In the urban areas, there is an increased demand for ownership of the vehicles which has led to a civic problem of traffic control and vehicle identification. For an organization/institution or any restricted areas, security is important and to enhance this security it is advisable to keep track of the vehicles entering. Hence vehicle number plate recognition plays an important role in solving these problems. It is an image processing technique that uses a number plate to identify the vehicle. In this approach, the image of the vehicle has been enhanced and threshold technique was applied for a better resolution. Our approach to license plate recognition is based on a Convolution Neural Network YOLO, holistically processes the whole image, avoiding segmentation of the license plate characters. This work aims to recognize license plate images automatically to fulfill the requirement for automation in surveillance of any highly restricted areas. The result shows the success rate of number plate recognition is 98.6% and 84.7% in vehicle number detection. This accuracy can be improved greatly by positioning the camera suitably to capture the best frame and using better image enhancing techniques
Enhanced Vehicle Plate Identification using YOLO
13.12.2022
3847253 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch