EdgeSpotter: Multi-Scale Dense Text Spotting for Industrial Panel Monitoring

TL;DR

EdgeSpotter introduces a multi-scale dense text spotting method utilizing a novel Transformer and shape encoding to improve accuracy and robustness in industrial panel monitoring, validated on a new benchmark dataset.

Contribution

The paper presents a novel multi-scale dense text spotter with a Transformer-based interdependency learning and shape encoding, addressing multi-scale and dense text challenges in industrial monitoring.

Findings

Superior performance on the IPM benchmark dataset.

Effective handling of multi-scale and dense text regions.

Practical validation on an edge AI vision system.

Abstract

Text spotting for industrial panels is a key task for intelligent monitoring. However, achieving efficient and accurate text spotting for complex industrial panels remains challenging due to issues such as cross-scale localization and ambiguous boundaries in dense text regions. Moreover, most existing methods primarily focus on representing a single text shape, neglecting a comprehensive exploration of multi-scale feature information across different texts. To address these issues, this work proposes a novel multi-scale dense text spotter for edge AI-based vision system (EdgeSpotter) to achieve accurate and robust industrial panel monitoring. Specifically, a novel Transformer with efficient mixer is developed to learn the interdependencies among multi-level features, integrating multi-layer spatial and semantic cues. In addition, a new feature sampling with catmull-rom splines is designed, which explicitly encodes the shape, position, and semantic information of text, thereby alleviating missed detections and reducing recognition errors caused by multi-scale or dense text regions. Furthermore, a new benchmark dataset for industrial panel monitoring (IPM) is constructed. Extensive qualitative and quantitative evaluations on this challenging benchmark dataset validate the superior performance of the proposed method in different challenging panel monitoring tasks. Finally, practical tests based on the self-designed edge AI-based vision system demonstrate the practicality of the method. The code and demo will be available at https://github.com/vision4robotics/EdgeSpotter.