Figure 1. License plate localization using histogramFigure 2. Illustration of pattern matching algorithmThe pattern of the letter "K" in more detail can be illustrated in the following figure:Figure 3. Illustration of a letter template4 . The Proposed MethodIn this paper we propose to use histogram for license plate localization and pattern matching for recognition. The flowchart of the proposed method is shown in Figure 4.Figure 4. The flowchart of the proposed methodThe input image should be an RGB image. First the RGB image will be converted to a grayscale image using Equation 1[10]. The dilation process is then applied to the image to make the characters thicker. The next step is processing the vertical edge. This will process the image vertically creating the vertical histogram. This histogram represents the sum of the gray value differences between neighboring pixels in an image, in a row. (1) Where = 0.299 = 0.587 = 0.114 Y = grayscale value Figure 5. Vertical edge processing The parts of the image that have a vertical histogram value below the average value will be eliminated, so the image will be segmented line by line (Figure 5). Next, the remaining parts of the image that are connected to the top or bottom of the image are removed because it is not possible to connect the license plate to the top or bottom of the image. Then the most probable row candidate will be chosen by selecting the row based on the maximum value of the vertical histogram. The result is shown in Figure 6. Figure 6. Result of vertical edge processing The next process is horizontal edge processing. This will process the image horizontally creating the horizontal histogram. This histogram represents the sum of the differences in the gray values......middle of the sheet......comparison of acquisition configurationsFigure 15. The screens showing police number recognitionA. License Plate Detection Test From all the samples, there are 63 samples successfully detected (78.75%) while the original Naikur Bharatkumar Gohil method achieves 28.75%. The license plate is detected correctly if it covers all characters of the police number. Examples of successfully detected license plate are shown in Figure 16 and Figure 17. Figure 16. Successfully Detected License Plate Object 1 Figure 17. Successfully Detected License Plate Object 2 The remaining unsuccessfully detected license plates are those whose image is cut off or exceeds the police number area. Some examples of errors in license plate detection are shown in Figure 18 - 20. Figure 18. License plate cut Figure 19. License plate area exceeded Figure 20. License plate area exceeded and cut B.