Thesis Open Access

ETHIOPIAN CAR LICENSE PLATE RECOGNITION USING DEEP LEARNING

ERDEY SYOUM


Citation Style Language JSON Export

{
  "DOI": "10.20372/nadre/4493", 
  "abstract": "<p>The focus of this research is to develop a system that assist humans in reading car<br>\nlicense plate. Such a study is important as the number of traffic on roads becomes<br>\nincreasing constantly, the manual process in car license plate recognition becomes a<br>\nserious problem for traffic management system which not only detect and track a<br>\nvehicle but also identify it. Initially a dataset that contains 930 car images was prepared<br>\nfor model comparison purpose. Two object detection algorithms (Faster R-CNN and<br>\nSSD) were trained and tested on the same dataset using the same model to select the<br>\nbest candidate. The metrics for the comparison were accuracy, average prediction time,<br>\nand total training time taken. It was found that Faster R-CNN gives high accuracy, short<br>\naverage prediction time, and short total training time. After that additional car and<br>\ncropped license plate images were added to the prepared dataset and based on this, two<br>\nobject detection networks were trained using Faster R-CNN one for plate detection and<br>\nanother for character recognition on the detected plate. The proposed approach has been<br>\ntested on test set and later collected images of national license plate of Ethiopia. Both<br>\nthe trained models were achieved a high accuracy which is 99 and 98.89 mAP over 0.5<br>\nIoU for plate detection and character recognition respectively and takes on average 12s<br>\nto complete the recognition of a license plate. The study could be further investigated<br>\non other countries.</p>", 
  "author": [
    {
      "family": "ERDEY SYOUM"
    }
  ], 
  "id": "4493", 
  "issued": {
    "date-parts": [
      [
        2020, 
        1, 
        16
      ]
    ]
  }, 
  "language": "eng", 
  "title": "ETHIOPIAN CAR LICENSE PLATE RECOGNITION USING DEEP LEARNING", 
  "type": "thesis"
}
105
26
views
downloads
All versions This version
Views 105105
Downloads 2626
Data volume 49.2 MB49.2 MB
Unique views 3636
Unique downloads 1515

Share

Cite as