Automatic license plate recognition system using neural networks
碩士 === 國立中興大學 === 電機工程學系所 === 95 === This thesis discusses the locating, segmentation, and recognition of the license plates of cars.In the procedure of locating license plates, the input image is first transformed into an image with a pre-specified resolution. Then the Sobel edge detector is adopte...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2007
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/23180934976831793562 |
| Summary: | 碩士 === 國立中興大學 === 電機工程學系所 === 95 === This thesis discusses the locating, segmentation, and recognition of the license plates of cars.In the procedure of locating license plates, the input image is first transformed into an image with a pre-specified resolution. Then the Sobel edge detector is adopted to find the edge map of the image. After that, the edge map is scanned to locate the regions with frequent variations in black and white. The threshold in the Sobel edge detector is dynamically adjusted so that the number of characters in the license plate is correct. Spatial transformation is utilized to rectify the detected license plate image to a rectangular image block. As to license plate character segmentation, connected components are extracted for each character. Then the segmented character image is input to the neural network for recognition.In the thesis, 100 images of license plates are used in the experiment. The success rate of the license plate detection is 100%; and success rate of character segmentation and recognition is 96%.
|
|---|