The Automatic recognition System to vehicles through its number is an important topic, because of its important uses, such as security applications by monitoring the entrances of a important institutions, monitor the vehicles on the road, detection of stolen cars, and even that could be useful in statistical studies, where we can study the traffic congestion in an area. In this work we offer an overview of the Automatic Number Plate Recognition System (ANPR) through to identify the license plate number, and also recognize the color of car. The focus of this research on the stage of converting the numbers into a picture of a car plate to actual figures, to improve the performance of all system, where many of errors that occur at this stage. In this search was used the algorithm of Principle component analysis (PCA) to identify the numbers plate inside the picture. and its integration with optical character Recognition algorithm(OCR) which usually used for recognition , to minimize errors in recognition numbers and thus improve the performance of the automatic number plate system.and also we add color car recognize(which another important parameter of car) , this helps after return to data base detect stolen vehicles and improve the reliability of system