Characters Segmentation is one important step in the Automatic License Plate Recognition (ALPR) system. This paper proposed an improved method for one-row & two-row of Vietnam license plates (LP) characters segmentation. The proposed method consists of two main modules: the first task is pre-processing (image quantization, normalized image, adjust horizontal contours, morphology opening to remove noises), the second task is characters segmentation based on the method named peak-to-valley in order to segment the pictures in digit images getting the two bounds of the each digit segment according to the statistical parameter. We tested for 600 Vietnam LP (300 one-row LP, 300 two-row LP), the average rate of accuracy of our method is 98.03%.

In the Automatic License Plate Recognition (ALPR) system, the License Plate Location (LPL) is the key step before the final recognition. This paper proposed an improved LPL algorithm for Vietnam vehicle license plates (LP). The proposed algorithm consists of three main modules: Pre-processing (convert RGB image to grayscale image, adjust grayscale image intensity, image binarization use Otsu method), LP candidates location (morphology opening to remove noises & dilation operation, measure properties of image regions to find candidates), LP exactly location (finding the LP angle & rotating LP, cut exactly LP region). We implemented test for 350 Vietnam vehicle images, which obtained from the actual system, the average rate of accuracy of our method is 98.64%, our results are more exactly presented methods.

Rule extraction is a main goal for rough set theory. This paper mainly constructs a new algorithm (LBRM Algorithm) for rule extraction based on rough membership. The confidence principle is established based on rough membership. Thus, LBRM Algorithm is proposed by utilizing discretization and clearness strategies under the fuzzy environment, and is applied to both interval rules and general rules in fuzzy classification. LBRM Algorithm effectiveness is illustrated by a medical example. In particular, LBRM Algorithm integrates the confidence on both previous LBR Algorithm and fundamental rough membership, and has some improvements on rule confidence.