• Rupali Telkikar
• Sushma Kejgir

Detecting and recognizing text in computer vision is one of the difficult tasks and there is a lot of research going in technical field. To know the information contents of an image or the valuable data, there is need of analyzing the text appears in it. In this paper, for extracting the text regions Maximally Stable Extremal Region technique is used. Non-text region is removed by using geometric properties objects. Canny edge detector is used for obtaining edges of character component. Output of canny edge detector is then given to Optical Character Recognition for recognition of text present in the scene image.

Maximally Stable Extremal Region, Textbox, Canny Edge Detection, Optical Character Recognition

"Text Based Pattern Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.445-456, June 2019, Available :http://www.jetir.org/papers/JETIR1906I92.pdf

"Text Based Pattern Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp445-456, June 2019, Available at : http://www.jetir.org/papers/JETIR1906I92.pdf