Natural scenes images contain different objects. These images can be photos taken by people which are various and used in different situations. For example, scenery photos and portrait photos are commonly seen when we are in journey and daily life. However, to many people, text is the most intuitive way to get the around information. These images can also be disclaimers on the roads, construction sites or notices of hazards which are the text regions. These images might have text as well as other objects which are non text region. The aim of this paper is to focus only on text region and eliminate non text regions. To achieve this aim Text detection and localization is implemented along with eliminating non text region. In this paper, an efficient algorithm which can detect, localize and extract text in images with complex backgrounds is presented. The proposed approach is based on a method for edge detection, and the localization of text regions using projection profile analysis and geometrical properties. The present research aims at developing a text detection system from an image using edge based or texture based approach. The approach is targeted towards being robust with respect to different kinds of text appearances, including font size, color and language. The proposed method will be applied on the various images and detect regions of the text perfectly and removes the non text regions. The standard images available on the internet and used by the researchers will be used for validation of the proposed system. The entire framework is developed on MATLAB platform
Article Details
Unique Paper ID: 146785
Publication Volume & Issue: Volume 5, Issue 1
Page(s): 936 - 940
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024