Plate Number Recognition based on Hybrid Techniques

Globally and locally, the number of vehicles is on rise. It becoming more challenging for authorities to track down specific vehicles. Automatic License Plate Recognition becomes an addition transportation systems automation. Where extraction vehicle license plate done without human intervention. Identifying precise place a through its from moving images image among crucial activities discovery systems. Artificial intelligence are connecting gap between physical world digital automatic detection. The proposed research uses machine learning recognizing Arabic numbers. An captured detection by processing, character segmentation which locates numeric characters plate. system recognizes area extracts image. background color identifies types: (1) White private vehicle; (2) red bus taxi; (3) blue governmental (4) yellow trucks, tractors, cranes; (5) black temporary license; (6) green army. recognition numbers plates achieved two methods as Google Tesseract OCR based Machine Learning-based training testing K-nearest neighbors (kNN). has been tested 90 downloaded internet CCTV. Empirical outcomes show that finds well successfully. overall success rates localization have done. rate 97.78%, in 45.56 % KNN 92.22%.