| 一种图像汉字智能识别机的研究 |
| |
| 引用本文： | 王建平,黄冉,王金玲,徐晓冰. 一种图像汉字智能识别机的研究[J]. 微电子学与计算机, 2006, 23(12): 161-164,167 |
| |
| 作者姓名： | 王建平 黄冉 王金玲 徐晓冰 |
| |
| 作者单位： | 合肥工业大学,电气与自动化工程学院,安徽,合肥,230009 |
| |
| 摘 要： | 文章将智能控制与模式识别方法相结合，提出了一种仿人识字行为的图像汉字智能识别机。采用决策控制级、模式识别级和反馈校正并行式结构。决策控制级选择最佳的识别策略和参数．模式识别级进行多分类器结果融合识别，并根据对模式识别级输出的可信度判断结果进行反馈，校正识别方法和参数，最终提高汉字的识别效率。
|
| 关 键 词： | 反馈 识别策略 多分类器结果融合 |
| 文章编号： | 1000-7180（2006）12-0161-04 |
| 收稿时间： | 2005-11-14 |
| 修稿时间： | 2005-11-14 |
A Chinese Characters Image Intelligent Recognizing Machine |
| |
| WANG Jian-ping,HUANG Ran,WANG Jin-ling,XU Xiao-bing. A Chinese Characters Image Intelligent Recognizing Machine[J]. Microelectronics & Computer, 2006, 23(12): 161-164,167 |
| |
| Authors: | WANG Jian-ping HUANG Ran WANG Jin-ling XU Xiao-bing |
| |
| Affiliation: | School of Electric Engineering and Automation, Hefei University of Technology, Hefei 230009, China |
| |
| Abstract: | A Chinese characters image intelligent recognizing machine is presented in this paper. It combines intelligent control with pattern recognition. A paralleling structure of decision-making level, pattern recognition level and feedback level is adopted. Decision-making level chooses the best recognizing strategies and parameters. Pattern recognition level uses multi-classifier results fusion. Feedback level can feed back to revise the recognizing methods and parameters depending on different results of recognition. This structure can increase the recognition efficiency. |
| |
| Keywords: | Feedback Recognizing strategies Multi-classifier results fusion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
