A Survey on Document Image Processing Methods Useful for Assistive Technology for the Blind

Abstract

This paper offers a review of the state-of-the-art document image processing methods and their classification by identifying new trends for automatic document processing and understanding. Document image processing (DIP) is an important problem related with most of the challenges coming from the image processing field and with applications to digital document summarization, readers for the visually impaired etc. Difficulties in the processing of documents can arise from lighting conditions, page curl, page rotation in 3D, and page layout segmentation. Document image processing is usually performed in the context of higher-level applications that require an undistorted document image such as optical character recognition and document restoration/preservation. Typically, assumptions are made to constrain the processing problem in the context of a particular application. In this survey, we categorize document image processing methods on the basis of the technique, provide detailed descriptions of representative methods in each category, and examine their pros and cons. It important to notice here that the DIP field is broad, thus we try to provide a top–down/horizontal survey rather a bottom up. At the same time, we target the area of document readers for the blind, and use this application to guide us in a top–down survey of DIP. Moreover, we present a comparative survey based on important aspects of a marketable system that is dependent on document image processing techniques.