Authors :
Krishna Kumar Sahu; Sudhanshu Shekhar Dadsena; Komal Yadav
Volume/Issue :
Volume 10 - 2025, Issue 6 - June
Google Scholar :
https://tinyurl.com/yu3rwmf9
DOI :
https://doi.org/10.38124/ijisrt/25jun1226
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
License Plate Recognition (LPR) systems are vital components of modern intelligent transportation systems. Their
performance heavily depends on the availability of high-quality datasets and reliable benchmarking techniques. This paper
provides a comparative analysis of widely used LPR datasets and benchmarks, highlighting their unique characteristics, use
cases, and limitations. The study aims to guide researchers in selecting appropriate datasets for training and evaluating LPR
models.
Keywords :
License PlateRecognition, Dataset, Benchmark, Intelligent Transportation, OCR, Deep Learning.
References :
- R. S. Laroca et al., "A Robust Real-Time Automatic License Plate Recognition Based on the YOLODetector," 2019.
- X. Xu et al., "Towards End-to-End Car License Plates Detection and Recognition with Deep NeuralNetworks," 2018.
- S.-L. Chen et al., "Application-Oriented License Plate Recognition," 2012.
- T. Younes et al., "Synthetic Data for License Plate Recognition," arXiv, 2019.
- Caltech Cars Dataset, http://www.vision.caltech.edu/Image_Datasets/CaltechCars/
License Plate Recognition (LPR) systems are vital components of modern intelligent transportation systems. Their
performance heavily depends on the availability of high-quality datasets and reliable benchmarking techniques. This paper
provides a comparative analysis of widely used LPR datasets and benchmarks, highlighting their unique characteristics, use
cases, and limitations. The study aims to guide researchers in selecting appropriate datasets for training and evaluating LPR
models.
Keywords :
License PlateRecognition, Dataset, Benchmark, Intelligent Transportation, OCR, Deep Learning.
