A Novel Approach of Data Extraction from Indian Degraded Historical Documents using Gamma Variation and Histogram Balancing Method

Abstract

Palm leaves manuscripts copper plate compositions, wooden compositions were one of the earliest manifestations of composing media and their utilization as writing material in India has been recorded from as early as the fifth century B.C. until as of late as the late nineteenth century. Palm leaf manuscripts identifying with arts, science, structural engineering, arithmetic, cosmology, astrology, and medication going back a few many years are still accessible for reference today because of numerous continuous endeavors for safeguarding of old archives by libraries and colleges not in India yet all around the globe. Such sort of original copies normally last a couple of hundreds of years yet with time the material degrades and the writing becomes illegible to be valuable in any structure. Advanced Digital Image processing can help enhance the images of these manuscripts in order to empower recovery of the written content from these degraded documents. In this paper we proposed a filter and transform based technique for recovery of data written on such historical original manuscripts. The method uses a dynamically selected pivoting background color in a linear transform to enhance the legibility of the foreground text. At that point a blend of two other image processing algorithms gamma variation method and histogram balancing are applied to the transformed image. The algorithms can be mathematically combined into one or two transformations for computational efficiency. The method is tested on a set of different historical document images in different environmental condition and the result of the proposed method is compared with Bilateral filter with Binarization method show significant improvement in readability with show noteworthy change in clarity. This enhanced image is send to a trained OCR engine for extracting Sanskrit data contents written on manuscripts. The method can likewise be utilized to improve digital images of antiquated, historical, degraded wooden, paper documents.