Recognition of handwritten Chinese characters by self-growing probabilistic decision-based neural networks
檔案
- 000077456300015.pdf (1.32 MB, Adobe PDF)
日期
1998
類型
系所
期刊名稱
INPUT/OUTPUT AND IMAGING TECHNOLOGIES
卷期與頁次
第 3422 卷,頁 134–145
ISSN
0277-786X
ISBN
0-8194-2876-0
語言
英文
摘要
In this paper, we present a Bayesian decision-based neural networks (BDNN) for handwritten Chinese character recognition. The proposed Self-growing Probabilistic Decision-based Neural Networks (SPDNN) adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme. Our prototype system demonstrates a successful utilization of SPDNN to the handwriting of Chinese character recognition on the public databases, CCL/HCCR1 and in house database (NCTU/NNL). Regarding the performance, experiments on three different databases all demonstrated high recognition (86 similar to 94%) accuracy as well as low rejection/acceptance (6.7%) rates. As to the processing speed, the whole recognition process (including image preprocessing feature extraction, and recognition) consumes approximately 0.27 second/character on a Pentium-100 based personal computer, without using hardware accelerator or co-processor.
關鍵詞
Bayesian decision-based neural networksSelf-growing Probabilistic Decision-based Neural Networkssupervised learningoptical character recognition所屬典藏
會議論文引用此條目
Fu, H., & Xu, Y. (1998). Recognition of handwritten Chinese characters by self-growing probabilistic decision-based neural networks. INPUT/OUTPUT AND IMAGING TECHNOLOGIES, 3422, 134–145. https://doi.org/10.1117/12.311079
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/19453