On vehicle image segmentation difficult, license plate location positioning to wait for a problem, put forward a kind of new rapid location method of vehicle license plate. In the image with gray, gray stretch, edge detection and the value of the two pretreatment on the basis, according to the license plate area rich texture features, the value of two images of row, column scanning, and the use of license plate location information, size information to reduce the search area, improve the positioning accuracy and real-time performance. Effects of light, different scenes, depending on the size of the vehicle image simulation results show that, the method has better accuracy and robustness, real-time, suitable for different applications, which is in order to separate the object from the background because of an image with different gray values in the object, the minimum of the histogram is often used as the threshold to separate the image. In this paper, a method is adopted based on neural network’s linear searching to determine the minimum of histogram, whose emphases is the liner search technology based on neural network. Through this method the optimal threshold is obtained and the instability and the unreliability of the minimum are conquered. Experimental results show that adopting this method to search for the minimum can obtain the absolute minimum, and using the optimal value to segment the image can separate the object from the background and get the satisfactory results.