Title :
Recognizing characters in scene images
Author :
Ohya, Jun ; Shio, Akio ; Akamatsu, Shigeru
Author_Institution :
ATR Commun. Syst. Res. Labs., Kyoto, Japan
fDate :
2/1/1994 12:00:00 AM
Abstract :
An effective algorithm for character recognition in scene images is studied. Scene images are segmented into regions by an image segmentation method based on adaptive thresholding. Character candidate regions are detected by observing gray-level differences between adjacent regions. To ensure extraction of multisegment characters as well as single-segment characters, character pattern candidates are obtained by associating the detected regions according to their positions and gray levels. A character recognition process selects patterns with high similarities by calculating the similarities between character pattern candidates and the standard patterns in a dictionary and then comparing the similarities to the thresholds. A relaxational approach to determine character patterns updates the similarities by evaluating the interactions between categories of patterns, and finally character patterns and their recognition results are obtained. Highly promising experimental results have been obtained using the method on 100 images involving characters of different sizes and formats under uncontrolled lighting
Keywords :
image segmentation; optical character recognition; adaptive thresholding; character recognition; image segmentation; multisegment characters; relaxational approach; scene images; Character recognition; Humans; Image recognition; Image segmentation; Laboratories; Layout; Manufacturing automation; Noise shaping; Optical character recognition software; Pattern recognition;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on