Recognition of handwritten numeric characters using neural networks designed on approximate reasoning architecture
| Autor: | Y. Kojima, K. Kawakami, M. Mizutani, Hiroshi Yamamoto, Yasuharu Shimeki, Shigeo Sakaue, Susumu Maruno, Toshiyuki Kohda |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
Artificial neural network
Contextual image classification Time delay neural network business.industry Intelligent character recognition Computer science Speech recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Word error rate Neocognitron Pattern recognition Intelligent word recognition ComputingMethodologies_PATTERNRECOGNITION Feature (machine learning) Artificial intelligence business Classifier (UML) |
| Zdroj: | Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan). |
| Popis: | We have newly developed a handwritten numeric character recognition system with neural networks based on an approximate reasoning architecture (NARA). Handwritten character recognition is one of the most difficult tasks in an area of pattern recognition because of the variation of handwritten images even in a same category of character. NARA, which consists of a classifier of input data, several sub-neural networks and an integrator of the outputs of sub-neural networks can realize a stable recognition of large variations of handwritten character images, and achieved a correct answer rate of 95.41%, an error rate of 0.20% and a rejection rate of 4.38%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|