DocumentCode :
2147409
Title :
A Study on Edge Tracing for Vehicle Algorithm
Author :
Wang, Weihua
Author_Institution :
Sch. of Comput., ChongQing Univ. of Arts & Sci., Chongqing
fYear :
2008
fDate :
30-31 Dec. 2008
Firstpage :
249
Lastpage :
252
Abstract :
Feature extraction is an important step for vehicle recognition. However, there are many regions in a vehicle image, and it is difficult to extract the edge vectors of the regions of the image. So, a new developed contour tracing approach has been proposed in this study, it was applied to the pixel set formed from the vehicle image in order to obtain the characteristic vector which is very important in the vehicle recognition. This approach is based on scan-line and neighborhoods of the analyzed point algorithm. The results of this test shows good sensitivity to noise and local edge distortions, it also shows that the edges of basic non-convex and convex objects could be determined easily.
Keywords :
feature extraction; image recognition; image resolution; contour tracing approach; edge tracing; feature extraction; pixel set; vehicle image; vehicle recognition; Art; Data mining; Feature extraction; Image edge detection; Image recognition; Information technology; Intelligent transportation systems; Object detection; Pixel; Vehicles; edge detection; feature extraction; feature vector; scan-line; vehicle recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
MultiMedia and Information Technology, 2008. MMIT '08. International Conference on
Conference_Location :
Three Gorges
Print_ISBN :
978-0-7695-3556-2
Type :
conf
DOI :
10.1109/MMIT.2008.51
Filename :
5089106
Link To Document :
بازگشت