DocumentCode :
2628793
Title :
A color map processing system PU-CMPS
Author :
Gao, Qinghuai ; He, Jun ; Qiu, Guisheng ; Shi, Qingyun
Author_Institution :
Center for Inf. Sci., Peking Univ., Beijing, China
fYear :
1993
fDate :
20-22 Oct 1993
Firstpage :
874
Lastpage :
877
Abstract :
A color map processing system PU-CMPS (color map processing system of Peking University) is introduced. The main functions of PU-CMPS are color-separating, segmentation, vectorizing, recognizing, and automatic editing. First, PU-CMPS strips each kind of color from the original color map. Then, segmentation is implemented to separate the character (including number and small graphic symbols), dash line, point, and solid region. After thinning, a new scanline vectorizing algorithm converts the raster images into vector images. On the vector version of images, a class of recognizing algorithms which is based on fuzzy synthesis analysis is developed to classify the graphic structures on the images. Several automatic editing algorithms are also developed to remove the noises and connect the broken lines. It is proved by experiments that all these algorithms are highly efficient
Keywords :
cartography; colour graphics; fuzzy set theory; image recognition; automatic editing; automatic editing algorithms; color map processing system PU-CMPS; color-separating; dash line; fuzzy synthesis analysis; graphic structures; raster images; recognizing algorithms; scanline vectorizing algorithm; segmentation; small graphic symbols; solid region; vector images; vectorizing; Algorithm design and analysis; Color; Colored noise; Feedforward neural networks; Graphics; Helium; Image analysis; Image converters; Neural networks; Strips;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Document Analysis and Recognition, 1993., Proceedings of the Second International Conference on
Conference_Location :
Tsukuba Science City
Print_ISBN :
0-8186-4960-7
Type :
conf
DOI :
10.1109/ICDAR.1993.395598
Filename :
395598
Link To Document :
بازگشت