YOLO and Mask R-CNN for Vehicle Number Plate Identification

TL;DR

This paper compares YOLO and Mask R-CNN for vehicle license plate recognition, demonstrating that Mask R-CNN outperforms YOLO in recognizing tilted plates and improves character recognition accuracy.

Contribution

It introduces a Mask R-CNN based approach for license plate detection and recognition, especially effective for skewed and oblique images, surpassing existing methods.

Findings

Mask R-CNN outperforms YOLO in recognizing plates with large bevel angles.

The proposed method significantly improves character recognition for tilted plates.

Experimental results on AOLP dataset show superior performance of the new approach.

Abstract

License plate scanners have grown in popularity in parking lots during the past few years. In order to quickly identify license plates, traditional plate recognition devices used in parking lots employ a fixed source of light and shooting angles. For skewed angles, such as license plate images taken with ultra-wide angle or fisheye lenses, deformation of the license plate recognition plate can also be quite severe, impairing the ability of standard license plate recognition systems to identify the plate. Mask RCNN gadget that may be utilised for oblique pictures and various shooting angles. The results of the experiments show that the suggested design will be capable of classifying license plates with bevel angles larger than 0/60. Character recognition using the suggested Mask R-CNN approach has advanced significantly as well. The proposed Mask R-CNN method has also achieved significant progress in character recognition, which is tilted more than 45 degrees as compared to the strategy of employing the YOLOv2 model. Experiment results also suggest that the methodology presented in the open data plate collecting is better than other techniques (known as the AOLP dataset).