Answers are grounded in this paper and cite their sources.
This study introduces the Diverse Iranian License Plate (DILP) dataset, an open-source benchmark for detecting and recognizing Iranian license plates under various conditions. In addition to the dataset, baseline evaluations are conducted using YOLOv10 models, implementing custom and COCO labeling methods to demonstrate their effectiveness for vehicle and license plate detection under varying conditions. Results indicate that COCO labeling offers greater accuracy in differentiating between vehicles and license plates. For recognition, a convolutional neural network (CNN) with bidirectional long short-term memory (BiLSTM) layers facilitates character sequence recognition, with Connectionist Temporal Classification (CTC) loss optimizing performance across diverse lighting and environmental settings. This benchmark is intended to foster future research and development in Automatic License Plate Recognition (ALPR), offering a standardized framework for evaluating recognition methods.
No takes yet. Share an insight, caveat, or question.
Naeini et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: