A New Method for Automatic Vehicle License Plate Detection

Abstract

1-License plate recognition has been widely studied, and the advance in image capture technology helps enhance or create new methods to achieve this objective. In this work is presented a method for real time detection and segmentation of car license plates based on image analyzing and processing techniques. The results show that the computational cost and accuracy rate considering the proposed approach are acceptable to real time applications, with an execution time under 1 second. The proposed method was validated using two datasets (A and B). It was obtained over 92% detection success for dataset A, 88% in digit segmentation for datasets A and B, and 95% digits classification accuracy rate for dataset B.

Comparison of Gabor Filter Bank and Fuzzified Gabor Filter for License Plate Detection

“…Corneto et al [18] used a Haar classifier for a plate detection and extraction followed by plate segmentation. The results indicate that the computational cost and accuracy rate considering this approach were acceptable to real time applications, with an execution time less than one second.…”

“…In the low enforcement applications, the controlled illumination, capturing distance and angle, and image quality (by using a special REG cameras) ensure robust performance. With the commercial image qualities, as used in this work, the limitations have to be imposed at least on the capturing settings (distance and angle), with similar examples in [1], [2], [5], [11], [18], [25], [28], [36].The fair comparisons of the license plate algorithms developed under the similar assumptions and for the predefined settings would be possible only over the same image database. However, such an exhaustive comparison is beyond a scope of this paper.…”

Brazilian Automatic License Plate Recognition: On the Importance to Add Vehicle Detection Phase in a Deep Learning Approach

“…The automatic recognition of license plates can be defined as a series of digital image processing and computer vision techniques that seek, from an image or video with vehicles, to extract the license plate information in the text format [1]. With the increased use of surveillance cameras in cities, the possible applications of this technology in society are countless, but we can highlight: assistance in monitoring highways and streets; detection and search of stolen vehicles; access monitoring to public and private places and among other applications [2].…”

Detecção E Reconhecimento De Placas De Licenciamento Veicular Em Tempo Real Usando CNN

“…A detecção e o reconhecimento de placas de licenciamento veicular não é uma tarefa trivial de se realizar. Existe uma série de fatores que dificultam todo o processo, como, por exemplo, placa danificada e ou desgaste do material, variação de iluminação, distância em que a imagem é capturada, entre outros (SILVA et al, 2013) (WANG;ZHU;ZHANG, 2016) (CORNETO et al, 2017).…”