Title :
Character segmentation of color images from digital camera
Author :
Wang, Kongqiao ; Kangas, Jari A. ; Li, Wenwen
Author_Institution :
Human Interface Technol., Nokia (China) Res. Center, Beijing, China
fDate :
6/23/1905 12:00:00 AM
Abstract :
Because of the lack of prior knowledge about the color of characters and the disturbance caused by lighting conditions and noise, character segmentation from scene images is a very difficult issue. In this paper, a novel character segmentation method for color images from a digital camera is presented, combining edge detection, a watershed transform and clustering. Since the characters extracted from color images are output in a binary format, they can be input directly to an OCR system for recognition. Experimental results have proven the method´s effectiveness
Keywords :
document image processing; edge detection; image colour analysis; image segmentation; lighting; optical character recognition; pattern clustering; transforms; OCR system; binary format; character color; character extraction; character segmentation; color clustering; color images; digital camera; edge detection; lighting; noise; optical character recognition; scene images; watershed transform; Anisotropic magnetoresistance; Character recognition; Color; Colored noise; Digital cameras; Image edge detection; Image segmentation; Layout; Optical character recognition software; Optical noise;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953785
