Real-time Jordanian license plate recognition using deep learning
Countries have different specifications for License Plates (LPs), therefore developing one Automatic license plate recognition (ALPR) system that works well for all LPs types is a difficult task. This paper aims to develop an accurate ALPR for Jordanian LPs. Two-stage Convolutional Neural Networks (...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157820305152 |
| _version_ | 1811334719746342912 |
|---|---|
| author | Salah Alghyaline |
| author_facet | Salah Alghyaline |
| author_sort | Salah Alghyaline |
| collection | DOAJ |
| description | Countries have different specifications for License Plates (LPs), therefore developing one Automatic license plate recognition (ALPR) system that works well for all LPs types is a difficult task. This paper aims to develop an accurate ALPR for Jordanian LPs. Two-stage Convolutional Neural Networks (CNNs) are used in the proposed approach, the CNNs are based on the YOLO3 framework. The sizes of LPs' characters are very small compared with the frame size, therefore the YOLO3 network architecture is modified to a shallow network to detect small objects. The proposed approach uses temporal information from different frames to remove false predictions. A set of arrays data structure is used to track the vehicles’ LPs and eliminate incorrect ones. To my knowledge, the proposed approach represents the first end-to-end Jordanian ALPR that processes video stream in real-time. To my knowledge, there is no dataset for Jordanian license plates, therefore this paper proposes a new dataset called JALPR dataset. The dataset is available online and includes many real videos for moving vehicles in Jordan. Two well-known commercial software packages are used for comparisons. The experimental results in real videos from YouTube show that the proposed approach is very efficient in recognizing the Jordanian license plates and achieved 87% recognition accuracy, whereas the commercial systems have recognition accuracies that are less than 81%. |
| first_indexed | 2024-04-13T17:13:21Z |
| format | Article |
| id | doaj.art-e8934fb7c2474248bc572ade41de99a3 |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-13T17:13:21Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-e8934fb7c2474248bc572ade41de99a32022-12-22T02:38:13ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-06-0134626012609Real-time Jordanian license plate recognition using deep learningSalah Alghyaline0The World Islamic Sciences and Education University, Faculty of Information Technology, Department of Computer Science, Tabarbour, Amman, JordanCountries have different specifications for License Plates (LPs), therefore developing one Automatic license plate recognition (ALPR) system that works well for all LPs types is a difficult task. This paper aims to develop an accurate ALPR for Jordanian LPs. Two-stage Convolutional Neural Networks (CNNs) are used in the proposed approach, the CNNs are based on the YOLO3 framework. The sizes of LPs' characters are very small compared with the frame size, therefore the YOLO3 network architecture is modified to a shallow network to detect small objects. The proposed approach uses temporal information from different frames to remove false predictions. A set of arrays data structure is used to track the vehicles’ LPs and eliminate incorrect ones. To my knowledge, the proposed approach represents the first end-to-end Jordanian ALPR that processes video stream in real-time. To my knowledge, there is no dataset for Jordanian license plates, therefore this paper proposes a new dataset called JALPR dataset. The dataset is available online and includes many real videos for moving vehicles in Jordan. Two well-known commercial software packages are used for comparisons. The experimental results in real videos from YouTube show that the proposed approach is very efficient in recognizing the Jordanian license plates and achieved 87% recognition accuracy, whereas the commercial systems have recognition accuracies that are less than 81%.http://www.sciencedirect.com/science/article/pii/S1319157820305152Transportation in JordanAutomatic license plate recognitionDeep learningIntelligent transportation system (ITS) |
| spellingShingle | Salah Alghyaline Real-time Jordanian license plate recognition using deep learning Journal of King Saud University: Computer and Information Sciences Transportation in Jordan Automatic license plate recognition Deep learning Intelligent transportation system (ITS) |
| title | Real-time Jordanian license plate recognition using deep learning |
| title_full | Real-time Jordanian license plate recognition using deep learning |
| title_fullStr | Real-time Jordanian license plate recognition using deep learning |
| title_full_unstemmed | Real-time Jordanian license plate recognition using deep learning |
| title_short | Real-time Jordanian license plate recognition using deep learning |
| title_sort | real time jordanian license plate recognition using deep learning |
| topic | Transportation in Jordan Automatic license plate recognition Deep learning Intelligent transportation system (ITS) |
| url | http://www.sciencedirect.com/science/article/pii/S1319157820305152 |
| work_keys_str_mv | AT salahalghyaline realtimejordanianlicenseplaterecognitionusingdeeplearning |