Character Recognition And Extraction of An Indian State License Plates Using K-NN
License plate recognition is an application-specific optimization in Optical Character Recognition (OCR) software which enables computer systems to read automatically the License Plates of vehicles from digital images. This thesis discusses the character extraction from the respective License Plates of vehicles and problems in the character extraction process. An OCR based training algorithm named k-nearest neighbor with predefined OpenCV libraries is implemented and evaluated in the BeagleBone Black Open Hardware. In an OCR, the character extraction involves certain steps which include Image acquisition, Pre-processing, Feature extraction, Detection/ Segmentation, High-level processing, Decision making. A key advantage of the method is that it is a fairly straightforward technique which utilizes from k-nearest neighbor algorithm segments normalized result as a format in text. The results show that training an image with this algorithm gives better results when compared with other algorithms.