Hybrid method for enhancement of low-resolution ancient Kannada Stone Inscription images

Abstract

In this paper, we proposed the hybrid-based method for the enhancement of low-resolution Kannada Stone Inscription images. To test the performance of the proposed method, a total of 110 low-resolution samples of Kannada stone inscription images were collected from internet sources for the experimental setup due to the non-availability of the standard datasets for the Kannada stone inscriptions. The collected data set samples from the internet were complex in nature to read the contents present on stone images. The experimental workflow of the proposed method is to separate the text and non-text regions from the stone inscription images using a proposed technique for setting the coordinates. Then, the preprocessing process starts to filter out the noises and other unwanted regions found in the image foreground region using the median filtering composition method. Finally, the hybrid approach is implemented using a Fuzzy adaptive thresholding technique for the elimination of the background region of the input image and smooth enhancement of Kannada stone inscription images due to enormous challenges related to perspective distortion, diverse lighting conditions, the minimal disparity between the foreground and background, a lack of standardized text size and shape, reduced perceptible colour contrast, and associated noises. Hence, we obtained an enhancement accuracy of 78.18% using a hybrid method. The obtained accuracy is more acceptable compared to existing methods found in the global literature and is also carried out during the experimental study. The novelty of the paper is working on low-resolution ancient Kannada stone inscription images and a hybrid approach to enhance the quality of the original input image.