笔迹鉴别多用匹配方法比较字符的书写风格，而字符图像的预处理和归一化对匹配是非常重要的。
In writer identification (WI), writing styles are always compared by character matching, while image preprocessing and normalization are very important for matching.
文章介绍了车牌图像的二值化和字符分割算法。
This article introduces the algorithm of bicycle images binary and segmentation of characters.
然后进一步提出根据图像边缘和字符投影特征构造图像特征矢量的思想，以及特征矢量的构成方式和归一化方法。
We present a method to construct image feature vector using edge and projection of character image. The composing way and normalizing of feature vector are shown.
应用推荐