Image Recognition Technology Based on Machine Learning

With the development of machine learning for decades, there are still many problems unsolved, such as image recognition and location detection, classification, generation, speech recognition, natural language processing so on. In field deep research, research on classification has always been most basic, traditional urgent direction. At same time, computer intelligent technology is also conducive to gradually better respond international indicators, promote progress various fields. Therefore, based widely used in feature image, segmentation a hot spot However, due complexity video images distribution objects different application backgrounds, accuracy becomes important difficult. paper transportation industry, applied license plate extract from complex background, segment characters recognize characters, construct non automatic generation algorithm, which may improve efficiency recognition. The diversity high speed training sample set can achieve purpose effectively strong classifier. By using genetic algorithm optimize BP neural network classify information, anti-interference ability improved certain extent.