Hand-written Character Recognition System Using Uniform Division of Training Samples on subspace Method
スポンサーリンク
概要
- 論文の詳細を見る
In spite of the fact that subspace method can approximate the distribution of categories precisely, only a few attempts have so far been made at applying it in hand-written character recognition. The subspace method proposed by Watanabe (1969) offers the basic concept of subspace construction, but the issue of how to use the limited samples to construct effective subspace to avoid the problem of mis-recognition caused by the fact that the subspace of a category is almost parallel to the mean vector of the category remains unresolved. This problem leads to the mis-recognition of the samples far from the mean vector. To cope with this problem, Abe, Nemoto and Sun (1995) have proposed the Combination method (CM), which constructs the subspace from several groups including different number of samples divided from the whole training samples. CM obtained a high recognition rate of 97.76% with respect to ETL9B, the largest database of hand-written characters in Japan. ETL9B was published by Electro-technical Laboratory of Japan in 1985. It includes 2,965 categories of Chinese characters and 71 categories of Japanese Kana, there are 200 data sets in the database where each set has one sample per category. Total number of samples is 607,200. The issues that need to be dealt with next are how to improve the recognition accuracy and how to accelerate the recognition speed. In this paper, we propose a new method called Uniform Division Method (UDM), which uses the uniformly divided training samples to construct subspace. Compared to CM given earlier, UDM is very simple and effective enough to improve the accuracy of recognition; as a result, we obtained a recognition rate of 98.64% for ETL9B compared to the 97.76% for CM. This is the first time that such a high recognition rate has been obtained by making good use of subspace method. Furthermore, the computation required for UDM is less than a half of that of CM. The UDM algorithm and the experiments with ETL9B will be described in this paper.
著者
-
KATO Nei
Graduate School of Information Sciences, Tohoku University
-
Kato Nei
Graduate School Of Information Sciences (gsis) Tohoku University
-
Kato Nei
Graduate School Of Information Sciences Tohoku University
-
Nemoto Yoshiaki
Graduate School Of Information Sciences Tohoku University
-
Nemoto Yoshiaki
Graduate School Of Information Science Tohoku University
関連論文
- On the effect of mobility on reliable topology control in ad-hoc networks (ネットワークシステム)
- On the Effect of Mobility on Reliable Topology Control in Ad-hoc Networks
- Characterization of Packet Losses and Delays in Multi-Layered Satellite Networks Over an Efficient Routing Scheme
- A secure and robust framework of service level specification for next generation wireless networks (ユビキタス・センサネットワーク)
- Problems in Management Information Retrieval for High-Speed Networks and a Proposed Solution (Special Issue on Multimedia on Demand)
- B-11-10 A Study on QoS guarantee for Multiclass Traffic
- Hand-written Character Recognition System Using Uniform Division of Training Samples on subspace Method
- Performance evaluation of TCP over hybrid satellite/MANET networks (衛星通信)
- Capacity Design of Guaranteed-QoS VPN
- A Satellite Selection Method for Walker Delta LEO Satellite Networks(Recent Fundamental Technologies for Broadband Satellite Communications)
- A New Coding Scheme for Infrared ASK Communication Systems Which Have Zero-Spectrum Points within the Main-Lobe Region (Joint Special Issue on Recent Progress in Optoelectronics and Communications)
- A New Coding Scheme for Infrared ASK Communication Systems Which Have Zero-Spectrum Points within the Main-Lobe Region (Joint Special Issue on Recent Progress in Optoelectronics and Communications)
- A Fundamental Study on Effect of Contact Condition for Electromagnetic Noise at Copper-Carbon Electrodes (Special Issue on Electromechanical Devices and Their Materials)
- Usage Parameter Control Scheme for ATM Networks : Markovian State-Dependent Approach
- High Accuracy Recognition of ETL9B Using Exclusive Learning Neural Network-II : ELNET-II (Special Issue on Character Recognition and Document Understanding)
- ELB in IP/NGEO Satellite Constellations : Issues and Solutions(Advanced Technology-I)
- A Study of Gaussian Activation Function Based Modular Neural Network for Alternative-Style Handwritten Characters Recognition System
- Characterization of Packet Losses and Delays in Multi-Layered Satellite Networks Over an Efficient Routing Scheme
- Detecting and Tracing DDoS Attacks in the Traffic Analysis Using Auto Regressive Model(Traffic Measurement and Analysis)(New Thechnologies and their Applications of the Internet)
- High Speed and High Accuracy Rough Classification for Handwritten Characters Using Hierarchical Learning Vector Quantization
- A Handprinted Character Recognition System Using Image Transformation Based on Partial Inclination Detection (Special Issue on Character Recognition and Document Understanding)
- A Traffic Congestion Avoidance Scheme for LEO Satellite Networks by Using Traffic Detour Technique(System Engineering-II)
- B-6-128 Admission Control and Resource Allocation for Hierarchical-Generalized Processor Sharing System
- Congestion Prediction Based Load Balancing in IP/LEO Satellite Networks(Satellite Network)