Search papers, labs, and topics across Lattice.
This study evaluates the effectiveness of Vision-Language Models (VLMs) as a zero-shot learning alternative for Nigerian License Plate Recognition (LPR), traditionally reliant on the YOLO object detection framework and Optical Character Recognition (OCR). By testing five VLMs on a curated dataset of 88 challenging images, the research reveals that Gemini 2.0 Flash Exp and Qwen2.5-VL-7B-Instruct significantly outperform their counterparts in terms of accuracy and robustness. These findings challenge the efficacy of conventional LPR systems and highlight the potential of VLMs in real-world applications where annotated datasets are scarce.
VLMs can outperform traditional LPR systems, achieving superior accuracy and robustness in challenging environments without the need for extensive annotated datasets.
License Plate Recognition (LPR) systems are critical tools in traffic monitoring, security enforcement, and urban mobility management. Traditional LPR systems often rely on a multi-stage pipeline involving object detection using You Only Look Once (YOLO) and Optical Character Recognition (OCR), which suffer from limitations such as high resource demands, poor performance in unstructured environments, and the need for large annotated datasets. This study explores the potential of Vision-Language Models (VLMs) as a unified, zeroshot learning solution for Nigerian license plate recognition. Using a curated dataset of 88 challenging real-world images collected in Nigeria, we evaluate five selected VLMs: Gemini 2.0 Flash Exp (Google DeepMind), Qwen2.5-VL-7B-Instruct (Alibaba), GPT-4o (OpenAI), Claude 4 Sonnet (Anthropic), and Llama 3.2 Vision 90b (Meta). Results based on Character Error Rate (CER) reveal that Gemini and Qwen significantly outperform other models in both accuracy and robustness, on the challenging image scenarios. This work highlights the practical advantages of VLMs over YOLO+OCR, questions the claims by model providers, and compares the performances of the VLMs.
