Automatic Number Plate Recognition (ANPR) with YOLOv3-CNN
This work addresses automatic number plate recognition for traffic monitoring, but it is incremental as it applies existing methods to new environmental factors.
The authors tackled vehicle and license plate detection using a YOLOv3-CNN pipeline, achieving varying accuracy under different environmental conditions like angle and blur, with an overall accuracy reported.
We present a YOLOv3-CNN pipeline for detecting vehicles, segregation of number plates, and local storage of final recognized characters. Vehicle identification is performed under various image correction schemes to determine the effect of environmental factors (angle of perception, luminosity, motion-blurring, and multi-line custom font etc.). A YOLOv3 object detection model was trained to identify vehicles from a dataset of traffic images. A second YOLOv3 layer was trained to identify number plates from vehicle images. Based upon correction schemes, individual characters were segregated and verified against real-time data to calculate accuracy of this approach. While characters under direct view were recognized accurately, some numberplates affected by environmental factors had reduced levels of accuracy. We summarize the results under various environmental factors against real-time data and produce an overall accuracy of the pipeline model.