License Plate Recognition via Attention Mechanism
Source abstract
Abstract
License plate recognition technology use widely in intelligent traffic management and control. Researchers have been committed to improving the speed and accuracy of license plate recognition for nearly 30 years. This paper is the first to propose combining the attention mechanism with YOLO-v5 and LPRnet to construct a new license plate recognition model (LPR-CBAM-Net). Through the attention mechanism CBAM (Convolutional Block Attention Module), the importance of different feature channels in license plate recognition can be re-calibrated to obtain proper attention to features. Force information to achieve the purpose of improving recognition speed and accuracy. Experimental results show that the model construction method is superior in speed and accuracy to traditional license plate recognition algorithms. The accuracy of the recognition model of the CBAM model is increased by two percentage points to 97.2%, and the size of the constructed model is only 1.8 M, which can meet the requirements of real-time execution of embedded low-power devices. The codes for training and evaluating LPR-CBAM-Net are available under the open-source MIT License at: .
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Vehicle License Plate Recognition · Handwritten Text Recognition Techniques · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (48)
Show source-provided references
1. License plate automatic recognition based on edge detection
2. Vertical-edge-based car-license-plate detection method10.1109/TVT.2012.2222454 ↗
3. Candida albicans biofilms: A developmental state associated with specific and stable gene expression patterns10.1128/EC.3.2.536-545.2004 ↗
4. Multinational vehicle license plate detection in complex backgrounds10.1016/j.jvcir.2017.03.020 ↗
5. An efficient texture descriptor for the detection of license plates from vehicle images in difficult conditions10.1109/TITS.2019.2897990 ↗
6. Automatic recognition of a car license plate using color image processing
7. License number plate recognition system using entropy-based features selection approach with SVM10.1049/iet-ipr.2017.0368 ↗
8. Unconstrained licence plate and text localization and recognition
9. A geometric framework for rectangular shape detection10.1109/TIP.2014.2343456 ↗
10. Rich feature hierarchies for accurate object detection and semantic segmentation
11. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
12. SSD: Single shot multibox detector
13. You only look once: Unified, real-time object detection
14. Yolo9000: Better, faster, stronger
15. J. Redmon and A. Farhadi, “YOLOv3: An incremental improvement,” arXiv preprint arXiv:1804.02767, 2018.
16. A. Bochkovskiy, C. Y. Wang and H. Y. M. Liao, “Yolov4: Optimal speed and accuracy of object detection,” arXiv preprint arXiv:2004.10934, 2020.
17. G. Jocher, “YOLOv5,” 2021. [Online]. Available: https://github.com/ultralytics/yolov5.
18. Research on license plate image segmentation and intelligent character recognition
19. Detection of fonts and characters with hybrid graphic-text plate numbers
20. Numeric character recognition system for Chilean license plates in semicontrolled scenarios10.2991/ijcis.2017.10.1.28 ↗
21. An adaptive car number plate image segmentation using K-means clustering
22. Bangla license plate reader for metropolitan cities of Bangladesh using template matching
23. A review on feature extraction and feature selection for handwritten character recognition
24. Deep residual learning for image recognition
25. License plate character recognition using binarization and convolutional neural networks
26. Robust model for Chinese license plate character recognition using deep learning techniques
27. Cascaded deep learning-based efficient approach for license plate detection and recognition
28. Toward end-to-end car license plate detection and recognition with deep neural networks10.1109/TITS.2018.2847291 ↗
29. A robust deep learning approach for automatic Iranian vehicle license plate detection and recognition for surveillance systems10.1109/ACCESS.2020.3035992 ↗
30. Research progress of attention mechanism in deep learning
31. Squeeze-and-excitation networks
32. Cbam: Convolutional block attention module
33. CNN-RNN based method for license plate recognition10.1049/trit.2018.1015 ↗
34. Real-time license plate detection and recognition using deep convolutional neural networks10.1016/j.jvcir.2020.102773 ↗
35. Automatic vehicle license plate recognition using optimal deep learning model10.32604/cmc.2021.014924 ↗
36. Automatic vehicle license plate recognition using optimal K-means with convolutional neural network for intelligent transportation systems10.1109/ACCESS.2020.2993008 ↗
37. Robust automatic recognition of Chinese license plates in natural scenes10.1109/ACCESS.2020.3026181 ↗
38. EfficientDet: Scalable and efficient object detection
39. LPR-Net: Recognizing Chinese license plate in complex environments10.1016/j.patrec.2018.09.026 ↗
40. Multi-object detection of Chinese license plate in complex scenes10.32604/csse.2021.014646 ↗
41. A two-stage deep neural network for multi-norm license plate detection and recognition10.1016/j.eswa.2019.06.036 ↗
42. An end-to-end textspotter with explicit alignment and attention
43. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks
44. S. Zherzdev and A. Gruzdev, “Lprnet: License plate recognition via deep neural networks,” arXiv preprint arXiv:1806.10447, 2018.
45. Gcnet: Non-local networks meet squeeze-excitation networks and beyond
46. Towards end-to-end license plate detection and recognition: A large dataset and baseline
47. Distance-IoU loss: Faster and better learning for bounding box regression10.1609/aaai.v34i07.6999 ↗
48. Focal loss for dense object detection