Research of Vehicle Video Image Recognition Technology Based on Naive Bayesian Classification Model

This paper introduced the information of vehicle corner can not be obtained as a result of the existence of image noise that the value of projective invariant features appear errors leading the misjudgment of the vehicles types. In view of this situation Naive Bayesian classification is introduced. While characteristic parameter errors occurred, the probability values of different types of vehicles are calculated by Naive Bayesian classification, and compare the probability values. Ultimately determine the types of vehicles to achieve the identification of vehicles.