应用于JBIG2的一种文档图像分割方法

A Document Image Segmentation Algorithm for JBIG2

JBIG2是即将实施的文档图像压缩编码标准 ,主要应用于传真、互联网和无线传输 .其编码对象是文字与二值图像的混合文档 ,通过对特定内容采用特定的模式匹配算法进行编码 .图像分割是编码的第一步工作 .文中在简述 JBIG2标准后 ,通过对文字和二值图像的特征分析 ,提出了一种新的与轮廓无关的文档分割算法 ,快速准确且有一定适应性 .经过实验证明 。

The JBIG2 standard supports lossless or lossy coding models for document. It is mainly used for the low end facsimile, Internet and wireless transmission. Typically, a JBIG2 encoder decomposes the input bi level image into several regions and codes each of the regions separately using a different coding method. This paper presented an algorithm for layout independent document segmentation based on the differences in structure between halftone and text. It is fast and can be applied to the documents that contain any halftone images. The experiments show that this algorithm has good results.