Science, 30, 1 10.1109/TIT.1968.1054155 dasarathy, 1991, Nearest neighbor (nn) norms: Nn pattern classification techniques, IEEE-computer Society Press duda, 1973, Pattern Classification and Scene Analysis 10.1016/0031-3203(95)00146-8