Seeing the Signs: A Survey of Edge-Deployable OCR Models for Billboard Visibility Analysis

2025-07-15

AI Summary

To address the challenge of verifying text readability on outdoor billboards under complex scenes, diverse fonts, and adverse weather conditions, this paper systematically evaluates the suitability of lightweight OCR and vision-language models (VLMs) for edge deployment. We conduct the first comparative benchmark of Qwen2.5-VL-3B, InternVL3, SmolVLM2, and the compact CNN-based PaddleOCRv4 on weather-distorted real-world datasets (ICDAR 2015/SVT). Results show that while VLMs offer superior scene understanding, the lightweight CNN achieves comparable recognition accuracy on cropped text regions, with 3–8× faster inference speed and over 60% lower GPU memory consumption—making it markedly more suitable for resource-constrained edge devices. We propose an efficient edge-oriented paradigm tailored for advertising visibility analysis and publicly release our weather-augmented dataset, evaluation framework, and implementation code.

Technology Category

• Computer Vision: Language and Vision
• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Outdoor advertisements remain a critical medium for modern marketing, yet accurately verifying billboard text visibility under real-world conditions is still challenging. Traditional Optical Character Recognition (OCR) pipelines excel at cropped text recognition but often struggle with complex outdoor scenes, varying fonts, and weather-induced visual noise. Recently, multimodal Vision-Language Models (VLMs) have emerged as promising alternatives, offering end-to-end scene understanding with no explicit detection step. This work systematically benchmarks representative VLMs - including Qwen 2.5 VL 3B, InternVL3, and SmolVLM2 - against a compact CNN-based OCR baseline (PaddleOCRv4) across two public datasets (ICDAR 2015 and SVT), augmented with synthetic weather distortions to simulate realistic degradation. Our results reveal that while selected VLMs excel at holistic scene reasoning, lightweight CNN pipelines still achieve competitive accuracy for cropped text at a fraction of the computational cost-an important consideration for edge deployment. To foster future research, we release our weather-augmented benchmark and evaluation code publicly.

Problem

• Assessing billboard text visibility in real-world outdoor conditions
• Comparing OCR models for complex scenes and weather distortions
• Evaluating edge-deployable OCR solutions for computational efficiency

Innovation

• Benchmarking multimodal VLMs for OCR tasks
• Comparing VLMs with lightweight CNN pipelines
• Augmenting datasets with synthetic weather distortions