Abstract. The recognition of vehicle license plate numbers is an essential step to implementing traffic laws and reducing the number of daily traffic accidents. This paper aims to apply a recognition system for Arabic license plates by using one method. Support vector machine (SVM) was used in association with data obtained from Iraq .Support vector machines (SVMs) are a set of related supervised learning methods used for classification and recognition. In simple words, given a set of training examples, each marked as belonging to one of two categories, an SVM training HOG builds a model that predicts whether a new example falls into one category or the other. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on. Here we are using the concept of SVM in LPR systems. Then a License plate recognition HOG is proposed for character segmentation and recognition. This algorithm employs an SVM to recognize numbers. The algorithm starts from a collection of samples of numbers from License plates. Each number is recognized by an SVM, which is trained by some known samples in advance. The recognition results are achieved by finding the maximum value between the outputs of SVMs. The experimental results show that our new method is of higher recognition accuracy and higher processing speed than using traditional SVM based multi-class classifier. This new approach provides a good direction for automatic license plate recognition. Here we can conclude SVM is better than any other supervised learning.