Page segmentation using texture analysis

Anil K. Jain

doi:10.1016/0031-3203(95)00131-X

Return

Page segmentation using texture analysis

1996-05-01

135

PRE

Anil K. Jain

Yu Zhong

DOI：10.1016/0031-3203(95)00131-X

Original

Original request for help

Save

Abstract

En 中文

We propose a new texture-based language-free page segmentation algorithm which automatically extracts the text, halftone, and line-drawing regions from input greyscale document images. This approach utilizes a neural network to train a set of masks which is optimal for discriminating the three main texture classes in the page segmentation problem: halftone, background, and text and line-drawing regions. The text and line-drawing regions are further discriminated based on connectivity analysis. We have applied the algorithm to successfully segment English and Chinese document images. We also demonstrate that the masks can perform language separation (English/Chinese) when appropriately trained.

Keywords:

document analysis

neural network

page segmentation

texture

learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.