License plate recognition based on temporal redundancy

Abstract

Recognition of vehicle license plates is an important task applied to a myriad of real scenarios. Most approaches in the literature first detect an on-track vehicle, locate the license plate, perform a segmentation of its characters and then recognize the characters using an Optical Character Recognition (OCR) approach. However, these approaches focus on performing these tasks using only a single frame of each vehicle in the video. Therefore, such techniques might have their recognition rates reduced due to noise present in that particular frame. On the other hand, in this work we propose an approach to automatically detect the vehicle on the road and identify (locate/recognize) its license plate based on temporal redundant information instead of selecting a single frame to perform the recognition. We also propose two post-processing steps that can be employed to improve the accuracy of the system by querying a license plate database (e.g., the Department of Motor Vehicles database containing a list of all issued license plates and car models). Experimental results demonstrate that it is possible to improve the vehicle recognition rate in 15.5 percentage points (p.p.) (an increase of 23.38%) of the baseline results, using our proposal temporal redundancy approach. Furthermore, additional 7.8 p.p. are achieved using the two post-processing approaches, leading to a final recognition rate of 89.6% on a dataset with 5, 200 frame images of 300 vehicles recorded at Federal University of Minas Gerais (UFMG). In addition, this work also proposes a novel benchmark, designed specifically to evaluate character segmentation techniques, composed of a dataset of 2, 000 Brazilian license plates (resulting in 14, 000 alphanumeric symbols) and an evaluation protocol considering a novel evaluation measure, the Jaccard-Centroid coefficient.

A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector

“…Knowing that all Brazilian LPs have the same format: three letters and four digits, we use 26 classes for letters and 10 classes for digits. As pointed out by Gonc ¸alves et al [25], this reduces the incorrect classification.…”

“…We train two CNNs in this stage: one for vehicle detection in the input image and other for LP detection in the detected vehicle. Recent works [20], [25] also performed the vehicle detection first.…”

“…Many authors have proposed approaches with a vehicle detection stage prior to LP detection, aiming to eliminate false positives (FPs) and reduce processing time [5][6][7]. Regarding character This paper is a preprint of a paper submitted to IET Intelligent Transport Systems.…”

Deep Classifiers-Based License Plate Detection, Localization and Recognition on GPU-Powered Mobile Platform

“…The results show that there was an increase of two percent in single character accuracy and an increase of 13 percent in full plate accuracy after error correction. Furthermore, the temporal redundancy approach can be employed for classification using multiple frames [17]. Instead of a single frame, multiple frames can be processed and averaged using the simplified proposed flow of the ALPR system for accuracy improvement.…”

Automatic License Plate Recognition: An Efficient and Layout-Independent System Based on the YOLO Detector

“…We consider LP recognition as the current bottleneck of ALPR systems since (i) impressive LP detection results have been reported in recent works [13], [20], [22], both in terms of recall rate and execution time; (ii) Optical Character Recognition (OCR) approaches must work as close as possible to the optimality (i.e., 100%) in the ALPR context, as a single mistake may imply in incorrect identification of the vehicle [33]. Therefore, in this work, we propose a unified approach for LP detection and layout classification in order to improve the recognition results using heuristic rules.…”