Application to the extraction of textual information in scene images

Md Nor, Danial and Omar, Rosli and Mohd Jenu, Mohd Zarar and Ogier, Jean-Mrag (2011) Application to the extraction of textual information in scene images. In: International Seminar on the Application of Science and Mathematics 2011, 1 - 3 November 2011, Putra World Trade Centre, Kuala Lumpur.

[img]
Preview
PDF
180Kb

Abstract

This paper proposes a solution to the problem o f extraction of textual information in presentation scene images. The problem has gained numerous of interest by document analysis and recognition (DAR) co mmunity. As an extention in DAR, new research domain, Camera Based Document Analysis and Recognition (CBDA R) has been established which deals with the textual information in scene images taken by lo w cost hand held devices like digital camera, cell phones, etc. A lot of applications like text translation, read ing text for visually impaired and blind person, information retrieval fro m media document, e-learning, etc., can be built using the techniques developed in CBDA R domain. The proposed approach of extraction of textual information is composed of three steps: image segmentation, text localization and extraction, and Optical Character Recognition. First of all, for pre-processing the resolution of each image is checked for re-sampling to a common resolution format (720 X 540). Then, the final image is converted to grayscale and binarized using Otsu segmentation method for further processing. In addition, looking at the mean horizontal run length of both black and white pixels , the proper segmentation of foreground objects is checked. In the post-processing step, the text localizer validates the candidate text regions proposed by text detector. We have employed a connected component approach for text localization. The extracted text is then has been successfully recognized using ABBYY FineReader for OCR.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:image segmentation; scene text; textual information; text extraction; OCR
Subjects:T Technology > TA Engineering (General). Civil engineering (General) > TA1501-1820 Applied optics. Photonics
Divisions:Faculty of Electrical and Electronic Engineering > Department of Computer Engineering
ID Code:2380
Deposited By:M.Iqbal Zainal A
Deposited On:20 Feb 2012 10:32
Last Modified:20 Feb 2012 10:32

Repository Staff Only: item control page