期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2015
卷号：4
期号：5
页码：2492-2496
出版社：Shri Pannalal Research Institute of Technolgy
摘要：In natural scene image, text characters and strings can provide valuable information for many applications. Extracting text is challenging task in natural scene image because of diverse text patterns and variant background interferences. This proposes a method of scene text recognition from detected text regions. In scene text detection, first we perform layout analysis of color conversion and K-mean clustering respectively to search for image regions of text strings. In scene text recognition, Support Vector Machine is proposed to extract text from surrounding environment. Our algorithm design is compatible with smart mobile devices. An Android based demo system is developed in scene text information extraction to show the effectiveness of our proposed method. The demo system also provides some insight into algorithm design and performance improvement of scene text extraction.
关键词：Character Segmentation; Clustering; Feature ; Extraction; Pre-processing; Scene Text Detection; Scene Text ; Recognition; Support Vector Machine
