Digital acquisition and character extraction from stone inscription images using modified fuzzy entropy-based adaptive thresholding
01 Apr 2019-Vol. 23, Iss: 8, pp 2611-2626
TL;DR: 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), which helps predicting uncertainty among the character and the background pixels.
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.
Citations
More filters
26 Aug 2022
TL;DR: This survey attempts to give a detailed analysis of the recent research works on character recognition from the images of stone inscriptions with a special reference to Tamil, and details the methods applied for preprocessing, feature extraction and classification.
Abstract: Character recognition on inscriptions is an area which explores our knowledge of an ancient language. Inscriptions were done in all kinds of environments. This work focuses on recognizing Tamil language characters on stone-based images. From the inscription images, we come to know about the importance of old century languages. Some of the general challenges researchers face in recognizing the characters in stone inscriptions are differentiating the foreground pixel from the background stone images, perspective distortion, different light illumination, the same kind of background/foreground, damaged stones, lack of shape and size of the text. Despite the different ways proposed by the researchers, obstacles and issues continue to exist. This survey attempts to give a detailed analysis of the recent research works on character recognition from the images of stone inscriptions with a special reference to Tamil. It details the methods applied for preprocessing, feature extraction and classification. It gives a road map for future researchers who wish to carry out research in this area.
2 citations
26 Aug 2022
TL;DR: A detailed analysis of the recent research works on character recognition from the images of stone inscriptions with a special reference to Tamil is given in this article , which gives a road map for future researchers who wish to carry out research in this area.
Abstract: Character recognition on inscriptions is an area which explores our knowledge of an ancient language. Inscriptions were done in all kinds of environments. This work focuses on recognizing Tamil language characters on stone-based images. From the inscription images, we come to know about the importance of old century languages. Some of the general challenges researchers face in recognizing the characters in stone inscriptions are differentiating the foreground pixel from the background stone images, perspective distortion, different light illumination, the same kind of background/foreground, damaged stones, lack of shape and size of the text. Despite the different ways proposed by the researchers, obstacles and issues continue to exist. This survey attempts to give a detailed analysis of the recent research works on character recognition from the images of stone inscriptions with a special reference to Tamil. It details the methods applied for preprocessing, feature extraction and classification. It gives a road map for future researchers who wish to carry out research in this area.
1 citations
03 Mar 2023
TL;DR: In this paper , a project aims to document ancient Brahmi stone inscriptions along with documents and to further improve the quality and readability of these Brahmi texts by converting them into a digital format.
Abstract: inscriptions are ancient texts that were carved into stones or etched into metals. They were discovered engraved on copper plates, construction stones, and other materials in the southern areas of Asia. Stone inscriptions from ancient times have degraded over time due to various factors. There are also countless documents and manuscripts that contain valuable information. The information contained in these inscriptions is important and should be safeguarded. Our project aims to document ancient Brahmi stone inscriptions along with documents and to further improve the quality and readability of these Brahmi texts by converting them into a digital format. Once in a digital format, the stone inscriptions can be easily read, studied, and preserved. This project is paramount in preserving old inscriptions found throughout India and the world.
11 Feb 2023
TL;DR: In this article , an attempt was made to identify and recognize the historical Tamil paleographic writings by extracting the sequence of patches from the image and feeding them into a CNN-LSTM framework.
Abstract: The historic paleographic writings that contributes to cultural heritage of India were inscribed on various materials such as stone inscriptions, rock carving, palm manuscripts, pots, coins, copper plates etc. Archaeological departments throughout the world have undertaken massive digitization projects to digitize the historical contents. But it is highly complicated as it involves images with complex backgrounds, noises and various illumination conditions. The paleographic writings are camera captured and processed for recognition of characters. A character recognition system is an inevitable tool to offer global visibility to the paleographic writings. Automatic character recognition is a challenging problem as in the proposed work it needs a cautious blend of image enhancement, patch extraction, feature extraction, classification and recognition techniques. This involves extracting the sequence of image patches and feature vector of the patches using Convolutional Neural Network and feeding the feature vectors using attention mechanism to recognize the character with LSTM model. As paleographic writings have lengthy sequence of characters which requires special attention during character recognition. The proposed work is an attempt to identify and recognize the historical Tamil paleographic writings by extracting the sequence of patches from the image and feeding them into a CNN-LSTM framework. The proposed method mainly consists of pre-processing, feature extraction, and character-level recognition. The LSTM network is built and the sequence of feature vectors is fed to the network and trained. The sequence of characters is recognized. The performance of the proposed method recorded an character recognition accuracy of 97.9%.
References
More filters
37,017 citations
04 Jan 1998
TL;DR: In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception.
Abstract: Bilateral filtering smooths images while preserving edges, by means of a nonlinear combination of nearby image values. The method is noniterative, local, and simple. It combines gray levels or colors based on both their geometric closeness and their photometric similarity, and prefers near values to distant values in both domain and range. In contrast with filters that operate on the three bands of a color image separately, a bilateral filter can enforce the perceptual metric underlying the CIE-Lab color space, and smooth colors and preserve edges in a way that is tuned to human perception. Also, in contrast with standard filtering, bilateral filtering produces no phantom colors along edges in color images, and reduces phantom colors where they appear in the original image.
8,738 citations
01 Mar 1985-Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing
TL;DR: Two methods of entropic thresholding proposed by Pun (Signal Process.,2, 1980, 223–237;Comput.16, 1981, 210–239) have been carefully and critically examined and a new method with a sound theoretical foundation is proposed.
Abstract: Two methods of entropic thresholding proposed by Pun (Signal Process.,2, 1980, 223–237;Comput. Graphics Image Process.16, 1981, 210–239) have been carefully and critically examined. A new method with a sound theoretical foundation is proposed. Examples are given on a number of real and artifically generated histograms.
3,551 citations
TL;DR: A new method is presented for adaptive document image binarization, where the page is considered as a collection of subcomponents such as text, background and picture, which adapts and performs well in each case qualitatively and quantitatively.
2,120 citations