Title :
An across-scale fusion approach to segment document image
Author :
Zhu, Qingshneg ; Wu, Zhongfu ; Wang, Qian ; Zhu, Zhengyu
Author_Institution :
Dept. of Comput. Sci., Chongqing Univ., China
Abstract :
Segmenting an image into text and picture area is very important for efficiently compressing document images. The paper introduces an across-scale fusion approach to segment document images, which makes use of the multiscale down-sampling bi-level images and a Markov tree model in order to directly calculate the classification based original image to be segmented. The main process of the method is divided into a classification stage and a segmentation stage. In the first stage, we separate picture from text blocks based on multiscale bi-level images. Then we segment the image into the foreground level and the background level in the second stage. The paper describes in detail a multiscale representation of the image, the Markov tree, likelihood computation for classifying image blocks, and a modified bi-color clustering algorithm for segmenting the non-picture area.
Keywords :
Markov processes; document image processing; image classification; image segmentation; Markov tree model; across-scale fusion approach; background level; classification based original image; classification stage; document image compression; document image segmentation; foreground level; likelihood computation; modified bi-color clustering algorithm; multiscale down-sampling bi-level images; multiscale image representation; segmentation stage; text blocks; Classification tree analysis; Clustering algorithms; Computer science; Image coding; Image segmentation; Pixel; Probability density function; Software libraries; Statistics; Wavelet domain;
Conference_Titel :
TENCON '02. Proceedings. 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering
Print_ISBN :
0-7803-7490-8
DOI :
10.1109/TENCON.2002.1181335