Thesis Open Access

ETHIOPIAN CAR LICENSE PLATE RECOGNITION USING DEEP LEARNING

ERDEY SYOUM


JSON Export

{
  "conceptdoi": "10.20372/nadre/4492", 
  "conceptrecid": "4492", 
  "created": "2020-01-29T05:21:55.950137+00:00", 
  "doi": "10.20372/nadre/4493", 
  "files": [
    {
      "bucket": "faa04614-43e2-48b8-bbee-57f62e3d2bb2", 
      "checksum": "md5:1f8b34cd7c017dab99cd1125972c8440", 
      "key": "ETHIOPIAN CAR LICENSE PLATERECOGNITION USING DEEP LEARNING.pdf", 
      "links": {
        "self": "https://nadre.ethernet.edu.et/api/files/faa04614-43e2-48b8-bbee-57f62e3d2bb2/ETHIOPIAN%20CAR%20LICENSE%20PLATERECOGNITION%20USING%20DEEP%20LEARNING.pdf"
      }, 
      "size": 1892534, 
      "type": "pdf"
    }
  ], 
  "id": 4493, 
  "links": {
    "badge": "https://nadre.ethernet.edu.et/badge/doi/10.20372/nadre/4493.svg", 
    "bucket": "https://nadre.ethernet.edu.et/api/files/faa04614-43e2-48b8-bbee-57f62e3d2bb2", 
    "conceptbadge": "https://nadre.ethernet.edu.et/badge/doi/10.20372/nadre/4492.svg", 
    "conceptdoi": "https://doi.org/10.20372/nadre/4492", 
    "doi": "https://doi.org/10.20372/nadre/4493", 
    "html": "https://nadre.ethernet.edu.et/record/4493", 
    "latest": "https://nadre.ethernet.edu.et/api/records/4493", 
    "latest_html": "https://nadre.ethernet.edu.et/record/4493"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "aastu"
      }, 
      {
        "id": "nadre"
      }
    ], 
    "creators": [
      {
        "affiliation": "ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY", 
        "name": "ERDEY SYOUM"
      }
    ], 
    "description": "<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>", 
    "doi": "10.20372/nadre/4493", 
    "keywords": [
      "Automatic Vehicle Identification Convolutional Neural Network Deep Learning Object Detection Optical Character Recognition"
    ], 
    "language": "eng", 
    "license": {
      "id": "cc-by"
    }, 
    "publication_date": "2020-01-16", 
    "related_identifiers": [
      {
        "identifier": "10.20372/nadre/4492", 
        "relation": "isVersionOf", 
        "scheme": "doi"
      }
    ], 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4493"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "4492"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "thesis", 
      "title": "Thesis", 
      "type": "publication"
    }, 
    "thesis": {
      "supervisors": [
        {
          "affiliation": "ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY", 
          "name": "Sreenivasa Rao.vuda (PhD)"
        }
      ], 
      "university": "ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY"
    }, 
    "title": "ETHIOPIAN CAR LICENSE PLATE RECOGNITION USING DEEP LEARNING"
  }, 
  "owners": [
    3
  ], 
  "revision": 2, 
  "stats": {
    "downloads": 26.0, 
    "unique_downloads": 15.0, 
    "unique_views": 36.0, 
    "version_downloads": 26.0, 
    "version_unique_downloads": 15.0, 
    "version_unique_views": 36.0, 
    "version_views": 105.0, 
    "version_volume": 49205884.0, 
    "views": 105.0, 
    "volume": 49205884.0
  }, 
  "updated": "2020-01-31T09:20:22.888657+00:00"
}
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