Thesis Open Access
ERDEY SYOUM
<?xml version='1.0' encoding='UTF-8'?> <record xmlns="http://www.loc.gov/MARC21/slim"> <leader>00000nam##2200000uu#4500</leader> <datafield tag="041" ind1=" " ind2=" "> <subfield code="a">eng</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">publication</subfield> <subfield code="b">thesis</subfield> </datafield> <datafield tag="653" ind1=" " ind2=" "> <subfield code="a">Automatic Vehicle Identification Convolutional Neural Network Deep Learning Object Detection Optical Character Recognition</subfield> </datafield> <datafield tag="856" ind1="4" ind2=" "> <subfield code="s">1892534</subfield> <subfield code="u">https://nadre.ethernet.edu.et/record/4493/files/ETHIOPIAN CAR LICENSE PLATERECOGNITION USING DEEP LEARNING.pdf</subfield> <subfield code="z">md5:1f8b34cd7c017dab99cd1125972c8440</subfield> </datafield> <datafield tag="520" ind1=" " ind2=" "> <subfield code="a"><p>The focus of this research is to develop a system that assist humans in reading car<br> license plate. Such a study is important as the number of traffic on roads becomes<br> increasing constantly, the manual process in car license plate recognition becomes a<br> serious problem for traffic management system which not only detect and track a<br> vehicle but also identify it. Initially a dataset that contains 930 car images was prepared<br> for model comparison purpose. Two object detection algorithms (Faster R-CNN and<br> SSD) were trained and tested on the same dataset using the same model to select the<br> best candidate. The metrics for the comparison were accuracy, average prediction time,<br> and total training time taken. It was found that Faster R-CNN gives high accuracy, short<br> average prediction time, and short total training time. After that additional car and<br> cropped license plate images were added to the prepared dataset and based on this, two<br> object detection networks were trained using Faster R-CNN one for plate detection and<br> another for character recognition on the detected plate. The proposed approach has been<br> tested on test set and later collected images of national license plate of Ethiopia. Both<br> the trained models were achieved a high accuracy which is 99 and 98.89 mAP over 0.5<br> IoU for plate detection and character recognition respectively and takes on average 12s<br> to complete the recognition of a license plate. The study could be further investigated<br> on other countries.</p></subfield> </datafield> <controlfield tag="001">4493</controlfield> <datafield tag="100" ind1=" " ind2=" "> <subfield code="a">ERDEY SYOUM</subfield> <subfield code="u">ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</subfield> </datafield> <datafield tag="245" ind1=" " ind2=" "> <subfield code="a">ETHIOPIAN CAR LICENSE PLATE RECOGNITION USING DEEP LEARNING</subfield> </datafield> <controlfield tag="005">20200131092022.0</controlfield> <datafield tag="650" ind1="1" ind2="7"> <subfield code="a">cc-by</subfield> <subfield code="2">opendefinition.org</subfield> </datafield> <datafield tag="260" ind1=" " ind2=" "> <subfield code="c">2020-01-16</subfield> </datafield> <datafield tag="542" ind1=" " ind2=" "> <subfield code="l">open</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">user-aastu</subfield> </datafield> <datafield tag="980" ind1=" " ind2=" "> <subfield code="a">user-nadre</subfield> </datafield> <datafield tag="773" ind1=" " ind2=" "> <subfield code="a">10.20372/nadre/4492</subfield> <subfield code="i">isVersionOf</subfield> <subfield code="n">doi</subfield> </datafield> <datafield tag="502" ind1=" " ind2=" "> <subfield code="c">ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</subfield> </datafield> <datafield tag="024" ind1=" " ind2=" "> <subfield code="a">10.20372/nadre/4493</subfield> <subfield code="2">doi</subfield> </datafield> <datafield tag="540" ind1=" " ind2=" "> <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield> <subfield code="a">Creative Commons Attribution</subfield> </datafield> <datafield tag="700" ind1=" " ind2=" "> <subfield code="a">Sreenivasa Rao.vuda (PhD)</subfield> <subfield code="u">ADDIS ABABA SCIENCE AND TECHNOLOGY UNIVERSITY</subfield> <subfield code="4">ths</subfield> </datafield> </record>
All versions | This version | |
---|---|---|
Views | 202 | 202 |
Downloads | 268 | 268 |
Data volume | 507.2 MB | 507.2 MB |
Unique views | 113 | 113 |
Unique downloads | 202 | 202 |