Recognition of Hand-Printed Chinese Characters and the Japanese Cursive Syllabary
Recognition of Hand-Printed Chinese Characters and the Japanese Cursive Syllabary
复制标题
手写汉字和日文草书五十音的识别
DOI：
10.1007/978-3-642-77281-8_12
复制
发表时间：
1992
期刊：
影响因子：
--
通讯作者：
Hiromitsu Yamada
中科院分区：
文献类型：
--
作者：
Kazuhiko Yamamoto;Hiromitsu Yamada
我们描述了一种识别手写汉字（汉字）和日语草书音节字符（平假名）的方法。该系统利用细胞特征进行预分类，然后结合线段特征提取、极值点法和松弛匹配法进行分类。松弛是一种使用上下文信息来减少局部歧义的技术：将初始概率分配给字典中的线段对与输入之间的匹配，然后迭代找到可接受的匹配组合。系统在ETL8数据库上进行训练和测试；在“质量好”数据集上，识别结果正确率为 99%，在“质量差”数据集上，识别结果正确率为 94.6%。
We describe a method for the recognition of hand-printed Chinese characters (Kanji) and Japanese cursive syllabary characters (Hiragana). The system preclassifies using cellular features and then classifies by a combination of feature extraction of line segments, an extreme-point method, and a relaxation matching method. Relaxation is a technique using contextual information to reduce local ambiguities: initial probabilities are assigned to matches between pairs of the line segments in the dictionary and the input, and then iteration finds acceptable combinations of the matches. The system was trained and tested on the ETL8 database; recognition results were 99% correct on the “good quality” data set, and 94.6% on the “poor quality” data set.