Automatic license plate recognition (ALPR) is the extraction of vehicle license plate information from an image or a sequence of images. The extracted information can be used with or without a database in many applications, such as electronic payment systems (toll payment, parking fee payment), and freeway and arterial monitoring systems for traffic surveillance. The ALPR uses either a color, black and white, or infrared camera to take images. The quality of the acquired images is a major factor in the success of the ALPR. ALPR as a real-life application has to quickly and successfully process license plates under different environmental conditions, such as indoors, outdoors, day or night time. It should also be generalized to process license plates from different nations, provinces, or states. These plates usually contain different colors, are written in different languages, and use different fonts; some plates may have a single color background and others have background images. The license plates can be partially occluded by dirt, lighting, and towing accessories on the car. In this paper, we present a comprehensive review of the state-of-the-art techniques for ALPR. We categorize different ALPR techniques according to the features they used for each stage, and compare them in terms of pros, cons, recognition accuracy, and processing speed. Future forecasts of ALPR are given at the end.

https://romisatriawahono.net/lecture/rm/survey/computer%20vision/Du%20-%20Automatic%20License%20Plate%20Recognition%20-%202013.pdf

Automatic License Plate Recognition (ALPR): A State-of-the-Art Review

A vehicle’s license plate is the unique feature by which to identify each individual vehicle. As an important research area of an intelligent transportation system, the recognition of vehicle license plates has been investigated for some decades. An approach based on a visual attention model and deep learning is proposed to handle the problem of Chinese car license plate recognition for traffic videos. We first use a modified visual attention model to locate the license plate, and then the license plate is segmented into seven blocks using a projection method. Two classifiers, which combine the advantages of convolutional neural network-based feature learning and support vector machine for multichannel processing, are designed to recognize Chinese characters, numbers, and alphabet letters, respectively. Experimental results demonstrate that the presented method can achieve high recognition accuracy and works robustly even under the conditions of illumination change and noise contamination.

https://www.spiedigitallibrary.org/journals/journal-of-electronic-imaging/volume-24/issue-3/033001/Vehicle-license-plate-recognition-using-visual-attention-model-and-deep/10.1117/1.JEI.24.3.033001.pdf

Vehicle license plate recognition using visual attention model and deep learning

In this study, the authors propose a real-time multiple licence plate (LP) detection algorithm for dense traffic conditions which is of vital importance in this modern era due to increased traffic congestion. The chromatic component of YDbDr colour space is proposed to detect the blue regions, whereas a simple yet effective colour detection method is used to identify yellow LP regions. The low-intensity pixel values are eliminated as a pre-processing step to enhance the LP regions and Otsu method is used to obtain the binary image. The candidate regions are acquired by using the connected component analysis. The false candidate regions are by large rejected by inspecting the area and aspect ratio of LPs. Additionally, a two-layered false LP detection approach has been introduced to remove fake LP regions. Experimental results in practical scenarios carried out in various weather conditions show that the proposed method is highly effective in coping with various illumination conditions to accurately detect the multiple vehicle LPs with an accuracy of 93.86%. The average processing time per image is 0.33 s that can achieve real-time performance.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2016.0008

Multiple licence plate detection for Chinese vehicles in dense traffic scenarios

Technologies and services towards smart-vehicles and Intelligent-Transportation-Systems (ITS), continues to revolutionize many aspects of human life. This paper presents a detailed survey of current techniques and advancements in Automatic-Number-Plate-Recognition (ANPR) systems, with a comprehensive performance comparison of various real-time tested and simulated algorithms, including those involving computer vision (CV). ANPR technology has the ability to detect and recognize vehicles by their number-plates using recognition techniques. Even with the best algorithms, a successful ANPR system deployment may require additional hardware to maximize its accuracy. The number plate condition, non-standardized formats, complex scenes, camera quality, camera mount position, tolerance to distortion, motion-blur, contrast problems, reflections, processing and memory limitations, environmental conditions, indoor/outdoor or day/night shots, software-tools or other hardware-based constraint may undermine its performance. This inconsistency, challenging environments and other complexities make ANPR an interesting field for researchers. The Internet-of-Things is beginning to shape future of many industries and is paving new ways for ITS. ANPR can be well utilized by integrating with RFID-systems, GPS, Android platforms and other similar technologies. Deep-Learning techniques are widely utilized in CV field for better detection rates. This research aims to advance the state-of-knowledge in ITS (ANPR) built on CV algorithms; by citing relevant prior work, analyzing and presenting a survey of extraction, segmentation and recognition techniques whilst providing guidelines on future trends in this area.

https://www.mdpi.com/1424-8220/21/9/3028/pdf

Automatic Number Plate Recognition:A Detailed Survey of Relevant Algorithms.

In this paper, for finding the place of plate, a real time and fast method is expressed. In our suggested method, the image is taken to HSV color space; then, it is broken into blocks in a stable size. In frequent process, each block, in special pattern is probed. With the appearance of pattern, its neighboring blocks according to geometry of plate as a candidate are considered and increase blocks, are omitted. This operation is done for all of the uncontrolled blocks of images. First, all of the probable candidates are exploited; then, the place of plate is obtained among exploited candidates as density and geometry rate. In probing every block, only its lip pixel is studied which consists 23.44% of block area. From the features of suggestive method, we can mention the lack of use of expensive operation in image process and its low dynamic that it increases image process speed. This method is examined on the group of picture in background, distance and point of view. The rate of exploited plate reached at 99.33% and character recognition rate achieved 97%.

/pdf/a-novel-and-robust-method-for-automatic-license-plate-r5gu33lo5l.pdf

A novel and robust method for automatic license plate recognition system based on pattern recognition

License plate location (LPL) plays an important role in the license plate recognition (LPR). The license plate characters contain abundant corners which distribute intensively and regularly. Accord to the feature, a novel method to locate the license plate accurately and fast is proposed in this paper. The method is dived into three steps which are corners detection, finding out candidate license plates and locating the license plate accurately. In the course of locating license plate, three thresholds are used. First, the reasonable threshold is used to eliminate a great number of non-corner pixels to speedup corner-detections. Second, a big threshold is selected with a slid window to find out candidates. Finally, the region of candidate license plates are expanded, all the corners in it were stand out with a smaller threshold, and the license plate is located accurately using clustering analyses. Experiments have been conducted, 1200 license plate images are tested, the accuracy is 98.42% and the average consuming time is 20ms.

Zhong Qin

Papers

Method of License Plate Location Based on Corner Feature