Document image segmentation and quality improvement by moiré pattern analysis

Abstract

Moire patterns are distortions on the results of scanning printed documents. However, the patterns can be utilized in document image segmentation and quality improvement. The moire phenomenon comes from sampling periodical structures in images, such as halftone screens, color components, and text galleys which often appear in printed magazines and newspapers. The generated moire patterns appear in the scanning result in the form of obvious periodical patterns, color skew, and color noise on the edges of artworks. The moire pattern degrades the scanning result and makes document analysis more difficult. A new approach to document image segmentation and quality improvement by moire pattern analysis is proposed. A scanning resolution, called the conductor of screen sharing, is proposed to control the moire pattern. With the resolution, moire patterns are generated and enhanced in certain designed areas in the frequency domain. Then, a logical filter, called the comb filter, is proposed to detect the moire pattern. The new method, which is based on the sampling theory and moire analysis in the frequency domain, is actually performed in the spatial domain by re-sampling and logical filtering. The proposed method can efficiently extract gray or color pictures, artworks, and text paragraphs in printed documents. Moreover, the moire patterns on the segmented document components can be easily suppressed. The suppression yields better image quality for further analysis and image compression. Experimental results are shown to demonstrate the feasibility of the proposed approach.