A novel interactive technique for extraction of text characters from the images of stone inscriptions is introduced in this paper. It is designed particularly for on-site processing of inscription images acquired at various historic palaces, monuments, and temples. Its underlying principle is made of several robust character-analytic elements like HoG features, vowel diacritics, and location-bounded scan lines. Since the process involves character spotting and extraction of the inscribed information to editable text, it would subsequently help the archaeologists for epigraphy, transliteration, and translation of rock inscriptions, particularly for the ones having high degradations, noise, and a variety of styles according to the mason origin and reign. The spotted characters can also be used to create a database for ancient script analysis and related archaeological work. We have tested our method on various stone inscriptions collected from some of the heritage sites of Karnataka, India, and the results are quite promising. An Android application of the proposed work is also developed to aid the epigraphers in the study of inscriptions using a tablet or a mobile phone.

A Method for Extracting Text from Stone Inscriptions Using Character Spotting

In this paper we have presented a technique for enhancement and retrieval of historic inscription images. Inscription images in general have no distinction between the text layer and background layer due to absence of color difference and possess highly correlated signals and noise; pertaining to which retrieval of such images using search based on feature matching returns inaccurate results. Hence, there is a need to first enhance the readability and then binarize the images to create a digital database for retrieval. Our technique provides a suitable method for the same, by separating the text layer from the non-text layer using the proposed cumulants based Blind Source Extraction(BSE) method, and store them in a digital library with their corresponding historic information. These images are retrieved from database using image search based on Bag-of-Words(BoW) method.

Enhancement and Retrieval of Historic Inscription Images

Epigraphs are important sources for reshaping our culture and history. They have a remarkable importance to mankind. But modern epigraphists find it difficult to interpret the information in scripts. It is mainly because inscriptions are eroded over a period of time due to natural calamities. Scripts of ancient times are largely unknown. Character sets used have changed from one form to another over the centuries. Therefore, for reading ancient scripts the characters have to be extracted. In this paper, a model for enhancement and binarization of historical epigraphs is proposed. This model consists phase congruency and of Gaussian model based background elimination using expectation maximization(EM) algorithm, preprocessing and binarization. In binarization, phase based features are used with specialised filters. Adaptive Gaussian filters are used to smoothen the output images. Weighted mean angle is calculated to differentiate the foreground from the background. EM algorithm removes the background noise completely where foreground characters are untouched. Proposed method is tested on different datasets of inscriptions and epigraphs. Obtained results are compared with the existing classical algorithms.

Preprocessing and Binarization of Inscription Images using Phase Based Features

Epigraphic Documents are the ancient handwritten text documents inscribed on stone, metals, wood and shell. They are the most authentic, solitary and unique documented evidences available for the study of ancient history. In the recent years, Archeological Departments worldwide have taken up the massive initiative of converting their repository of ancient Epigraphic Documents into digital libraries for the perennial purpose of their preservation and easy dissemination. The visual quality of the digitized Epigraphic Document images is poor as they are captured from sources that would have suffered from various kinds of degradations like aging, depositions and risky handling. Enhancement of these images is an essential prerequisite to make them suitable for automatic character recognition and machine translation. A new approach for enhancement of Epigraphic Document images using Retinex method is presented in this paper. This method enhances the visual clarity of the degraded images by highlighting the foreground text and suppressing the background noise. The method has been tested on digitized estampages of ancient stone inscriptions of 11th century written in old Kannada language. The results achieved are efficient in terms of root mean square contrast and standard deviation.

Epigraphic Document Image Enhancement Using Retinex Method

As relics of history, ancient copper inscriptions are found in many countries. Information in the image or letter forms contained on copper ancient inscription has a very high value. The age and environmental factors caused damage to the surface of the inscription and also reduced the appearances of the image and letter. In this paper, we describe a novel segmentation methodology based on multi-texture features for ancient copper inscriptions which were severely damaged. The segmentation results of letters on ancient copper inscriptions by using the proposed method have an average accuracy of 90%. Based on these results, the proposed method is suitable for letter segmentation of the ancient copper inscriptions.

Texture Detection for Letter Carving Segmentation of Ancient Copper Inscriptions

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.

/pdf/ngfica-based-digitization-of-historic-inscription-images-42s52ls99v.pdf

NGFICA Based Digitization of Historic Inscription Images

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 neither possess 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.

Rishi Pandey

Papers

NGFICA Based Digitization of Historic Inscription Images

Enhancement of inscription images