Figure 3 - available via license: CC BY
Content may be subject to copyright.
Algorithm flow chart of the proposed smart access control for vehicle entrance using sensors platform and an image-based LP recognition.
Source publication
The paper proposes a sensors platform to control a barrier that is installed for vehicles entrance. This platform is automatized by image-based license plate recognition of the vehicle. However, in situations where standardized license plates are not used, such image-based recognition becomes non-trivial and challenging due to the variations in lic...
Contexts in source publication
Context 1
... section explains the proposed architecture including the main functions from vehicle detection to the barrier control mechanism. Figure 2 illustrates the block diagram of the proposed system while Figure 3 depicts the algorithm flowchart of the proposed system. Following are the main steps. ...
Context 2
... this end, for a segment to be considered an LP, the number of objects inside that segment should be more than five. This is due to the fact that the Pakistani LP consists of at least five characters as shown in Figure 3. Once the mask of the LP is generated in this way, it is used to extract the LP from the RGB image. ...
Similar publications
A License Plate Recognition (LPR) is a technique to automatically identify and recognize the license plate of a vehicle. In today's world where we want to do everything in no time, automated LPR has opened a new door in Intelligent Traffic System. With the help of ALPR, we can implement many smart systems starting from a parking facility to crime i...
Citations
... The system incorporates many real-world elements, such as screw fastening, typeface variety, spacing, color, and various number plate symbolism. 8 Images collected from diverse scenes assess how well the suggested technique works. The system's accuracy for locating license plates is 97.9%, and its success rate for identifying plates is 95.6%. ...
Car owners altering license plates using different typefaces and designs violate the law that strictly forbids such behaviour. Traffic police officers claim that changing the license plates makes it impossible to read the registration numbers due to an increase in fatal street collisions and car thefts. They worry that it may be difficult to track down vehicles used in hit-and-run incidents. It is challenging to impose further limitations on any algorithm used to identify and recognise license plates in a developing nation like Bangladesh. This work has the primary objective of designing a reliable detection and recognition system for transitional, standard car license plates, which are frequently seen in developing countries. Increase the effectiveness of reading license plates drawn or printed in various styles and typefaces employing cuttingedge technology, including machine learning (ML) models. For this study, You Only Look Once (YOLOv3) is used to utilising the most recent version of the object detection method. The raw image is pre-processed to increase its quality and then divided into appropriate-sized grid cells to determine where the license plate should be placed. After that, the data is post-processed, and the accuracy of the proposed model is evaluted using industry-recognised standards. A sizeable image dataset was used to be tested using this proposed methodology. The presented system is expected to be essential for vehicle monitoring, parking fee collection, lowering traffic accidents, and identifying unregistered vehicles. The results demonstrate that the suggested method achieves 97.1% mAP, 95.3% precision and 96.8% in plate detection
... The system incorporates many real-world elements, such as screw fastening, typeface variety, spacing, color, and various number plate symbolism. 8 Images collected from diverse scenes assess how well the suggested technique works. The system's accuracy for locating license plates is 97.9%, and its success rate for identifying plates is 95.6%. ...
Car owners altering license plates using different typefaces and designs violate the law that strictly forbids such
behaviour. Traffic police officers claim that changing the license plates makes it impossible to read the registration
numbers due to an increase in fatal street collisions and car thefts. They worry that it may be difficult to track
down vehicles used in hit-and-run incidents. It is challenging to impose further limitations on any algorithm
used to identify and recognise license plates in a developing nation like Bangladesh. This work has the primary
objective of designing a reliable detection and recognition system for transitional, standard car license plates,
which are frequently seen in developing countries. Increase the effectiveness of reading license plates drawn
or printed in various styles and typefaces employing cutting-edge technology, including machine learning (ML)
models. For this study, You Only Look Once (YOLOv3) is used to utilising the most recent version of the object
detection method. The raw image is pre-processed to increase its quality and then divided into appropriate-sized
grid cells to determine where the license plate should be placed. After that, the data is post-processed, and the
accuracy of the proposed model is evaluted using industry-recognised standards. A sizeable image dataset was
used to be tested using this proposed methodology. The presented system is expected to be essential for vehicle
monitoring, parking fee collection, lowering traffic accidents, and identifying unregistered vehicles. The results
demonstrate that the suggested method achieves 97.1% mAP, 95.3% precision and 96.8% in plate detection
... Image-based text detection, extraction and recognition is applied to reduce the time and cost of several applications such as the recognition of number plates [1,2], medical images [3] and road signs [4]. In this regard, the proposed system is based on these techniques by applying them to the novel problem of automatic image-based electrical energy meter reading in Pakistan. ...
... This work proposes using the methodology proposed for license plate characters extraction and recognition [1] where the following set of features are calculated to represent the digits in feature vectors. ...
We propose to perform an image-based framework for electrical energy meter reading. Our aim is to extract the image region that depicts the digits and then recognize them to record the consumed units. Combining the readings of serial numbers and energy meter units, an automatic billing system using the Internet of Things and a graphical user interface is deployable in a real-time setup. However, such region extraction and character recognition become challenging due to image variations caused by several factors such as partial occlusion due to dust on the meter display, orientation and scale variations caused by camera positioning, and non-uniform illumination caused by shades. To this end, our work evaluates and compares the state-of-the art deep learning algorithm You Only Look Once (YOLO) along with traditional handcrafted features for text extraction and recognition. Our image dataset contains 10,000 images of electrical energy meters and is further expanded by data augmentation such as in-plane rotation and scaling to make the deep learning algorithms robust to these image variations. For training and evaluation, the image dataset is annotated to produce the ground truth of all the images. Consequently, YOLO achieves superior performance over the traditional handcrafted features with an average recognition rate of 98% for all the digits. It proves to be robust against the mentioned image variations compared with the traditional handcrafted features. Our proposed method can be highly instrumental in reducing the time and effort involved in the current meter reading, where workers visit door to door, take images of meters and manually extract readings from these images.
... Handcrafted features: Farmanullah et al. [23] perform detection of the license plates using image processing operators. The character recognition on the detected license plates is then performed by evaluating various machine learning classifiers over the geometric features of the characters. ...
We propose an automatic framework for toll collection, consisting of three steps: vehicle type recognition, license plate localization, and reading. However, each of the three steps becomes non-trivial due to image variations caused by several factors. The traditional vehicle decorations on the front cause variations among vehicles of the same type. These decorations make license plate localization and recognition difficult due to severe background clutter and partial occlusions. Likewise, on most vehicles, specifically trucks, the position of the license plate is not consistent. Lastly, for license plate reading, the variations are induced by non-uniform font styles, sizes, and partially occluded letters and numbers. Our proposed framework takes advantage of both data availability and performance evaluation of the backbone deep learning architectures. We gather a novel dataset, \emph{Diverse Vehicle and License Plates Dataset (DVLPD)}, consisting of 10k images belonging to six vehicle types. Each image is then manually annotated for vehicle type, license plate, and its characters and digits. For each of the three tasks, we evaluate You Only Look Once (YOLO)v2, YOLOv3, YOLOv4, and FasterRCNN. For real-time implementation on a Raspberry Pi, we evaluate the lighter versions of YOLO named Tiny YOLOv3 and Tiny YOLOv4. The best Mean Average Precision (mAP@0.5) of 98.8% for vehicle type recognition, 98.5% for license plate detection, and 98.3% for license plate reading is achieved by YOLOv4, while its lighter version, i.e., Tiny YOLOv4 obtained a mAP of 97.1%, 97.4%, and 93.7% on vehicle type recognition, license plate detection, and license plate reading, respectively. The dataset and the training codes are available at https://github.com/usama-x930/VT-LPR
... Accordingly, the matter of controlling proximity arises. In current research, physical access control is performed at the perimeter [4] of a physical space such as a door to the room [5]. These approaches do not cater toward proximity-based access control once within the room. ...
Cyber-physical systems are defined by the integration of physical space entities and cyberspace information processing systems. Physical access control is generally perimeter-based, where assets can be vulnerable to a malicious entity once they have entered the perimeter of the space. Therefore, the relative distances between subjects and objects are needed to enforce cyber-physical access control within the perimeter of the physical space. The interplay between a physical entity and its virtual representation can be modelled using the concept of a digital twin. A digital twin enables the virtual monitoring of a physical entity to ensure better access control decision-making. This research presents a prototype indoor positioning and tracking system that can uniquely identify and track people and equipment in physical 3D space to create and maintain digital twins in real-time. The integration of 2D image processing and 3D depth-sensing technologies results in a system that can monitor a physical space where entities come into proximity to one another. Furthermore, the system can be used to prevent transgressions between physical entities within a relative distance of a few centimetres by tracking entities using human digital twin technology and reporting their relative proximity to an access control system for real-time enforcement.
... The physical components that capture pictures and the algorithms that analyze the pictures define the quality of an AVLPR system. The detection range of interest in the images, such as the license plate, character extraction from the license plate, and identification of the characters are the three steps of a typical AVLPR system [7]- [9]. ...
Securing and monitoring the territory have become a big challenge for everyone as the number of vehicle users have increased. The premise area must be secure with enforced entrances and exits. It should have an automated and efficient security and monitoring system. For this purpose, an automated vehicle access system with accurate and secure monitoring of vehicle entry and exit was developed with Graphical User Interface (GUI) and vehicle’s user database along with the prototype of Ultra-High Frequency RFID. The suitable configuration for the hardware prototype has also been evaluated to maximize the system’s capabilities. This system operates on frequencies from 400MHz to 950MHz and is performed at distances of 7 meters. The passive tag was attached to the various condition and sizes of the car. The result shows showed that the system was optimally performed with the speed of the vehicle up to 50 km/h, 7 m of reading range and a maximum 20% tinted windshield. The ideal angle for the reader is around 60ᵒ to 70ᵒ with 2 meters of mounting pole. For future improvement, it is suggested that the registered vehicle user data was linked with the official premise’s database and the data is saved in an off-site location (cloud storage). The GUI is also able to support more than 1 reader at a time depending on demand.
... The authors propose a sensors platform control a barrier that contains an image-based license plate recognition of the vehicle in [21]. The proposed approach performs plate recognition in challenging environments such as variations in license plate background, use of different fonts, and deformations. ...
... We frequently use adaptation thresholding filters to increase the plate area before segmentation is performed. The threshold adaptation is used to separate the absence of light foreground from the illuminated background [21]. After thresholding, the horizontal projection P x (x) of license plate ( f (x, y)) is calculated. ...
Non-standard license plates are a part of current traffic trends in Pakistan. Private number plates should be recognized and, monitored for several purposes including security as well as a well-developed traffic system. There is a challenging task for the authorities to recognize and trace the locations for the certain number plate vehicle. In a developing country like Pakistan, it is tough to have higher constraints on the efficiency of any license plate identification and recognition algorithm. Character recognition efficiency should be a route map for the achievement of the desired results within the specified constraints. The main goal of this study is to devise a robust detection and recognition mechanism for non-standard, transitional vehicle license plates generally found in developing countries. Improvement in the character recognition efficiency of drawn and printed plates in different styles and fonts using single using multiple state-of-the-art technologies including machine-learning (ML) models. For the mentioned study, 53-layer deep convolutional neural network (CNN) architecture based on the latest variant of object detection algorithm-You Only Look Once (YOLOv3) is employed. The proposed approach can learn the rich feature representations from the data of diversified license plates. The input image is first pre-processed for quality improvement, followed by dividing it into suitable-sized grid cells to find the correct location of the license plate. For training the CNN, license plate characters are segmented. Lastly, the results are post-processed and the accuracy of the proposed model is determined through standard benchmarks. The proposed method is successfully tested on a large image dataset consisting of eight different types of license plates from different provinces in Pakistan. The proposed system is expected to play an important role in implementing vehicle tracking, payment for parking fees, detection of vehicle over-speed limits, reducing road accidents, and identification of unauthorized vehicles. The outcome shows that the proposed approach achieves a plate detection accuracy of 97.82% and the character recognition accuracy of 96%.
... Many researchers have worked with Convolutional Neural Network (CNN) in recent years, due to its numerous potentials for solving problems related to object detection and classification [3]. CNN is considered as "a special architecture of artificial neural networks and the top-performing model" which currently has many applications in license plate detection and localization [4]. ...
... Salt and pepper noises are associated with license plates identification system. To eliminate the noises, authors in [10] utilized a median filter while authors in [3] utilized a Gaussian filter. The images were made readable in [11] by the usage of different image preprocessing techniques. ...
Real-time identification of vehicle license plate has become more practical within the last decade in many applications such as; storage and retrieval of vehicular inflow records, automatic toll collection, parking fee payment, traffic monitoring, tracking of moving vehicles, recovery of stolen vehicles etc. A lot of researches have been carried out on vehicles license plates detection and localization which has led to the development of new techniques and modification of existing techniques. In this paper, we present an improved Faster Region-based Convolutional Neural Network (R-CNN) for localizing vehicle license plates. The Faster R-CNN utilized inceptionV2 architecture. The region of interest pooling of the existing Faster R-CNN was replaced by region of interest align which improvedthe creation quality of region proposals for license plateslocalization. The performance of the model was evaluated usingMean Average Precision (mAP) obtained from the precision-recall (PR) curves that were computed during model training andaccuracy of 99% was achieved. The performance of the systemwas evaluated via real-time testing with 100 vehicles andlocalization accuracy of 99% was achieved. An effective camerato vehicle distance was also established via real time testing atdifferent camera to vehicle distances.
... The authors [7] propose the client-server system of license plate recognition by using the mobile phone. In [8], the barrier access control system is presented that is based on the RaspberryPi platform and sensors. However, an essential fault of the algorithms used by the authors is the inability to process the stream video. ...
A new mathematical model of the intelligent access monitoring and control system based on the cybernetic approach is proposed for solving the problems of vehicle access to the territory of an organization. The distinctive feature of the mathematical model is the ability to take into account and recognize normal and abnormal situations at the protected object and develop control actions. To localize vehicles and recognize their license plates, the composition of traditional methods of image processing and two-pass classification performed by the developed modified architecture of convolutional neural network MobileNet is offered. The composition allows to define additional identification features of the object. The proposed adaptations allow to recognize the situation in real time with low computational costs and high accuracy. The natural experiment has shown that the integration of the modern hardware means and algorithms of object detection and recognition, even in the rough conditions of street closed-circuit television monitoring, provides not less than 96% accuracy, and the processing time of one frame is not more than 0.094 s based on the Nvidia GeForce 1080Ti graphic processor. High recognition accuracy without loss of speed in the real-time mode is achieved by integrating the modern hardware means and the algorithms of object detection and recognition. The program module in Python using the Tensorflow and Keras library is developed for carrying out the access control functions.
... Moreover, many methods [6,[9][10][11]16,18] do not consider the orientation of the license plate, which is only applicable to specific scenarios, such as parking charges and vehicle access/exit management. When it comes to more complex scenarios, such as road scenes, if we regard the tilted license plate as the horizontal direction, it may cause errors in the subsequent license plate recognition [19][20][21][22]. Although Dong et al. [14,23] propose to detect the multidirectional license plate, these methods are very complicated due to adopting multiple separate models. ...
... Both detection branches can detect multidirectional license plates by regressing the four corners of the license plate. After tilt correction, we can improve the license plate recognition performance [19][20][21][22]. The license plate information can be applied to barrier access control [20,22], vehicle target detection [49], vehicle re-identification [50], etc. ...
... After tilt correction, we can improve the license plate recognition performance [19][20][21][22]. The license plate information can be applied to barrier access control [20,22], vehicle target detection [49], vehicle re-identification [50], etc. Moreover, the location of the license plate can be used for vehicle trajectory prediction [51] via license plate detection and tracking. ...
As the license plate is multiscale and multidirectional in the natural scene image, its detection is challenging in many applications. In this work, a novel network that combines indirect and direct branches is proposed for license plate detection in the wild. The indirect detection branch performs small-sized vehicle plate detection with high precision in a coarse-to-fine scheme using vehicle–plate relationships. The direct detection branch detects the license plate directly in the input image, reducing false negatives in the indirect detection branch due to the miss of vehicles’ detection. We propose a universal multidirectional license plate refinement method by localizing the four corners of the license plate. Finally, we construct an end-to-end trainable network for license plate detection by combining these two branches via post-processing operations. The network can effectively detect the small-sized license plate and localize the multidirectional license plate in real applications. To our knowledge, the proposed method is the first one that combines indirect and direct methods into an end-to-end network for license plate detection. Extensive experiments verify that our method outperforms the indirect methods and direct methods significantly.
