Automatic Number Plate Recognition:A Detailed Survey of Relevant Algorithms

Abstract

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.

A Live-Video Automatic Number Plate Recognition (ANPR) System Using Convolutional Neural Network (CNN) with Data Labelling on an Android Smartphone

“…The first database; SSIG-SegPlate Database by Smart Surveillance Interest Group (SSIG), contains 2000 frames from nearly 101 vehicle videos. The system attains 93.53% recognition precision at 47 FPS, performing better than both the OpenALPR commercial systems and Sighthound (with corresponding recognition precision of 93.03% and 89.80%), and significantly better results than the past techniques, which attain an accuracy of 81.80% [1].…”

“…The character with the most similarities to one of the candidates in the template set is picked. The resultant image's grey level intensities are noticeably affected by changes in lighting conditions, which is why these approaches are often employed on binary pictures [1]. Khalil [10] used Template Matching and test his system on license plates in Saudi Arabia and Egypt.…”

“…Automatic Number Plate Recognition (ANPR) and its various complex algorithms are actively being researched especially alongside the rising interests in autonomous driving and intelligent transportation systems, where the need for human intervention is minimized by the system to determine vehicle identity [1]. ANPR system combines computer hardware and software algorithms in computer vision to recognize a license plate number which can then be verified against a database of registered users and confirm the identity of the vehicle owner.…”

Image Processing in Automatic License Plate Recognition Using Combined Methods

“…All we need to do is just run through the full range of t values [1,256] and pick the value that minimizes the variance within classes.…”

“…Since no standard technique exists that performs in all degradation cases for all image type, there is many proposed studies [1] related to the combination of a set of binarization techniques. However, most of other studies are focused on using one method at the time.…”