Title :
On distributed representation of output layer for recognizing Japanese Kana characters using neural networks
Author :
Kenni, K. ; Shimodaira, Hiroshi ; Nakayama, Kenji
Author_Institution :
Sch. of Inf. Sci., Japan Adv. Inst. of Sci. & Technol., Ishikawa, Japan
Abstract :
The paper presents an automatic coding scheme for representing the output layer of a neural network. Compared to local representation where the number of output unit is p, the number of output unit required for the proposed representation is close to logp. The output of seven different printers were used for evaluating the performance of the system. The proposed automatic representation gave the average recognition rate of 98.7% for 71 categories
Keywords :
character recognition; natural languages; neural nets; pattern classification; Japanese Kana character recognition; automatic coding scheme; automatic representation; average recognition rate; distributed representation; neural networks; output layer; output unit; printers; Character recognition; Data preprocessing; Feature extraction; Image databases; Information science; National electric code; Neural networks; Printers; Testing;
Conference_Titel :
Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on
Conference_Location :
Ulm
Print_ISBN :
0-8186-7898-4
DOI :
10.1109/ICDAR.1997.620573
