GENERATING NEW SAMPLES FROM HANDWRITTEN NUMERALS BASED ON POINT CORRESPONDENCE
暂无分享,去创建一个
[1] Peter E. Hart,et al. Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.
[2] Henry S. Baird,et al. Document image defect models and their uses , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).
[3] K. Ishii,et al. Generation of distorted characters and its applications , 1983 .
[4] Kenichiro Ishii. Design of a recognition dictionary using artificially distorted characters , 1990, Systems and Computers in Japan.
[5] Tin Kam Ho,et al. Large-Scale Simulation Studies in Image Pattern Recognition , 1997, IEEE Trans. Pattern Anal. Mach. Intell..
[6] Norihiro Hagita,et al. Model for selectively increasing learning sample number in character recognition , 1996, Electronic Imaging.
[7] Ihsin T. Phillips. How to extend and bootstrap an existing data set with real-life degraded images , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).
[8] Akira Suzuki,et al. On-line cursive Kanji character recognition as stroke correspondence problem , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.
[9] Fumitaka Kimura,et al. Modified Quadratic Discriminant Functions and the Application to Chinese Character Recognition , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.
[10] R. Casey. Moment normalization of handprinted characters , 1970 .