The Fuzzy License Plate Recognition Based On Machine Learning

As analytical tools Intelligent Transportation Systems dealing with the city and highwayvehicles are developing rapidly. License Plate Recognition System related to computer vision,image processing, pattern recognition, and other disciplines. Scenarios and the license plate itself,the complexity of the issues to be addressed in the system is quite complex, such as outsidelighting conditions, special weather conditions, the complexity of the non-plate regioninterference factors can affect the performance of the license plate recognition system. Theselection of anti-noise better wavelet packet transform image enhancement; according to thelicense plate image with Haar features using Adaboost algorithm training data to distinguishbetween images with and without license plates containing the license plate image, using theSUSAN corner detection method to mark all corner location, and then define a rectangularsliding window to scan the entire image, the location of the white pixels in the last slidingwindow is the plate area to locate the plate region. Vertical split level split according to theHough transform, and then accurate segmentation of the various characters, the last BP neuralnetwork method is to identify the split out of character.