Digital acquisition and character extraction from stone inscription images using modified fuzzy entropy-based adaptive thresholding

Abstract

Soft computing is an emerging technology, which is more powerful with fuzzy logic by choosing the degree of membership function. This work is an effort to extract the foreground character from stone inscription images using fuzzy logic. Differentiating the character pixel from the stone background is a challenging task. Moreover, several collections of stone inscriptions are available, but only few of them are estampaged and preserved in a document format, which are highly exposed to deterioration. The Department of Archeology, Government of Tamil Nadu, acquired the inscriptions by a manual method called wax rubbing, which is time-consuming. The major challenges faced in character extraction from the camera-captured stone inscriptions are difficulties in perspective distortion, various light illumination, similar background and foreground, deteriorated stones, lack of text shape, size, and noise. Many binarization methods have been proposed for printed and handwritten document images, but no such work has been reported for stone inscription images. In this paper, a new stone inscription image enhancement system is proposed by combining Modified Fuzzy Entropy-based Adaptive Thresholding (MFEAT) with degree of Gaussian membership function and iterative bilateral filter (IBF). Since there is a variation in stone color, the images are equally normalized and stretched by linear contrast stretching, followed by foreground extraction by MFEAT, and the resultant image after binarization includes some noise. Hence, IBF is used to remove unwanted noise by preserving the character edges. The proposed fuzzy system helps predicting uncertainty among the character and the background pixels. The results were tested on various light illumination images and achieved a good PSNR rate compared to other binarizing techniques.