搜索资源列表
UnicodeOCR
- Unicode Optical Character Recognition
transfer.py.tar
- 通过Unicode内码值计算，将中文全角标点符号转换为中文半角标点符号的Python脚本，可用于统一语料中的标点符号全半角。-Code value in Unicode within the Chinese full-width punctuation into Chinese half-width punctuation Python scr ipt can be used for the width of a unified corpus of punctuation.
Unicode_OC
- 这段代码识别输入拉丁字符和输出相应的光学Unicode值和字符。它是利用人工神经网络实现方法和可以接受任何可用的字体类型。-This code identifies the input and output of the corresponding Latin characters optical Unicode values and character. It is the use of artificial neural network method and ca
BP-neural-network--based-on-Joone
- 基于joone编写的bp神经网络算法，并用到中文分词中，其中以“这支歌太平淡无味了”分词为例， 这支/歌/太/平淡/无味/了 为正确结果，分别获取两者的unicode的二进制形式作为输入样本和期望样本进行训练和测试。-Based joone written bp neural network algorithm, and used in Chinese word, unicode binary form as the input sample and expectations samples f
tthdl
- gbk与unicode互化的源程序,经过测试()