Advancing Parking Systems: A Performance Comparison of MobileNet and Canny in License Plate Detection

Vehicle license plate (LP) detection is a relatively complex problem until we assume the use of a static camera, variations in illumination, known templates of the LP, guaranteed color patterns and other simple assumptions. Practical applications demand robust and generalized LP detection techniques to accommodate complex scenarios. This work suggests a new approach to solving this problem by treating the vehicle LP as an object. The primary focus of this study is to address following tasks associated with the challenge of LP detection: (1) LP detection in every frame of a video sequence, (2) detection of partial LPs and (3) detection of LPs with moving cameras and moving vehicles. The state-of-the-art object detection techniques, including convolutional neural networks with region proposal (RCNN), its successors (Fast-RCNN and Faster-RCNN) and the exemplar-SVM, are used in this work to provide solutions to the problem. The suggested study demonstrates better results in comprehensive tests and comparisons than other conventional approaches.

Since 1970's, the need of an automatic license plate recognition system, sometimes referred as Automatic License Plate Recognition system, has been increasing. A license plate recognition system is an automatic system that is able to recognize a license plate number, extracted from image sensors. In specific, Automatic License Plate Recognition systems are being used in conjunction with various transportation systems in application areas such as law enforcement (e.g. speed limit enforcement) and commercial usages such as parking enforcement and automatic toll payment private and public entrances, border control, theft and vandalism control. Vehicle license plate recognition has been intensively studied in many countries. Due to the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. [License plate detection using cluster run length smoothing algorithm ].Generally, an automatic license plate localization and recognition system is made up of three modules; license plate localization, character segmentation and optical character recognition modules. This paper presents an Arabic license plate recognition system that is insensitive to character size, font, shape and orientation with extremely high accuracy rate. The proposed system is based on a combination of enhancement, license plate localization, morphological processing, and feature vector extraction using the Haar transform. The performance of the system is fast due to classification of alphabet and numerals based on the license plate organization. Experimental results for license plates of two different Arab countries show an average of 99 % successful license plate localization and recognition in a total of more than 20 different images captured from a complex outdoor environment. The results run times takes less time compared to conventional and many states of art methods.

Detection and tilt correction of vehicle license plates are inevitable problems to be solved before developing Intelligent Transportation Systems. This paper describes a method of extraction of the vehicle license plate region from a vehicle image with tilt correction. The method consists of five distinct phases: segmenting color, labeling and filtering, correcting tilt, verifying candidate region, and segmenting license plate characters. Initially, an adaptive technique with labeling and filtering capability is utilized to select a statistical threshold value in the HSI color space for detecting candidate vehicle license plate regions. In this way the proposed method can overcome the limitation of the failure to detect a license plate when the vehicle body and license plate are similar colors. The slopes and tilt angles in both the horizontal and vertical directions of the skewed vehicle license plate are determined using the candidate corner points detected by the Smallest Univalue Segment Assimilating Nucleus corner detector, and the license plate region is rotated accordingly. Finally, a horizontal and vertical position histogram is employed to segment the candidate region into rows and constituent characters. The proposed tilt correction method is compared with the least square fitting with perpendicular offsets method and found to outperform results when the tilt angle gradually increases. 145 vehicle images were used for testing with different conditions and the results are presented to prove its efficiency and effectiveness.

Although there has been a huge body of work on Bangla license plate detection and recognition, the successes of these works have largely been limited to correct detection and recognition of undistorted license plates whose images are taken chiefly from the front or the back of vehicles with slight angular variations. As a result, most Bangla automatic license plate recognition (ALPR) systems in practice struggle when the license plates are skewed on the viewing or the image planes of the license plates. In this paper, we address this issue by proposing an analytical approach that can enhance the ALPR of both normal and skewed license plates and can be incorporated into existing Bangla ALPR systems without modifying their internal structures. Specifically, we demonstrate how existing ALPR systems can be treated as black boxes and analyzed to understand what sort of license plate images they work best on and introduce a novel pipeline that combines deep learning and an algorithmic procedure for transforming images of both normal and skewed license plates into formats that are best suited for the ALPR systems. We note that our proposed method can be easily generalized and applied to non-Bangla license plates as well.

As one of the main identification marks of vehicles, vehicle license plate plays an important role in intelligent traffic management, and vehicle license plate detection and recognition is also a hot topic in recent years. Low accuracy of traditional method for license plate detection under the natural scene, the accuracy is higher based on the deep learning of license plate detection, but the real-time performance is poorer, for distortion correction of license plate alignment with special network return the four vertices of license plate, then the perspective transform <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[1]</sup> correct license plate area, the process to further increase the computational complexity. For existing detection and license plate four vertices of regression model, such as MTCNN <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[2]</sup> , but for the big input picture, MTCNN's image pyramid has more computation, so this paper proposes a mobilenet <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[3]</sup> backbone network and sampling at the three different scale layer on the license plate of the network to forecast the results, the network reference yolov4 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">[4]</sup> design ideas, so called mobilenet - yolov4, in addition to regress the category of the license plate and boundary box. Four vertices regress mission add to the license plate detection. The integration of these three tasks into a simple network improves the multiplexing of the network layer and reduces the computation of subsequent license plate alignment. Experiments show that the algorithm has higher real-time and accuracy, and has higher research and application value.

In this paper we present a instant and real-time mobile vehicle license plate recognition system in an open environment. Using a nonfixed video camera installed in the car, the system tries to capture the image of the car in front and to process instant vehicle license plate detection and recognition. Relying on the instant vehicle body recognition, the system can detect and locate the vehicle license plate without the need of background image. Vehicle body detection system utilizes the color characteristics of the barking lights to carry out detection. It first detects the location of the two barking lights in the captured image. Then set license plate detection region using the probability distribution of the license plate between the two lights, thus quickly locate the license plate. This method can eliminate any environmental interference during the license plate detection. From the results of experiment, it is determined that this system can effectively and quickly capture the vehicle image, detect and recognize the license plate whether it is dark, raining or under complicated environments.

Detection of vehicle license plates (VLP) become a challenging issue because of the variability in conditions and the types of the license plate. There are several solutions use stationary cameras with a limited angle and specific resolution and also for a specific license plate type. Unfortunately, license plate detection is a challenging issue when vehicles in the open environments and images are taken from a particular range by low cost cameras. Vehicle license plates can be detected with computer vision technology in real-time video conditions. In this paper, we propose vehicle license plates detection system by using convolutional neural network (CNN) with tensorflow. The research was conduct in three step process such as data pre-processing, training/testing process, and interpretation result. Using CNNs algorithm in tensorflow with 25,000 steps and 8 batches on the training process can produce a training model of vehicle license plates detection with high accuracy around 70-99%.

Frequently, there is a need to identify vehicle license plates (VLP) in images taken from a camera that is far away from the vehicle for security. The extracted information from vehicle license plates is used for enforcement, access-control, and flow management, e.g. to keep a time record for automatic payment calculations or to fight against crime. That's make license plates detection crucial and inevitable in the vehicle license plate recognition system. This paper aims to present a new robust method to detect and localize license plates in images. Especially we focus on the Moroccan's VLP. The proposed approach is based on edge features and characteristics of license plate's characters. Various images including Moroccan's VLP taken from different distances and under different angles were used to evaluate the proposed method. The experimental results show that our system can efficiently detect and localize the Moroccan's VLP in the images. Indeed, the recall/precision curve of the proposed method proves that 95% precision rate is obtained for recall rate value equals to 81%. In addition, the standard measure of quality is equal to 87.44 %.

Automatic license plate recognition (ALPR) is generally considered a solved problem in the computer vision community. However, most of the current works on ALPR are designed to work on license plates (LP) from specific countries and use country-specific information which limits their practical applicability. Such ALPR systems require changes in the algorithm to work on other countries’ LPs. Previous works on multinational LP recognition are tested on datasets from various countries that share the same LP layout. To address this issue, this study presents a deep ALPR system designed to be applicable to multinational LPs. The proposed approach consists of three main steps– LP detection, unified character recognition, and multinational LP layout detection. The system is mainly based on the you only look once (YOLO) networks. Particularly, tiny YOLOv3 was used for the first step whereas the second step uses YOLOv3-SPP– a version of YOLOv3 that consists of the spatial pyramid pooling (SPP) block. The localized LP is fed into YOLOv3-SPP for character recognition. The character recognition network returns the bounding boxes of the predicted characters and does not provide information about the sequence of the LP number. A LP number with an incorrect sequence is considered wrong. Thus, to extract the correct sequence, we propose a layout detection algorithm that can extract the correct sequence of LP numbers from multinational LPs. We collected our own Korean car plate (KarPlate) dataset and made it publicly available. The proposed system was evaluated on LP datasets from five countries which include South Korea, Taiwan, Greece, USA, and Croatia. In addition, a small dataset containing LPs from 17 countries was collected to evaluate the effectiveness of the multinational LP layout detection algorithm. The proposed ALPR system consumes about 42 ms per image on average for extracting LP number. Experimental results demonstrate the effectiveness of our ALPR system.

This paper suggests a method for enhancing vehicle license plate recognition performance and detection accuracy under unfavorable conditions through improving images by using the vehicle license plate region detection and denoising autoencoder technologies of Faster R-CNN in order to improve misrecognition in detection performance due to the slanting or breakage of license plates, or the influence of illumination, which are chronic problems in automatic license plate recognition system at construction sites. The learning of 3,000 images collected from actual construction sites were conducted for this paper, and the improvement of illumination resulted in more than 30% improvement in accuracy.

License Plate Detection is an intelligent system to find the exact license plate by analyzing image/video data for automatic license plate recognition (ALPR) system. The proposed system used image data. There is much early research has been done for ALPR purposes, however, it was still challenging tasks for accurately detect license plates in the open environment. The main difficulties lie in the diversity of plates such as language, font, color, and type of the number plates that differ across nations and conditional variations such as various background scenes and illumination when captured. The fundamental ALPR system consists of three processes: license plate detection, character segmentation, and character recognition. Proposed system focused on license plate detection based on image processing technology that is a crucial step for the whole ALPR system. A Myanmar License plate has a white boundary for every different color of plates, thus the proposed system applied an edge-based approach for any color of plates, and the plate region will remain because of its white boundary. After edge detection, morphological operation has been applied as it can add or remove pixels from/to the objects in an image. Thus the license plate can be extracted accurately. Finally, the bounding box technology was applied to extract only the number plate region properly.

Automatic License Plate Recognition is a computer vision technology that provides a way to recognize the vehicle's license plates without direct human intervention. Developing Automatic License Plate Recognition methodologies is a widely studied topic among the computer vision community to increase the accuracy rates. Automatic License Plate Recognition systems include image acquisition and character segmentation phases. Although there are many studies, the research in character segmentation and improving recognition accuracy remains limited. The lack of an international standard for license plates and the misinterpretation of ambiguous characters are challenging problems for Automatic License Plate Recognition systems. Several academic works have shown that the ambiguous character problem can be overcome by using a second model that contains only these characters. In this study, we propose a new methodology to reduce the character recognition errors of Automatic License Plate Recognition systems. One of the reasons for the low accuracy rates is the problem of ambiguous characters. In most studies using OCR, it was observed that a single model was used for alphanumeric characters during the recognition phase. Instead of using a single model, using separate models for letters and digits will improve the recognition process and increase accuracy. Therefore, we determined whether the characters are letters or numbers, and we expressed the license plates in the form of letters - digits. The method suggested for segmenting blobs worked with an accuracy of 96.12% on the test dataset. The method recommended for generating letter-digit expressions for the license plates worked with an accuracy of 99.28% on the test dataset. The proposed methodology can work only on Turkish license plates. In future studies, we will expand our method by using the license plate dataset of a different country.

Vehicle license plate detection and recognition is one application of computer vision which was widely deployed in traffic monitoring, road toll, and parking lot system. Its benefits are reducing service labor and increase processing accuracy. There are many studies in this area such as robotics and machine learning. With the strong development of neural networks and deep learning, application deployment becomes easier and more accurate. This paper focuses on the development of a license plate detector that supports the license plate detection and recognition system in unusual conditions under the influence of light, weather, and camera placement. The license plate detector is built based on the backbone, Feature Pyramid Network (FPN), and triple detector. The network was trained and tested on the CCPD (Chinese City Parking Dataset) dataset and achieved 96.1&#x0025; of AP (Average Precision) in total, the network can outperform the state-of-the-art detection network in this field. On the other hand, the license plate detection network combined with the LPRNet network (License Plate Recognition via Deep Neural Networks) embedded by the Spatial Transformer to recognize the numbers and characters in the license plate with 98.8&#x0025; of AP on CCPD-Base subset. As a result, the number plate detector exhibits superior capabilities compared to previous methodologies under unusual conditions, thereby enhancing the overall processing visibility of the system.

Detecting license plate (LP) is a crucial and inevitable component of the vehicle license plate recognition (VLPR) system. In this paper to select automatically statistical threshold value in HSI color model is proposed. The proposed vehicle license plate detection (VLPD) method consists of two main stages. Initially, HSI color model is adopted for detecting candidate regions. According to different colored LP, these candidate regions may include LP regions; geometrical properties of LP are then used for classification. The proposed method is able to deal with candidate regions under independent orientation and scale of the plate. Finally, the decomposition of candidate regions contains predetermined LP alphanumeric characters by using position in the histogram to verify and detect vehicle license plate (VLP) region. Experimental results show that the proposed method is very effective in coping with different images under the variety of conditions such as complex scenes, illumination changing, distances and varied weather etc.

- Indonesia is a country with an increasing number of vehicles each year. However, with the growing traffic density in urban areas, traffic violations such as disregarding traffic signs and exceeding speed limits often occur. This research aims to implement the Automatic License Plate Recognition (ALPR) system using the K-Nearest Neighbors (KNN) algorithm to predict and recognize vehicle license plates in plate images. The research also aims to evaluate the accuracy level of the implemented ALPR system. The method used in this research is KNN, which is one of the classification methods in machine learning. The training data used consists of a collection of preprocessed vehicle license plate images. After the training process, the system can recognize and predict vehicle license plates in new plate images. The research results show that the implemented ALPR system using the KNN algorithm can achieve an accuracy level of 93% in recognizing vehicle license plates. This success demonstrates that KNN is an effective algorithm for license plate recognition in plate images. This research has important implications for the development of ALPR systems that can be used for various purposes such as traffic surveillance, security, and law enforcement.