DELP-DAR system for license plate detection and recognition

• Published in: Pattern recognition letters 2020-01, Vol.129, p.213-223
• Main Authors: Selmi, Zied, Halima, Mohamed Ben, Pal, Umapada, Alimi, M. Adel
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Computer vision; Datasets; Deep learning; Fonts; Image detection; Image processing; Image quality; Image segmentation; Intelligent transportation systems; Languages; License plates; LP detection; LP recognition; Mask R-CNN; Neural networks; Numbering schemes; Recognition; Robustness
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2019.11.007

•The application of new training algorithm of Mask-RCNN in license plate field.•Solve the problems of detecting and recognizing LPs in several context, environment and in complex conditions.•Detect and recognize the LPs in multi-language: American and Arabic.•Collection of a new Arabic LPs dataset to test our system. Automatic License Plate detection and Recognition (ALPR) is a quite popular and active research topic in the field of computer vision, image processing and intelligent transport systems. ALPR is used to make detection and recognition processes more robust and efficient in highly complicated environments and backgrounds. Several research investigations are still necessary due to some constraints such as: completeness of numbering systems of countries, different colors, various languages, multiple sizes and varied fonts. For this, we present in this paper an automatic framework for License Plate (LP) detection and recognition from complex scenes. Our framework is based on mask region convolutional neural networks used for LP detection, segmentation and recognition. Although some studies have focused on LP detection, LP recognition, LP segmentation or just two of them, our study uses the maskr-cnn in the three stages. The evaluation of our framework is enhanced by four datasets for different countries and consequently with various languages. In fact, it tested on four datasets including images captured from multiple scenes under numerous conditions such as varied orientation, poor quality images, blurred images and complex environmental backgrounds. Extensive experiments show the robustness and efficiency of our suggested Extensive experiments show the robustness and efficiency of our suggested system that achieves in accuracy rate 99.3% on AOLP and 98.9% on Caltech dataset.