| License plate recognition system is an important part of intelligent transportation system. License plate location is a key technique of license plate recognition system and its accuracy and stability affect the performance of license plate recognition system directly. After the in-depth study on license plate location technology, two kinds of license plate location algorithm with good performance are put forward:(1) The license plate location algorithm based on edge detection and gradient direction features: After the conversion into gray image for the input image, the proposed method first uses the Sobel operator and the Gradientfaces algorithm to obtain the vertical edges image and the gradient direction image respectively. Then the background and noise edges are eliminated in accordance with the length and the density of the edges, and more inference edges are removed according to the gradient directions of the gradient direction image from the vertical edges image. Finally, the edge image is scanned by a rectangle window to locate and segment the real license plate region. The experiment results indicate that the proposed method is reliable and accurate and its positioning accuracy is 93.7%. Especially, the method is robust to the images with complex backgrounds or poor illumination.(2) The license plate location algorithm based on color features and character detection: This method firstly forms several candidate connected domains according to the characters of the color of license plate region. Then the trained SVM classifier is used to detect the characters from the areas of candidate connected domains of license plate image and to find the character regions.Finally, the adjacent character regions are merged into a connected domain and the license plate region is located according to the area of the connected domain. Experimental results show that the method is of high positioning accuracy and is suitable for different backgrounds and locations. |
PDF Full Text Request