Research on License Plate Recognition Using Digital Image Processing

Saraswathi, S.; Subban, Ravi; Shanmugasundari, T.; Manogari, S.

doi:10.1109/iccic.2017.8524147

Cited by 6 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vehicle LPR is widely employed in transportation [ 24 , 25 , 26 ] and comprises three steps: vehicle license plate localization, character segmentation, and character recognition [ 27 , 28 , 29 ]. However, several factors that are related to the images of license plates directly influence the difficulty of object detection and character recognition [ 30 , 31 ].…”

Section: Literature Reviewmentioning

confidence: 99%

Automated Sensing System for Real-Time Recognition of Trucks in River Dredging Areas Using Computer Vision and Convolutional Deep Learning

Chou

Liu

2021

Sensors

View full text Add to dashboard Cite

Sand theft or illegal mining in river dredging areas has been a problem in recent decades. For this reason, increasing the use of artificial intelligence in dredging areas, building automated monitoring systems, and reducing human involvement can effectively deter crime and lighten the workload of security guards. In this investigation, a smart dredging construction site system was developed using automated techniques that were arranged to be suitable to various areas. The aim in the initial period of the smart dredging construction was to automate the audit work at the control point, which manages trucks in river dredging areas. Images of dump trucks entering the control point were captured using monitoring equipment in the construction area. The obtained images and the deep learning technique, YOLOv3, were used to detect the positions of the vehicle license plates. Framed images of the vehicle license plates were captured and were used as input in an image classification model, C-CNN-L3, to identify the number of characters on the license plate. Based on the classification results, the images of the vehicle license plates were transmitted to a text recognition model, R-CNN-L3, that corresponded to the characters of the license plate. Finally, the models of each stage were integrated into a real-time truck license plate recognition (TLPR) system; the single character recognition rate was 97.59%, the overall recognition rate was 93.73%, and the speed was 0.3271 s/image. The TLPR system reduces the labor force and time spent to identify the license plates, effectively reducing the probability of crime and increasing the transparency, automation, and efficiency of the frontline personnel’s work. The TLPR is the first step toward an automated operation to manage trucks at the control point. The subsequent and ongoing development of system functions can advance dredging operations toward the goal of being a smart construction site. By intending to facilitate an intelligent and highly efficient management system of dredging-related departments by providing a vehicle LPR system, this paper forms a contribution to the current body of knowledge in the sense that it presents an objective approach for the TLPR system.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Automated Sensing System for Real-Time Recognition of Trucks in River Dredging Areas Using Computer Vision and Convolutional Deep Learning

Chou

Liu

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…There should ideally be particular and uniquely trained systems for different countries in order to work accurately and efficiently for that country. [2] For example, Chinese number plates have alphanumeric characters along with some Chinese symbol unlike an Indian license plate which is just formed by mix of alphanumeric characters. [7] Also, it is evident that different countries have different colour scheme for the number plate of the vehicles for their country.…”

Section: Open Accessmentioning

confidence: 99%

“…As theoretically there are many inputs to this kind of system, there are number of papers and citations that talk about how we can detect plate and recognize its characters in various possible as well as hypothetical methods to implement the same. [2] There can be many machine learning algorithms that can be brought into picture as well as there can be use of neural networks to recognize the results. The project thus built taking all aspects into consideration has its sole purpose to work on the accuracy of the detection such that the system can actually be deployed and brought into use.…”

Section: Purposementioning

confidence: 99%

“…If a similar thing can be obtained by a computer, we can possibly make it retain some wonderful human feature which is a natural one for us but might sound difficult for a machine. [2] We can find and identify objects as well a name them just by seeing it, a machine needs to be programmed or taught to get that capability, this could be termed as object recognition [6] in plain terms which is a computer vision technique working on the images using some machine learning and deep learning algorithms. This ability is renowned for its massive applications in driverless cars identifying signboards or other objects which is a symbol for these for when to apply breaks and when to drive.…”

Section: Survey Of Technologiesmentioning

confidence: 99%

“…A model will be trained to recognize characters further. [2] Then the segmented characters will be sent to the model to individually give the result of the number plate.…”

Section: Figure 7 Flowchart For Steps Involvedmentioning

confidence: 99%

See 2 more Smart Citations

License Plate Recognition for Traffic Management

Singh

2021

J. Manage. Serv. Sci.

View full text Add to dashboard Cite

The objective of this report is to present an overview of the project, license plate recognition. This system is to basically detect a vehicle using the information of the license plate in order to use the information at various valid sites. This tool can work as a part of other big projects in the industry for security purposes as well as for analysis purposes. There is a detailed insight of the project in several different chapters throughout the report. This project is based on detection and recognition algorithms; using several libraries of python to work on images and videos and thereafter using the processed image to further train and test a model using machine learning algorithm such that the recognition is done with higher accuracy. The beginning outlines the introduction to the topic and its importance in the real world by highlighting some other applications using similar approach. Later it highlights the technology and skills in use in order to completely deploy the idea. Further there is an explanation to the feasibility study as well as the requirement specification while system design revolves around the basic designing of several modules which would integrate to work as the whole system and test cases. Implementation and testing approach is being discussed and thereby light has been thrown on the results and conclusion thus bringing attention to system’s limitation and its future scope.

show abstract