Title :
Detection of text regions from digital engineering drawings
Author_Institution :
Inst. of Telecommun. Eng., Xidian Univ., Xi´´an, China
fDate :
4/1/1998 12:00:00 AM
Abstract :
An algorithm for text/graphics separation is presented in this paper. The basic principle of the algorithm is to erase nontext regions from mixed text and graphics engineering drawings, rather than extract text regions directly. This algorithm can be used to extract both Chinese and Western characters, dimensions, and symbols and has few limitations on the kind of engineering drawings and noise level. It is robust to text-graphics touching, text fonts, and written orientations
Keywords :
document image processing; engineering graphics; feature extraction; image segmentation; digital engineering drawings; document image analysis; feature extraction; pattern recognition; text graphics separation; text region detection; text segmentation; CADCAM; Character recognition; Computer aided manufacturing; Computer graphics; Engineering drawings; Image recognition; Noise level; Optical character recognition software; Pattern recognition; Text recognition;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
