一种对字符的图象进行机器识别的技术。
A technique for machine recognition of characters by their images.
根据“团价矩阵”和收缩规则，本方法可在不改变原字符图象结构的同时缩小字符图象。
According to "group-valence" and the rule of contracting, the size of character-picture can be contracted without changing their structure.
在图象处理算法中，应用图象全局二值化方法、字符“有效行”特征的提取和双BP神经网络，对手写体字符的识别取得了良好的效果。
With the way of binarization by globe threshold, the extracting mathod of "effective-rows" feature of handwriting numerals and recognition mathod of two parallel BP networks, good result is acquired.
该方法避免了一些传统汉字特征提取方法需要对图象进行二值化操作而造成的汉字字符结构信息丢失。
As a result, the proposed method avoids the binary operation used in some traditional Chinese character feature extractions that will seriously destroy the Chinese character structure.
提出了一个嵌入有意义字符串的图象隐形水印算法。
An invisible image watermarking algorithm for embedding meaningful watermarks is proposed.
更具体地说，每个不能被光学字符识别(ocr)的文字作为一个图象而被CAPTCHA用作测试使用。
More specifically, each word that cannot be read correctly by OCR is placed on an image and used as a CAPTCHA.
更具体地说，每个不能被光学字符识别(ocr)的文字作为一个图象而被CAPTCHA用作测试使用。
More specifically, each word that cannot be read correctly by OCR is placed on an image and used as a CAPTCHA.
应用推荐