License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images
License Plate Character Recognition (LPCR) is a technology for reading vehicle registration plates using optical character recognition from images and videos, and it has a long history due to its usefulness. While LPCR has been significantly improved with the advance of deep learning, training deep...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/10/8/2780 |
| _version_ | 1827718562553266176 |
|---|---|
| author | Byung-Gil Han Jong Taek Lee Kil-Taek Lim Doo-Hyun Choi |
| author_facet | Byung-Gil Han Jong Taek Lee Kil-Taek Lim Doo-Hyun Choi |
| author_sort | Byung-Gil Han |
| collection | DOAJ |
| description | License Plate Character Recognition (LPCR) is a technology for reading vehicle registration plates using optical character recognition from images and videos, and it has a long history due to its usefulness. While LPCR has been significantly improved with the advance of deep learning, training deep networks for LPCR module requires a large number of license plate (LP) images and their annotations. Unlike other public datasets of vehicle information, each LP has a unique combination of characters and numbers depending on the country or the region. Therefore, collecting a sufficient number of LP images is extremely difficult for normal research. In this paper, we propose LP-GAN, an LP image generation method, by applying an ensemble of generative adversarial networks (GAN), and we also propose a modified lightweight YOLOv2 model for an efficient end-to-end LPCR module. With only 159 real LP images available online, thousands of synthetic LP images were generated by using LP-GAN. The generated images not only looked similar to real ones, but they were also shown to be effective for training the LPCR module. As a result of performance tests with 22,117 real LP images, the LPCR module trained with only the generated synthetic dataset achieved 98.72% overall accuracy, which is comparable to that of training with a real LP image dataset. In addition, we improved the processing speed of LPCR about 1.7 times faster than that of the original YOLOv2 model by using the proposed lightweight model. |
| first_indexed | 2024-03-10T20:25:29Z |
| format | Article |
| id | doaj.art-c237a86ff9b44c9aa3a27dde7c9a0d01 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T20:25:29Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c237a86ff9b44c9aa3a27dde7c9a0d012023-11-19T21:51:54ZengMDPI AGApplied Sciences2076-34172020-04-01108278010.3390/app10082780License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real ImagesByung-Gil Han0Jong Taek Lee1Kil-Taek Lim2Doo-Hyun Choi3Electronics and Telecommunications Research Institute, Daegu 42994, KoreaElectronics and Telecommunications Research Institute, Daegu 42994, KoreaElectronics and Telecommunications Research Institute, Daegu 42994, KoreaSchool of Electronics Engineering, Kyungpook National University, Daegu 41566, KoreaLicense Plate Character Recognition (LPCR) is a technology for reading vehicle registration plates using optical character recognition from images and videos, and it has a long history due to its usefulness. While LPCR has been significantly improved with the advance of deep learning, training deep networks for LPCR module requires a large number of license plate (LP) images and their annotations. Unlike other public datasets of vehicle information, each LP has a unique combination of characters and numbers depending on the country or the region. Therefore, collecting a sufficient number of LP images is extremely difficult for normal research. In this paper, we propose LP-GAN, an LP image generation method, by applying an ensemble of generative adversarial networks (GAN), and we also propose a modified lightweight YOLOv2 model for an efficient end-to-end LPCR module. With only 159 real LP images available online, thousands of synthetic LP images were generated by using LP-GAN. The generated images not only looked similar to real ones, but they were also shown to be effective for training the LPCR module. As a result of performance tests with 22,117 real LP images, the LPCR module trained with only the generated synthetic dataset achieved 98.72% overall accuracy, which is comparable to that of training with a real LP image dataset. In addition, we improved the processing speed of LPCR about 1.7 times faster than that of the original YOLOv2 model by using the proposed lightweight model.https://www.mdpi.com/2076-3417/10/8/2780license plate image generationensemble datasegmentation-freeend-to-end recognitionGANALPR |
| spellingShingle | Byung-Gil Han Jong Taek Lee Kil-Taek Lim Doo-Hyun Choi License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images Applied Sciences license plate image generation ensemble data segmentation-free end-to-end recognition GAN ALPR |
| title | License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images |
| title_full | License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images |
| title_fullStr | License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images |
| title_full_unstemmed | License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images |
| title_short | License Plate Image Generation using Generative Adversarial Networks for End-To-End License Plate Character Recognition from a Small Set of Real Images |
| title_sort | license plate image generation using generative adversarial networks for end to end license plate character recognition from a small set of real images |
| topic | license plate image generation ensemble data segmentation-free end-to-end recognition GAN ALPR |
| url | https://www.mdpi.com/2076-3417/10/8/2780 |
| work_keys_str_mv | AT byunggilhan licenseplateimagegenerationusinggenerativeadversarialnetworksforendtoendlicenseplatecharacterrecognitionfromasmallsetofrealimages AT jongtaeklee licenseplateimagegenerationusinggenerativeadversarialnetworksforendtoendlicenseplatecharacterrecognitionfromasmallsetofrealimages AT kiltaeklim licenseplateimagegenerationusinggenerativeadversarialnetworksforendtoendlicenseplatecharacterrecognitionfromasmallsetofrealimages AT doohyunchoi licenseplateimagegenerationusinggenerativeadversarialnetworksforendtoendlicenseplatecharacterrecognitionfromasmallsetofrealimages |