| Summary: | 碩士 === 大葉大學 === 資訊工程學系碩士班 === 102 === In this thesis, we study a semi-automated license plate recognition system. First shoot plate image by artificially, then we can use the computer and the license plate recognition system to identify the car as the license plate. The proposed system consists of three stages: license plate location, character segmentation and character recognition.
License plate location achieved by the color transformation, Prewitt mask, binarization, median filter and morphology operations. The 8-connected label and threshold are applied to select the license plate.
Character segmentation and recognition are based on binary image. The license plate character segmentation achieved by the projection scheme. Character recognition schemes include normalization, thinning and the Pyramid model. The characteristic values by the Pyramid model are applied to match the character in the template pool. Experiments show that the proposed scheme has good result on plate recognition.
|
|---|
