Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/3998
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Rani, Sweta | - |
dc.contributor.author | Shukla, Vivek | - |
dc.contributor.author | Mohapatra, Ramesh Kumar | - |
dc.date.accessioned | 2023-04-04T08:07:36Z | - |
dc.date.available | 2023-04-04T08:07:36Z | - |
dc.date.issued | 2023-03 | - |
dc.identifier.citation | 3rd International Conference on Artificial Intelligence and Signal Processing(AISP'23), VIT-AP University, Vijayawada, India, 18-20 March 2023 | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/3998 | - |
dc.description | Copyright belongs to proceeding publisher | en_US |
dc.description.abstract | All vehicle owners must fix a High-Security Registration Plate (HSRP), under regulations of the Delhi Transport Department and Ministry of Road Transport and Highways (MoRTH), because it is more secure than old registration plates and tamper-proof. The government is taking this measure to deter theft, standardise the font and size of registration plates to make them simpler to recognize, and easily track the owner details of vehicles. In 2020, according to the National Crime Report Bureau (NCRB), data showed that over 1.3 lakh individuals lost their lives on Indian roads, earning India the dubious distinction of being the country with the highest number of fatalities in road accidents worldwide. The proposed model is implemented to detect a high-security registration plate placed on a vehicle and then recognise the character written on it. Many algorithms have been applied to recognise the characters of registration plates, but a dataset for high-security registration plates was lacking. As a result, a dataset consisting of 500 images is gathered and analysed to create this new model. In order to annotate the data, an image annotation tool is used. The model is built using a pretrained model, You Only Look Once version 5 (YOLOv5), for registration plate detection and EasyOCR for optical character recognition. The proposed model obtained an accuracy of 100% for detection and 80% for recognition as compared with the state-of-the-art methods. | en_US |
dc.subject | YOLOv5 | en_US |
dc.subject | High Security Registration Plate | en_US |
dc.subject | EasyOCR | en_US |
dc.subject | Optical Character Recognition | en_US |
dc.title | Recognition of High-Security Registration Plate for Indian Vehicles | en_US |
dc.type | Article | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2023_AISP_SRani_Recognition.pdf | 4 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.