Robust Chinese License Plate Recognition System

License plate detection and character recognition have unveiled new possibilities and challenges in the field of intelligent transport system. Numerous algorithms have been proposed regarding license plate localization and tracking, character segmentation and character recognition. License plate character recognition is still an active area of research specially in terms of processing complexity. A handful of feature extraction algorithms including vertical and horizontal histogram, center of gravity, structural characteristics, modified edge maps, image projection, multi zoning, adaptive multi zoning, concavities measurement, gradient directional features, median gradient features, longest-run features and momentum features have been proposed. Neural network followed by ensemble classifier shows recognition rate in the high nineties. However, ensemble classifier based on multi-feature is burdened with computational intricacy and lethargic processing. This paper presents a perspective view based license plate character recognition algorithm that copes with some of the inherent problems regarding character recognition. The proposed algorithm is resilient against slant, skewness and obscurity of image while limiting processing time and memory usage. Our algorithm tracks the principal curvature of the segmented image in terms of magnitude and inter-impulse distance. A simple back propagation neural network offers recognition rate of 93% with faster training and validation time. A thorough analysis of the algorithm and meticulous details of implementation are presented throughout this paper.

Automatic License Plate Recognition (ALPR) has been the focus of many\nresearches in the past years. In general, ALPR is divided into the following\nproblems: detection of on-track vehicles, license plates detection, segmention\nof license plate characters and optical character recognition (OCR). Even\nthough commercial solutions are available for controlled acquisition\nconditions, e.g., the entrance of a parking lot, ALPR is still an open problem\nwhen dealing with data acquired from uncontrolled environments, such as roads\nand highways when relying only on imaging sensors. Due to the multiple\norientations and scales of the license plates captured by the camera, a very\nchallenging task of the ALPR is the License Plate Character Segmentation (LPCS)\nstep, which effectiveness is required to be (near) optimal to achieve a high\nrecognition rate by the OCR. To tackle the LPCS problem, this work proposes a\nnovel benchmark composed of a dataset designed to focus specifically on the\ncharacter segmentation step of the ALPR within an evaluation protocol.\nFurthermore, we propose the Jaccard-Centroid coefficient, a new evaluation\nmeasure more suitable than the Jaccard coefficient regarding the location of\nthe bounding box within the ground-truth annotation. The dataset is composed of\n2,000 Brazilian license plates consisting of 14,000 alphanumeric symbols and\ntheir corresponding bounding box annotations. We also present a new\nstraightforward approach to perform LPCS efficiently. Finally, we provide an\nexperimental evaluation for the dataset based on four LPCS approaches and\ndemonstrate the importance of character segmentation for achieving an accurate\nOCR.\n

In this paper, we present a new design flow for robust license plate localization and recognition. The algorithm consists of three stages: 1) license plate localization; 2) character segmentation; and 3) feature extraction and character recognition. The algorithm uses Mexican hat operator for edge detection and Euler number of a binary image for identifying the license plate region. A pre-processing step using median filter and contrast enhancement is employed to improve the character segmentation performance in case of low resolution and blur images. A unique feature vector comprised of region properties, projection data and reflection symmetry coefficient has been proposed. Back propagation artificial neural network classifier has been used to train and test the neural network based on the extracted feature. A thorough testing of algorithm is performed on a database with varying test cases in terms of illumination and different plate conditions. Practical considerations like existence of another text block in an image, presence of dirt or shadow on or near license plate region, license plate with rows of characters and sensitivity to license plate dimensions have been addressed. The results are encouraging with success rate of 98.10% for license plate localization and 97.05% for character recognition.

Automatic License Plate Recognition (ALPR) is a very widely used system in applications such as parking management, theft detection, traffic control and management etc. Most of the existing ALPR systems fail to showcase acceptable performance on real time images/video scenes. This work proposes and demonstrates implementation of a deep learning-based approach to locate license plates of four wheeler vehicles thereby enabling optical character recognition (OCR) to recognize the characters and numbers on the located plates in real time. The proposed system is decomposed into three sub-blocks viz. Vehicle image/video acquisition, License plate localization and OCR. A simple setup using a reasonable resolution webcam has been designed to capture images/videos of vehicles at some entry point. We propose to utilize Single Shot Detector (SSD) based Mobilenet V1 architecture to localize the license plates. The hyper parameters of this architecture are selected with rigorous experimentation so as to avoid over-fitting. We have compared performance of two OCRs viz. Tesseract OCR, Easy OCR and found the superiority of Easy OCR since it utilizes deep learning approach for character recognition. NVIDIA Jetson Nano and Raspberry Pi 3B hardware platforms have been used to implement the entire system. The parameters of these three sub-blocks have been optimized to yield real time performance of ALPR with acceptable accuracy. The proposed and implemented system on Jetson Nano allows processing of videos for ALPR having accuracy more than 95%.

With the increasing advancement of science and technology, the popularity of automobiles in my country has gradually increased. Among them, license plate positioning and license plate recognition technology are very important key technologies in the license plate recognition system. Through the license plate positioning technology, the position information, centroid and other data information of the license plate can be obtained, so as to realize the positioning of the license plate. The license plate recognition technology can extract the uniqueness of the vehicle. Identifying the license plate number, so the design and implementation of vehicle recognition and license plate recognition technology based on embedded devices have practical significance and practical application value to promote the technological progress of intelligent transportation and vehicle recognition systems. This design is a license plate recognition system, an embedded character segmentation recognition processing platform with ARM Cortex-A9 as the core, and the method of cross-compiling OpenCV, Qt, BootLoader in the Linux operating system, and transplanting related drivers to the ARM Cortex-A9 platform; Based on the classic algorithm, the OpenCV library function is used to realize the segmentation and recognition of the license plate image characters. The experimental results show that the design has achieved the expected goal.

License plate recognition is currently used in various situations, such as parking lot vehicle management and the tracking of wanted vehicles. These applications require recognition from all possible camera angles. Therefore, we propose a method for license plate recognition in images captured from various camera angles. First, the license plate area is detected from the input image using the YOLOv5 object detection method. The subsequent process can be performed in two manners: by rotating the license plate to the front using projective transformation and trapezoidal correction, or by using graph matching. The first method performs Hough transforms or linear approximations as preprocessing, and then calculates the rectangle surrounding the license plate from the YOLOv5 output. After performing trapezoidal correction, the maximally stable extremal regions (MSER) are used to detect character candidates, and characters are recognized using 3D rotated character recognition. The second method performs character candidate detection and recognition without trapezoidal correction, followed by graph matching. These methods are versatile because they do not depend on the layout of license plates, which varies among countries and regions. Two types of datasets were used: a set of images containing Japanese license plates collected by ourselves, and a set of publicly available images containing Taiwanese license plates. Two recognition rates were evaluated: the license plate character recognition rate and license plate recognition rate in which all characters in one plate are recognized. The license plate character recognition rates using graph matching were 91.9% for the Japanese license plates and 89.3% for the Taiwanese license plates. The license plate recognition rates were 84.0% and 84.5%, respectively.

This paper presents an efficient method for license plate detection and recognition that will aid in the development of an intelligent transport system. To significantly accelerate license plate localization a simple image pre-processing method is first used without reducing detection performance compared with that obtained using original image. Line density filter approach is used to extract the license plate regions, there by significantly reducing area to be analysed for license plate localization. In license plate recognition, the characters are recognized from these detected license plates by using optical character recognition and the owner details are displayed. The aim of this paper is to serve the purpose of accurately localizing vehicle license plates from complex scenes in real time that would help motor vehicle department in various ways.

This paper presents a robust real time feature based algorithm for localization and recognition of multiple color and font style license plates. The algorithm uses digitized license plate images for robust detection and recognition. The resolution of the captured image is adjusted and the brightness and contrast are set to appropriate levels. An optimal threshold is applied to detect white regions of the enhanced image. The algorithm uses segmentation and component labeling to create candidate regions intelligently. For localization of the license plate, features of each region are extracted and analyzed by rectangularity percentage of the automobile's license plate. The use of color filter renders the algorithm more robust on license plate localization. Moreover, we use HSV color space to find the specific color regions. After localization of license plate in small sized image, the proposed algorithm uses rapid intelligent method for localization of license plate form the original image. The localized license plate image is cropped and processed by the recognition algorithm. Each character's region is identified by using segmentation algorithm based on the profile which includes character dilation and resizing for subsequent operations. In this paper, correlation optical character recognition and multi-layer perception neural networks techniques are used for recognizing the characters. The performance of the proposed algorithm is acceptable even in low-quality or bad light images.

As the difference of gray value between the numbers and letters on the license plate and the license plate background is very big. We first use region growing algorithm based on the gray value to separate each number and letter into different area. Secondly, we search for the bounding rectangles of all regions and find some rectangular sequences that meet a special condition. Thirdly, calculate the horizon bias for all rectangles according to the coordination of the up-right point in the rectangle, adjust and get the precise location of each rectangle. Forth, we get the binary image which can separate the numbers and letters on the license plates and the license plate background by the dynamic threshold algorithm. The relation of the maximum width of various license plate numbers and letters and its bounding rectangles helps to count the direction of the vertical bias, then the bias is adjusted. At last we statistic the foreground vertical histogram of the previous results, and get the result of precise vertical position and character segmentation. The experimental results show that this algorithm performs well for location of multi-national license plates.

Image processing-based vehicle recognition is one of the important research fields in ITS. The existing methods are all based on license plate recognition and car shape recognition. Their common problem is algorithm stability. And the license plates are easy to be changed. All information about vehicles should be used to recognize them reliably. A problem to be solved is to find a method to recognize vehicles besides license plate recognition and vehicle model recognition. Vehicle license plate location and character segmentation are critical steps in the license plate recognition system, and yet there are difficult problems to be solved. Kernel density estimation and Mean Shift theory

Any vehicle license plate recognition system consists of three main components which include plate detection, character segmentation, and character recognition. The main theme of this paper is the improvement and innovation in the recognition of license plate characters. The assessments and the comparison between the performances of the methods proposed in this paper and the previous methods have all been done on one database and in similar software and hardware environments. The database includes about 20000 characters which have been extracted by license plate recognition systems from images obtained in real situations, i.e. day, night, and different distances and angles. This database contains low-resolution (20 × 12) characters, and also includes images with noise, distortion and omission. In a review and evaluation of different methods that use the support vector machine (SVM) to enhance the separation process, the MLP-SVM approach has been found to be one of the best. This method has recognized all the characters of a license plate with an accuracy of 95.86% in an average time of 92.9 ms. In this paper, to improve the character recognition, two methods based on combining probabilistic classifiers with the SVM have been proposed, and the outcome is the achievement of 96.7% accuracy and an average time of 57.4 ms.

License plate localization (LPL) and character segmentation (CS) play key roles in the license plate (LP) recognition system. In this paper, we dedicate ourselves to these two issues. In LPL, histogram equalization is employed to solve the low-contrast and dynamic-range problems; the texture properties, e.g., aspect ratio, and color similarity are used to locate the LP; and the Hough transform is adopted to correct the rotation problem. In CS, the hybrid binarization technique is proposed to effectively segment the characters in the dirt LP. The feedback self-learning procedure is also employed to adjust the parameters in the system. As documented in the experiments, good localization and segmentation results are achieved with the proposed algorithms.

Traditional license plate recognition algorithms mainly employ edge detection and color detection to locate the license plate region, and then segment and recognize characters. Not only the procedure is tedious, but also is greatly affected by the ambient light, which is not suitable for the complex environment. Maximum stable extremum region (MSER) has affine invariance and adaptability to light, which is suitable for license plate recognition in complex environment. In this paper, a license plate recognition algorithm based on MSER and support vector machine is proposed. It can directly extract and recognize characters without locating license plate. Firstly, preprocessing the image and extracting the MSER is utilized. Then, most of the non-character regions can be removed through the proposed support vector machine model for the extracted regions. Besides, the character regions are screened out by using the proposed specific geometric features and arrangement rules of license plate characters. Finally, recognition of the license plate character is completed. The experimental results show that compared with the commonly used license plate recognition algorithm, the proposed algorithm combing the MSER and support vector machine model is more accurate and efficient.

Automatic license plate recognition (LPR) plays an important role in numerous applications and a number of techniques have been proposed. However, most of them worked under restricted conditions, such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds. In this study, as few constraints as possible on the working environment are considered. The proposed LPR technique consists of two main modules: a license plate locating module and a license number identification module. The former characterized by fuzzy disciplines attempts to extract license plates from an input image, while the latter conceptualized in terms of neural subjects aims to identify the number present in a license plate. Experiments have been conducted for the respective modules. In the experiment on locating license plates, 1088 images taken from various scenes and under different conditions were employed. Of which, 23 images have been failed to locate the license plates present in the images; the license plate location rate of success is 97.9%. In the experiment on identifying license number, 1065 images, from which license plates have been successfully located, were used. Of which, 47 images have been failed to identify the numbers of the license plates located in the images; the identification rate of success is 95.6%. Combining the above two rates, the overall rate of success for our LPR algorithm is 93.7%.

License plate segmentation is a key technology in the process of license plate location and recognition. How to realize automatic segmentation of license plate image under complex illumination conditions has been a hot issue in intelligent transportation system (ITS). This paper deals with license plate image segmentation under a variety of lighting conditions. Based on the adaptive segmentation of license plate images by the Pulse Coupled Neural Network (PCNN), the relationship between the license plate image contrast and the PCNN iteration entropy is analyzed. An adaptive segmentation algorithm for license plate image using Deep Neural Network (DNN) to select the optimal result is proposed, and the selected segmentation image is filtered by the connected domain, which lays a foundation for subsequent license plate location, character segmentation and recognition. Simulation experiments show that the proposed algorithm performs better license plate segmentation and optimal selection for license plate images under various lighting conditions.