Organizations: Department of Electrical and Electronic Engineering, Islamic University of Technology, Gazipur, Bangladesh · Department of Mechanical Engineering, Bangladesh University Of Engineering And Technology, Dhaka, Bangladesh
An Automatic License Plate Recognition (ALPR) system constitutes a crucial element in an intelligent traffic management system. However, the detection of Bangla license plates remains challenging because of the complicated character scheme and uneven layouts. This paper presents a robust Bangla License Plate Recognition system that integrates a deep learning-based object detection model for license plate localization with Optical Character Recognition for text extraction. Multiple object detection architectures, including U-Net and several YOLO (You Only Look Once) variants, are compared for license plate localization. This study proposes a novel two-stage adaptive training strategy built upon the YOLOv8 architecture to improve localization performance. The proposed approach outperforms the established models, achieving an accuracy of 97.83% and an Intersection over Union (IoU) of 91.3%. The text recognition problem is phrased as a sequence generation problem with a VisionEncoderDecoder architecture, with a combination of encoder-decoders evaluated. It was demonstrated that the ViT + BanglaBERT model gives better results at the character level, with a Character Error Rate of 0.1323 and Word Error Rate of 0.1068. The proposed system also shows a consistent performance when tested on an external dataset that has been curated for this study purpose. The dataset offers completely different environment and lighting conditions compared to the training sample, indicating the robustness of the proposed framework. Overall, our proposed system provides a robust and reliable solution for Bangla license plate recognition and performs effectively across diverse real-world scenarios, including variations in lighting, noise, and plate styles. These strengths make it well suited for deployment in intelligent transportation applications such as automated law enforcement and access control.
Figures & tables
Fig. 1 : BRTA Standard Vehicle Registration Plate
Fig. 2 : Images for License Plate Detection
Fig. 3 : Images for Text Extraction
Fig. 4 : Images for External Validation
Fig. 5 : Proposed Algorithm for Localization Model
Hyperparameter
Value
Decoder Mode ( is_decoder )
True
Add Cross Attention
True
Encoder Dropout Rate
0.3
Decoder Dropout Rate
0.3
Attention Probabilities Dropout
0.3
Max Sequence Length
20
TABLE I : Model Configuration and Hyperparameters
Model
Accuracy(%)
Precision(%)
Recall(%)
F1 Score(%)
IoU(%)
U-net
91.43
93.19
89.71
91.41
82.1
YOLOv5m
90.97
99.89
87.03
93.06
83.9
YOLOv7m
67.15
95.28
54.59
69.42
63.5
YOLOv8m
97.11
99.93
95.68
97.79
89.7
YOLOv8m + Multi Stage Learning
97.83
99.44
96.31
98.37
91.3
YOLOv9m
95.67
99.44
95.20
97.24
88.8
TABLE II : Evaluation Metrics of Localization Models
Fig. 6 : License plate detection
Model
Encoder
Decoder
CER ↓
WER ↓
ViT + B-BERT
ViT-Base
BanglaBERT
0.1323
0.1068
TrOCR
TrOCR-Base
TrOCR-Base
0.1363
0.1583
ViT + mBART
ViT-Base
mBART-50
0.4438
0.0935
TABLE III : Performance Comparison of OCR Models on external dataset
Metric
Best Value
Validation Loss
0.4101
Character Error Rate (CER)
0.1323
Word Error Rate (WER)
0.1068
Levenshtein Distance
3.02
TABLE IV : Summary of Best OCR Model Performance
Fig. 7 : Comparison of Character Error Rate (CER) over training steps.
Fig. 8 : Comparison of Levenshtein Distance convergence.
Fig. 9 : Comparison of Word Error Rate (WER) across models.
Fig. 10 : OCR outputs of the model using the external dataset.
Model
Accuracy(%)
Precision(%)
Recall(%)
F1 Score(%)
IoU(%)
U-net
80.43
92.10
82.59
80.79
60.4
YOLOv5m
52.53
94.26
63.20
72.81
45.20
YOLOv7m
55.12
97.46
62.74
75.43
43.04
YOLOv8m
61.11
99.87
69.13
79.30
52.51
YOLOv8m + Multi Stage Learning
82.9
99.92
89.14
92.10
67.5
YOLOv9m
53.62
99.86
63.68
75.83
47.42
TABLE V : Performance with External Dataset
Fig. 11 : Inference on External Dataset (Green = Annotation; Red = Prediction
Accurate vehicle license plate detection is essential for applications such as intelligent transportation systems, toll collection, parking management, and law enforcement. In Bangladesh, this task presents distinct challenges due to the complexity of localized license plates and environmental factors like lighting, occlusion, motion blur, and obstructions such as dirt or mud. These challenges often render conventional methods ineffective. This paper introduces a novel hybrid approach, combining the YOLO Tiny deep learning model with the Haar-Cascade classifier, for enhanced detection and localization of Bengali license plates. A key innovation of our system is the integration of a dynamic retraining pipeline, which allows the model to adapt to evolving real-world conditions. This retraining mechanism significantly boosts performance in low-confidence scenarios by continuously improving the model's accuracy as new data is encountered. Additionally, a publicly accessible dataset of BRTA-compliant license plates, captured under diverse and challenging conditions, has been developed to support this approach. Experimental results demonstrate that our approach not only achieves superior detection accuracy and computational efficiency over conventional models but also ensures consistent performance in resource-constrained environments, particularly in Bangladesh.
Debashis Kar Suvra, Tahsina Farah Sanam
Institute of Appropriate Technology Bangladesh University of Engineering and Technology Dhaka, Bangladesh
Robust license plate recognition in unconstrained environments remains a significant challenge, particularly in underrepresented regions with limited data availability and unique visual characteristics, such as Bolivia. Recognition accuracy in real-world conditions is often degraded by illumination changes and viewpoint distortion. To address these challenges, we introduce BLPR, a deep learning-based License Plate Detection and Recognition (LPDR) framework designed for Bolivian license plates. BLPR adaptively applies geometric rectification, illumination correction, and VLM-assisted fallback based on image-condition and confidence cues. The proposed system uses a YOLO-based detector pretrained on synthetic data generated in Blender to simulate extreme perspectives and lighting conditions, and is fine-tuned on street-level data collected in La Paz, Bolivia. Detected plates are processed by a YOLO-based character recognizer, while a lightweight vision-language model (Gemma3 4B) is selectively triggered in ambiguous cases as a confidence-driven fallback mechanism. We also introduce the first publicly available Bolivian LPDR dataset for academic research, supporting evaluation under diverse viewpoint and illumination conditions. The system achieves a character-level recognition accuracy of 89.6% on real-world data, demonstrating its effectiveness for deployment in challenging urban environments.
Guillermo Auza Banegas, Diego Calvimontes Vera, Natalia Condori Peredo +2
Department of Mechatronics Engineering, Universidad Catolica Boliviana “San Pablo”, La Paz, Bolivia · School of Electronic Engineering and Computer Science, Queen Mary University of London, England, United Kingdom
This paper presents a robust Automatic Number Plate Recognition (ANPR) system tailored for Nepali license plates written in Devanagari script. In this paper, a pipelined model was used that integrates YOLO-based models for license plate and character detection, followed by a CNN classifier trained on 34 Devanagari characters. Two publicly available data sets were used that incorporate diverse lighting, fonts, and structural variations. Data augmentation and additional training on embossed plates enhanced the generalizability of the model. The system achieved a recognition accuracy of up to 93%, demonstrating strong performance under real-world conditions and providing a scalable solution for traffic management in Nepal. Code: https://github.com/Satyasakhadka/Nepali-NumberPlate-Character-Recognition
Satyasa Khadka, Sandhya Baral, Sudip Tiwari +1
Pulchowk Campus, Institute of Engineering, Lalitpur, Nepal1