NGFICA Based Digitization of Historic Inscription Images. (7th May 2013)

• Record Type: Journal Article
• Authors: Sreedevi, Indu; Pandey, Rishi; Jayanthi, N.; Bhola, Geetanjali; Chaudhury, Santanu
• Other Names: Cheng L.-M. Academic Editor.; Hwang W.-L. Academic Editor.; Yin P.-Y. Academic Editor.
• Is Part Of: ISRN signal processing. Volume 2013(2013)
• Publication Date: 2013-05-07
• Subjects: Signal processing -- Periodicals; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2013/735857
• Languages: English
• ISSNs: 2090-5041

Abstract

Abstract : This paper addresses the problems encountered during digitization and preservation of inscriptions such as perspective distortion and minimal distinction between foreground and background. In general inscriptions possess neither standard size and shape nor colour difference between the foreground and background. Hence the existing methods like variance based extraction and Fast ICA based analysis fail to extract text from these inscription images. Natural gradient flexible ICA (NGFICA) is a suitable method for separating signals from a mixture of highly correlated signals, as it minimizes the dependency among the signals by considering the slope of the signal at each point. We propose an NGFICA based enhancement of inscription images. The proposed method improves word and character recognition accuracies of the OCR system by 65.3% (from 10.1% to 75.4%) and 54.3% (from 32.4% to 86.7%), respectively.