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

TL;DR

This paper benchmarks the performance of multimodal Vision-Language Models against traditional OCR for billboard visibility analysis under outdoor conditions, highlighting trade-offs between accuracy and computational efficiency.

Contribution

It systematically evaluates VLMs and CNN-based OCR on weather-augmented datasets, providing insights into their suitability for real-world outdoor scene text recognition.

Findings

VLMs excel at holistic scene understanding.

Lightweight CNNs are competitive for cropped text recognition.

Weather augmentation impacts OCR and VLM performance.

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.