scholarly journals License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images

2020 ◽  
Vol 10 (8) ◽  
pp. 2780
Author(s):  
Byung-Gil Han ◽  
Jong Taek Lee ◽  
Kil-Taek Lim ◽  
Doo-Hyun Choi
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Generative Adversarial Networks ◽  
License Plate ◽  
Image Generation ◽  
Adversarial Networks ◽  
Vehicle Registration ◽  
End To End ◽  
Vehicle Information ◽  
Public Datasets

License Plate Character Recognition (LPCR) is a technology for reading vehicle registration plates using optical character recognition from images and videos, and it has a long history due to its usefulness. While LPCR has been significantly improved with the advance of deep learning, training deep networks for LPCR module requires a large number of license plate (LP) images and their annotations. Unlike other public datasets of vehicle information, each LP has a unique combination of characters and numbers depending on the country or the region. Therefore, collecting a sufficient number of LP images is extremely difficult for normal research. In this paper, we propose LP-GAN, an LP image generation method, by applying an ensemble of generative adversarial networks (GAN), and we also propose a modified lightweight YOLOv2 model for an efficient end-to-end LPCR module. With only 159 real LP images available online, thousands of synthetic LP images were generated by using LP-GAN. The generated images not only looked similar to real ones, but they were also shown to be effective for training the LPCR module. As a result of performance tests with 22,117 real LP images, the LPCR module trained with only the generated synthetic dataset achieved 98.72% overall accuracy, which is comparable to that of training with a real LP image dataset. In addition, we improved the processing speed of LPCR about 1.7 times faster than that of the original YOLOv2 model by using the proposed lightweight model.

scholarly journals Research and Implementation of Vehicle Target Detection and Information Recognition Technology Based on NI myRIO

Sensors ◽  
2020 ◽  
Vol 20 (6) ◽  
pp. 1765 ◽  
Author(s):  
Hongliang Wang ◽  
Shuang He ◽  
Jiashan Yu ◽  
Luyao Wang ◽  
Tao Liu
Keyword(s):  
Information Extraction ◽  
Target Detection ◽  
Information Acquisition ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Recognition Algorithm ◽  
License Plate ◽  
Logo Recognition ◽  
Vehicle Information ◽  
High Recognition Accuracy

A vehicle target detection and information extraction scheme based on NI (National Instruments) myRIO is designed in this paper. The vehicle information acquisition and processing method based on image recognition is used to design a complete vehicle detection and information extraction system. In the LabVIEW programming environment, the edge detection method is used to realize the vehicle target detection, the pattern matching method is used to realize the vehicle logo recognition, and the Optical Character Recognition (OCR) character recognition algorithm is used to realize the vehicle license plate recognition. The feasibility of the design scheme in this paper is verified through the actual test and analysis. The scheme is intuitive and efficient, with the high recognition accuracy.

scholarly journals WRGAN: Improvement of RelGAN with Wasserstein Loss for Text Generation

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 275
Author(s):  
Ziyun Jiao ◽  
Fuji Ren
Keyword(s):  
Loss Function ◽  
State Of The Art ◽  
Wasserstein Distance ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Text Generation ◽  
Adversarial Networks ◽  
Slow Progress ◽  
Novel Method ◽  
Public Datasets

Generative adversarial networks (GANs) were first proposed in 2014, and have been widely used in computer vision, such as for image generation and other tasks. However, the GANs used for text generation have made slow progress. One of the reasons is that the discriminator’s guidance for the generator is too weak, which means that the generator can only get a “true or false” probability in return. Compared with the current loss function, the Wasserstein distance can provide more information to the generator, but RelGAN does not work well with Wasserstein distance in experiments. In this paper, we propose an improved neural network based on RelGAN and Wasserstein loss named WRGAN. Differently from RelGAN, we modified the discriminator network structure with 1D convolution of multiple different kernel sizes. Correspondingly, we also changed the loss function of the network with a gradient penalty Wasserstein loss. Our experiments on multiple public datasets show that WRGAN outperforms most of the existing state-of-the-art methods, and the Bilingual Evaluation Understudy(BLEU) scores are improved with our novel method.

scholarly journals CDL-GAN: Contrastive Distance Learning Generative Adversarial Network for Image Generation

2021 ◽  
Vol 11 (4) ◽  
pp. 1380
Author(s):  
Yingbo Zhou ◽  
Pengcheng Zhao ◽  
Weiqin Tong ◽  
Yongxin Zhu
Keyword(s):  
Distance Learning ◽  
Feature Learning ◽  
Image Synthesis ◽  
Image Feature ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Generative Adversarial Network ◽  
Feature Representations ◽  
Adversarial Network ◽  
Public Datasets

While Generative Adversarial Networks (GANs) have shown promising performance in image generation, they suffer from numerous issues such as mode collapse and training instability. To stabilize GAN training and improve image synthesis quality with diversity, we propose a simple yet effective approach as Contrastive Distance Learning GAN (CDL-GAN) in this paper. Specifically, we add Consistent Contrastive Distance (CoCD) and Characteristic Contrastive Distance (ChCD) into a principled framework to improve GAN performance. The CoCD explicitly maximizes the ratio of the distance between generated images and the increment between noise vectors to strengthen image feature learning for the generator. The ChCD measures the sampling distance of the encoded images in Euler space to boost feature representations for the discriminator. We model the framework by employing Siamese Network as a module into GANs without any modification on the backbone. Both qualitative and quantitative experiments conducted on three public datasets demonstrate the effectiveness of our method.

scholarly journals Residential Area Surveillance and Parking System

2020 ◽  
Vol 9 (5) ◽  
pp. 602-606
Keyword(s):  
Character Recognition ◽  
Optical Character Recognition ◽  
Residential Area ◽  
High Rate ◽  
Identification System ◽  
License Plate ◽  
License Plate Recognition ◽  
Position Effects ◽  
Plain Text ◽  
Alert Message

The vehicles playing the vital role in our day to day life for transport, and some of the vehicles violates the traffic rules are also increasing, vehicle theft, unnecessary entering into highly restricted areas, increased number of accidents lead to increase in the rate of crime slowly. The vehicle had its own identity it should be recognized which plays the major role in the world. For recognition of the vehicles which are used commonly in the field of safety and security system, LPDR plays a major role and the vehicle registration number is recognized at some certain distance accurately. License Plate recognition is the most efficient and cost effective technique used for detection and recognition purposes. Automatic license plate recognition (ALPR) is used for finding the location of the license plate in the vehicle. These methods and techniques vary based on the conditions like, quality of the image, vehicle on a fine-tuned position, effects of lighting, type of image, etc. The objective is to design an efficient automatic conveyance identification system of sanctioned or unauthorized in the residential societies by utilizing the conveyance number plate. By getting the car image from the surveillance camera in the entrance, we recognizing the number plate and the characters are extracted using OCR (optical character recognition). It converts the character in the image to plain text. Then the plain text of the license plate is cross-verified with the database to check whether the vehicle belongs to residents or visitor. It sends the alert message to the security official when a new visitor request method in a residential area. The log details are stored separately for the resident and visitor in the database. It also provides the details about the parking area availability in the residential area. By calculating the number of vehicles in and out of the area, the detail or availability parking slot is displayed and it sis robust to the size, lighting effects with high rate of detection.

scholarly journals Fractional Wavelet-Based Generative Scattering Networks

2021 ◽  
Vol 15 ◽  
Author(s):  
Jiasong Wu ◽  
Xiang Qiu ◽  
Jing Zhang ◽  
Fuzhi Wu ◽  
Youyong Kong ◽  
...  
Keyword(s):  
Dimensionality Reduction ◽  
Reduction Method ◽  
Gaussian White Noise ◽  
Principal Component ◽  
Experimental Results ◽  
Generative Adversarial Networks ◽  
Image Generation ◽  
Adversarial Networks ◽  
Dimensionality Reduction Method

Generative adversarial networks and variational autoencoders (VAEs) provide impressive image generation from Gaussian white noise, but both are difficult to train, since they need a generator (or encoder) and a discriminator (or decoder) to be trained simultaneously, which can easily lead to unstable training. To solve or alleviate these synchronous training problems of generative adversarial networks (GANs) and VAEs, researchers recently proposed generative scattering networks (GSNs), which use wavelet scattering networks (ScatNets) as the encoder to obtain features (or ScatNet embeddings) and convolutional neural networks (CNNs) as the decoder to generate an image. The advantage of GSNs is that the parameters of ScatNets do not need to be learned, while the disadvantage of GSNs is that their ability to obtain representations of ScatNets is slightly weaker than that of CNNs. In addition, the dimensionality reduction method of principal component analysis (PCA) can easily lead to overfitting in the training of GSNs and, therefore, affect the quality of generated images in the testing process. To further improve the quality of generated images while keeping the advantages of GSNs, this study proposes generative fractional scattering networks (GFRSNs), which use more expressive fractional wavelet scattering networks (FrScatNets), instead of ScatNets as the encoder to obtain features (or FrScatNet embeddings) and use similar CNNs of GSNs as the decoder to generate an image. Additionally, this study develops a new dimensionality reduction method named feature-map fusion (FMF) instead of performing PCA to better retain the information of FrScatNets,; it also discusses the effect of image fusion on the quality of the generated image. The experimental results obtained on the CIFAR-10 and CelebA datasets show that the proposed GFRSNs can lead to better generated images than the original GSNs on testing datasets. The experimental results of the proposed GFRSNs with deep convolutional GAN (DCGAN), progressive GAN (PGAN), and CycleGAN are also given.

scholarly journals Intelligent Parking System

2019 ◽  
Vol 8 (2S3) ◽  
pp. 550-553
Keyword(s):  
Urban Communities ◽  
Character Recognition ◽  
Optical Character Recognition ◽  
Exit Time ◽  
Region Of Interest ◽  
License Plate ◽  
Past Study ◽  
Entry Time ◽  
Parking System ◽  
Best Fit

As a key part of Automated vehicle technology Intelligent Parking System has become a popular research topic. Intelligent Parking System can grant permission to access the parking area with less human inference. This system can capture image of the vehicle, identify the type of vehicle and allot best fit and optimal parking slot based on its size. It extracts the vehicle’s License plate number, entry time, exit time and calculate total time of the vehicle present with in the parking space. Here, sensors are utilized to identify the presence of the vehicle during entry and exit. Two cameras are utilized to extract features. One camera is used to identify the Region of Interest, Vehicle license plate and identify the characters from the license plate. Tesseract Engine and Optical Character Recognition (OCR) functions are used to detect characters from the image. Another camera is utilized to extract features like dimensions of the vehicle using machine learning operations such as Convolutional Neural Network (CNN). Based on the size of the vehicle, best fit parking slot is allotted which gives optimal usage of parking area. These days the quantity of vehicles is expanding exceptionally, so that, searching for an empty parking slot turns out to be increasingly troublesome. By installing the Intelligent Parking System, in places like, shopping malls, train stations, and airports the need for searching of parking slot significantly reduces. A past study has demonstrated that traffic because of vehicle’s parking slot searching in downtowns of significant urban communities can represent half of the absolute traffic. With such a hefty traffic jam and time delay in parking slot identifying, Intelligent Parking System will be in great demand

Sign in / Sign up

Export Citation Format

Share Document