International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Text Extraction from Camera Captured Images

Author : Kanta Kamate ¹ Taufin Jeeralbhavi ² Dr.Jagadeesh Pujari ³ Dr.Vandana Bhat ⁴

Date of Publication :7th May 2016

Abstract: Extraction of content from a caught picture is a requesting assignment because of varieties in the text dimension, textual style, introduction, arrangement, different and heterogeneous foundations. The content information accessible in the scene picture holds valuable data for substance based data indexing and recovery. The framework uses Wavelet transform of the original image in its grayscale form followed by subband filtering. Then region clustering technique is applied using centroids of the regions. Further bounding box is fit to each region thus identifying the text regions. Proposed framework is removing content and separated content is changed over into PC understanding structure. Acknowledgment of the content is done utilizing OCR engine.

Reference :

1. Nobuo Ezaki, Marius Bulacu, Lambert Schomaker, Text Detection from Natural Scene Images: Towards a System for Visually Impaired Persons, Proc. of 17th Int. Conf. on Pattern Recognition (ICPR 2004), IEEE Computer Society, 2004, pp. 683-686, vol. II, 23-26 August, Cambridge, UK.
2. Boris Epshtein Eyal Ofek Yonatan Wexler Detecting Text in Natural Scenes with Stroke Width Transform
3. Jlang Wu, Shao-Lin Qu, Qing Zhuo Wen-Yuag Wang Automatic Text Detection In Complex Color Image. Proceedings of the First International Conference on Machine Learning and Cybernetics, Beijing, 4,5 November 2002.
4. JiSoo Kim, SangCheol Park, and SooHyung Kim Computer Science Dept., Chonnam National University, Text Locating from Natural Scene Images . Using Image Intensities. Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR’05).
5. Qixiang Ye *, Jianbin Jiao, Jun Huang, Hua Yu,Text detection and restoration in natural scene images.
6. Victor Wu, Raghavan Manmatha and Edward Riseman, Text finder- An automatic system to detect and recognize text in images,IEEE transactions on Pattern analysis and machine Intelligence volume 21, No 11, Nov 1999.
7. Zongyi Liu Sudeep SarkarRobust Outdoor Text Detection Using Text Intensity and Shape Features 2008 IEEE.