车牌定位及车辆特征识别研究

车牌定位及车辆识别是智能交通管理的主要研究问题.车牌定位识别,通过对图像进行预处理并结合形态学能粗略获取候选车牌位置,对符合特征的候选车牌进行筛选,精确获取车牌位置,最后采用神经网络完成字符识别过程.车辆识别采用迁移学习,采用AlexNet卷积神经网络构造出深度特征向量.形态学能够应对灰度底质量差的情形,为字符识别提供保障.车辆识别时对比直接分类图片特征,迁移学习构造的深度特征分类精度为85.13%,提高了38%,验证了迁移学习的有效性,通过KNN算法表明深度特征能够表征图片属性.针对新数据集重新提取特征、训练样本将消耗大量时间,对比迁移学习和AlexNet框架发现分类精度持平,表明了迁移学习的鲁棒性. 

A Study on Location of License Plate and Feature Recognition of Vehicles

Location of license plate and recognition of vehicles are main issues in intelligent traffic management.Through image preprocessing and morphology, the locations of license plates are roughly recognized, which then be filtered to obtain the accurate locations.A recognition process for characters on the plates is completed by utilizing a neural network.Transfer Learning is used for recognition of vehicles, and a deep feature vector is developed by using an AlexNet Convolutional neural network.Morphology can be used to process poor quality of grey background and guarantee accuracy of recognition.Compared with a direct classification of image features, the classification accuracy of the deep feature vectors constructed by Transfer Learning is 85.13%, which increases by 38%.It verifies the effectiveness of Transfer Learning and image attributes that characterized by deep features based on the KNN algorithm.However, it takes time when re-extracting features and training samples for new data sets.This method is found to have the equal accuracy of classification when it is compared with Transfer Learning and AlexNet framework, which proves the robustness of Transfer Learning.