Method Of Car Model Classification Based On SVM Studied And Presented

Intelligent Transportation System (ITS) has become one of the most popular worldwide research fields in traffic technology. The research topics acknowledged internationally include advanced traffic management system, advanced traffic information service system, commercial vehicle transportation and management system, electronic toll system, public transportation management system, emergency management system, and advanced car monitoring system.The thesis presented a Car Model Classification System based on the image acquired from cameras by feature extraction and pattern recognition algorithm.The main works in this thesis are s-mmarized as follows:(1)Applied processing technology on the digital image acquired from cameras, and then to suppress all kinds of noise.(2)Feature extraction. Seven car image invariant moments are extracted from the car outline except for the normal features such as the car length, car height, car outline perimeter,area surrounded by car outline, ratio between car length and car height, roundness, and ratio between the circum-rectangle area and the area surrounded by car outline. A high performance was achieved to identify the car at different positions in the picture because of the utilization of these car image invariant moments features. Presented a fast algorithm for computation of shape moments based on Freeman chain code. (3)Studied basic theories and main algorithms of pattern recognition and presented a Car Model Classification System based on Support Vector Machine (SVM).