Representation learning in a deep network for license plate recognition (original) (raw)
Related papers
Real-time Automatic License Plate Recognition Through Deep Multi-Task Networks
Conference on Graphics, Patterns and Images (SIBGRAPI), 2018
With the increasing number of cameras available in the cities, video traffic analysis can provide useful insights for the transportation segment. One of such analysis is the Automatic License Plate Recognition (ALPR). Previous approaches divided this task into several cascaded subtasks, i.e., vehicle location, license plate detection, character segmentation and optical character recognition. However, since each task has its own accuracy, the error propagation between each subtask is detrimental to the final accuracy. Therefore, focusing on the reduction of error propagation, we propose a technique that is able to perform ALPR using only two deep networks, the first performs license plate detection (LPD) and the second performs license plate recognition (LPR). The latter does not execute explicit character segmentation, which reduces significantly the error propagation. As these deep networks need a large number of samples to converge, we develop new data augmentation techniques that allow them to reach their full potential as well as a new dataset to train and evaluate ALPR approaches. According to experimental results, our approach is able to achieve state-of-the-art results in the SSIG-SegPlate dataset, reaching improvements up to 1.4 percentage point when compared to the best baseline. Furthermore, the approach is also able to perform in real time even in scenarios where many plates are present at the same frame, reaching significantly higher frame rates when compared with previously proposed approaches.
Employing Deep Learning Approaches for Automatic License Plate Recognition: A Review
3rd International Conference on Soft Computing, 2019
Employing deep learning approaches has resulted in magnificent perfections in computer vision applications in recent years. In addition, Deep Neural Networks (DNNs) have shown to be remarkable alternatives for common shallow machine learning techniques like Support Vector Machines (SVM). Deep learning provides great solutions for both classic and modern image processing, feature extraction and object detection problems. Considering the advantages of utilizing DNNs in a wide range of computer vision fields, this paper presents a concise review of different deep learning approaches employed in Automatic License Plate Recognition (ALPR) systems. In such systems, deep learning techniques have been utilized in various phases of ALPR including license plate detection, character segmentation and Optical Character Recognition (OCR). Additionally, a comprehensive overview of common DNN architectures is introduced for better clarification and classification of introduced methods.
ArXiv, 2019
Smart automated traffic enforcement solutions have been gaining popularity in recent years. These solutions are ubiquitously used for seat-belt violation detection, red-light violation detection and speed violation detection purposes. Highly accurate license plate recognition is an indispensable part of these systems. However, general license plate recognition systems require high resolution images for high performance. In this study, we propose a novel license plate recognition method for general roadway surveillance cameras. Proposed segmentation free license plate recognition algorithm utilizes deep learning based object detection techniques in the character detection and recognition process. Proposed method has been tested on 2000 images captured on a roadway.
Car license plate segmentation and recognition system based on deep learning
Bulletin of Electrical Engineering and Informatics, 2022
Artificial intelligence techniques and computer vision techniques dealt with the issue of automatic license plate recognition (ALPR) that has many applications in important research field. In this paper, the method of recognizing the license plates of Iraqi cars was applied based on deep learning techniques convolutional neural network (CNN). The two database built to identifying Iraqi car plates. First database includes 2000 images of Arabic numbers and Arabic letters. Second database conations 1200 images of the Arabic names for Iraqi governorates. This paper used imageprocessing techniques to segmenting the numbers, letters and words from the car license plate images and then convert them into two databases that used to train the two CNN. These training CNN used to recognizing the vocabulary of the car license plate. The success rate of the numbers, letters and words recognition was 98%. The overall rate of success of this proposed system in all stages was 97%.
Development of a Nigerian Vehicle License Plate Recognition System Using Deep Learning
IJSES, 2024
License Plate Recognition (LPR) is a technology that combines object detection and optical character recognition (OCR) to automatically identify vehicles by their license plates. This study explores the development and evaluation of an LPR system using deep learning techniques. The system was trained and tested on a dataset of 1000 car images, with annotations provided using Label Studio. Various object detection models, including InceptionResNetV2, MobileNetV2, InceptionV3, and YOLOv8, were evaluated for their accuracy and efficiency. YOLOv8 emerged as the most suitable model due to its superior performance, achieving high precision, recall, and mAP (mean Average Precision) metrics. The study also investigated the challenges of character recognition in low-resolution images and explored the integration of a Superresolution Generative Adversarial Network (SRGAN) with Tesseract-OCR to enhance character recognition accuracy. The findings of this research contribute to the advancement of LPR technology and its potential applications in traffic management, security, and law enforcement.
A Deep Learning Solution for Vehicle License Plate Detection
ICEAT Sep 2024 - Conference proceedings vol1, 2024
Accurate vehicle license plate detection is crucial for various applications, including traffic management and law enforcement. Deep learning has emerged as a powerful tool for enhancing the accuracy and efficiency of this task. This research aims to develop and evaluate a deep learning-based solution for detecting vehicle license plates with high accuracy and efficiency. The proposed solution utilizes a Convolutional Neural Network (CNN) architecture trained on a diverse dataset of vehicle images. Various preprocessing techniques, including image augmentation, were employed to enhance the model's robustness. The model was evaluated using metrics such as precision, recall, and Intersection over Union (IoU) to ensure its effectiveness. The experimental results demonstrate that the proposed deep learning model achieved a high detection accuracy of 95%, outperforming traditional methods in both precision and recall. These findings suggest that the developed deep learning solution is a reliable and efficient approach for vehicle license plate detection. Future work will focus on optimizing the model for real-time applications and extending its capabilities to license plate recognition
Improving the performance of license plate detection using deep neural networks on diverse datasets
IRJET, 2022
The detection of license plates (LPs) is a crucial step to develop the intelligent traffic management systems. Several challenges exist for the detection of LPs such as the high variation of the geometry of LPs or the frequent variation in the conditions of LP image acquisition. The paper proposed improvements for the detection of LPs. Firstly, advanced deep neural networks are employed to detect LPs accurately. For training the deep neural networks efficiently, the data augmentation techniques are applied. Then, the strategies of the deployment and testing of the deep neural networks on various hardware plat- forms are proposed to improve the inference time of LP detection. We have performed the evaluation on two public datasets (Vietnamese license plate detection and Kaggle datasets). The performance comparison (the detection accuracy and execution time) with existed methods on various hardware platforms shows the effectiveness of the proposed method.
Desktop Based Application for Numberplate and License Recognition Using Deep Learning
2021
In this research, we look at detecting and recognizing car license plate’s problem in natural scene photographs. In a single forward transfer, here We introduce a deep neural network that could simultaneously locate license number plates and identify letters. The entire network could be trained from start to end. Unlike current techniques, which consider license plate detection and identification as two separate tasks that must be solved one at a time, our system incorporates the two tasks into one network that can solve them both simultaneously. It not only prevents intermediate errors from building up, but it also speeds up the processing. Four data sets containing photographs taken from different scenes under various conditions are evaluated for performance evaluation. Extensive tests demonstrate the efficacy and effectiveness of our suggested strategy. Index Terms Car Plate Detection, deep neural network, license identification.
Licence Plate Recognition Using Supervised Learning and Deep Learning
IRJET, 2022
For example, cost transaction frameworks, halting expenditure payment frameworks, and private access control are widely used in present metropolitan regions. With these technological frameworks, people's dayto-day activities may be made easier, as well as the job of executives. It is a well-developed but erroneous innovation: the calculation of tag acknowledgment, for example. It is difficult to use real-world sceneries since the standard area acknowledgment calculation is affected by light, shadows, foundation complexity, and other factors. The computation for determining licence recognition can extricate more components as deep learning progresses, increasing the discovery and recognition precision tremendously. As a result, the focus of this research is on the application of deep learning to vehicle identification plates. As indicated by this cycle, the profound learning calculations are categorised into direct identification and backhanded discovery calculations; the benefits of the flow and flow tag location and character acknowledgment calculations and the distinctions in informational collocation are broken down; Present the most advanced calculation from the three principle special challenges: tag angle, picture commotion, and tag obscure. Examine the current public tag databases to determine the number of images, purpose, and ecological complication and devise a plan for future licence plate examinations under the new examination heading.