Development of License Plate Recognition on Complex Scene with Plate-Style Classification and Confidence Scoring Based on KNN

Abstract

This paper presents an approach for developing an algorithm for automatic license plate recognition system (ALPR) on complex scenes. A plate-style classification method is also proposed in this paper to address the inherent challenges for ALPR in a system that uses multiple plate-styles (e.g., different fonts, multiple plate layout , variations in character sequences) which is the case in the current Philippine license plate system. Methods are proposed for each ALPR module: plate detection, character segmentation, and character recognition. K-nearest neighbor (KNN) is used as a classifier for character recognition together with a proposed confidence scoring to rate the decision made by the classifier. A small dataset of Philippine license plates but with relevant features of complex scenarios for ALPR is prepared. Using the proposed system on the prepared dataset, the performance of the system is evaluated on different categories of complex scenes. The proposed algorithm structure shows promising results and yielded an overall accuracy higher than the existing ALPR systems on the dataset consisting mostly of complex scenes.

Light-YOLOv3: License Plate Detection in Multi-Vehicle Scenario

“…With the continuous development of Internet of Vehicles technology and the continuous expansion of traffic volume, traffic management in complex traffic scenarios has become a major problem. The license plate is the only identification mark of the car's identity and the automatic detection of the license plate [1] plays an important role in intelligent transportation. Traditional license plate detection [2] technology is based on graphic segmentation and graphic recognition theory to determine the position of the license plate in the picture to complete the detection.…”