Document Image Binarization Using Independent Component Analysis For OCR

Abstract

 The Image binarization plays a vital role in text segmentation which is used in OCR application. Binarization of text in degraded images is a challenging task due to the variations in size, color and font of the text and the results be often affected by complex backgrounds, dissimilar lighting conditions, reflections and shadow. A robust solution to this problem can significantly enhance the precision of scene text recognition algorithms leading to a variety of applications such as scene understanding, navigation, automatic localization and image retrieval. In this paper, we propose a novel method to extract and binarize text as of images that contains complex background. We apply an Independent Component Analysis (ICA) based technique to map out the text region, which is uniform in nature, while removing specularity, shadows and reflections, which are included in the background. This algorithm works better on images with different degradations. We implement our method on various DIBCO datasets.

Authors and Affiliations

Varada Sreeja

Keywords

Related Articles

 Principles of Ubiquitous Computing Systems

 This paper provides a concise summary of pervasive computing and also the challenges faced in computer systems research posed by the emerging field of pervasive computing. This papper probes the relationship of th...

 Current Research Issue, Trend & Applications of Powder Mixed Dielectric Electric Discharge Machining (PM-EDM): A Review

 In this paper new concept of manufacturing uses non-conventional energy sources like sound, light, mechanical, chemical, electrical, electrons and ions. With the industrial and technological growth, development o...

 A Comparative Study of Design of Hough Transform Implementation with two Different Methods

 Line detection is very important task in image processing field. It is mainly used in auto focusing camera input sensors. Many techniques used for line detection but gives improper result if noise is present in an...

 A Study on Interface Shear Strength Variability and Probability of failure of Land Filled Stability Analysis

 Now a day’s failure of modern landfills by slippage of lining materials is common. The majority of failures are controlled by slippage at interfaces between lining components. Information and variability of interf...

 THE COMPREHENSIVE EVALUATION OF ENERGY SAVING AND EMISSION REDUCTION PERFORMANCE OF THERMAL POWER ENTERPRISES BASED ON THE ENTIRE-ARRAY-POLYGON INDICTOR MODEL

 The effectiveness of Thermal energy saving and pollutants reduction as an important area of energy affects overall goals of our country. Based on the requirements of relevant national policies, a comprehensive...

Download PDF file
  • EP ID EP158692
  • DOI -
  • Views 109
  • Downloads 0

How To Cite

Varada Sreeja (30).  Document Image Binarization Using Independent Component Analysis For OCR. International Journal of Engineering Sciences & Research Technology, 3(9), 161-166. https://europub.co.uk/articles/-A-158692