Paper Info
Title
A Method to Extract Character Strings from Scene Images by Eliminating Non-character Strings: Towards Development of a Visual Assistance System for People with Visual Impairments
Abstract
This paper discusses a method to extract character strings from scene images. In this method, the Canny edge detector is first applied to a scene image, and the binary edge image is then obtained. Next, small edge elements are separated from large edge elements because edge elements from characters are much smaller than edge elements from non-character objects such as signboards etc. However, many of the small edge elements are noises, that is, most of the small edge elements are obtained from non-character objects such as roadside trees etc., and so we first remove some of the noises by a dilation operator, an operator of mathematical morphology. After that we remove again the remaining noise edge elements by checking the local segment densities. Finally, a fuzzy inference system is applied to detect character strings from the remaining small edge elements. The performance of the proposed method is examined by computer experiments.
Year
DOI
Venue
2013
10.1109/SITIS.2013.138
SITIS
Keywords
Field
DocType
character string,scene images,edge element,remaining noise edge element,binary edge image,scene image,extract character strings,non-character object,large edge element,small edge element,canny edge detector,visual impairments,non-character strings,visual assistance system,remaining small edge element,image segmentation,edge detection,mathematical morphology,fuzzy set theory
Canny edge detector,Computer vision,Dilation (morphology),Pattern recognition,Computer science,Mathematical morphology,Edge detection,Image processing,Fuzzy set,Feature extraction,Image segmentation,Artificial intelligence
Conference
Citations 
PageRank 
References 
0
0.34
2
Authors
2
Name
Order
Citations
PageRank
Jianjun Chen13912.52
Noboru Takagi24615.42