Type-Balanced Federated Learning for Visual Analog Meter Reading

2026-09-25

AI Summary

This study addresses the challenge of automatic reading for industrial analog meters caused by diverse meter types, scarce annotations, and privacy constraints. We propose a cross-site collaborative visual reading framework based on federated learning. Methodologically, we design a four-stage pipeline comprising deep segmentation, polar coordinate unwrapping, and scale counting decoding, enabling multi-client joint training without raw images leaving local domains. Furthermore, pseudo-clients are partitioned via deterministic rules to systematically evaluate data distribution heterogeneity. We also release a dedicated benchmark dataset, MeterFL, along with open-source code. Experimental results demonstrate that the proposed method achieves superior performance in both segmentation quality and end-to-end reading accuracy, providing an effective baseline for privacy-preserving industrial meter recognition.

Abstract

Analog dial meters are widely deployed in industrial applications and utility sites, where environments and meter types vary and inspection data may be sensitive. Currently, automatic meter readers must be individually developed and deployed for each environment and meter type in practice. Deep learning could handle this variability but requires diverse labeled data that are costly to collect and update. In practice, meter images are distributed across independent sites, each with limited labels, while raw images often cannot be pooled because of ownership, governance, or privacy constraints. To address these challenges, we present a federated framework for visual analog meter reading that enables multiple sites to collaboratively train a reading model without sharing their raw images. Our framework consists of a four-stage pipeline: (1) dial localization, (2) thin-structure segmentation trained federatively across clients, (3) polar unwrapping, and (4) tick-counting decoding for final reading. To enable systematic evaluation of this setting, we release MeterFL, a 1,382-image mask-annotated dataset organized into deployment-motivated pseudo-clients derived from visual attributes via deterministic rules, with dHash near-duplicate control between the segmentation train and test splits. We evaluate both segmentation quality and end-to-end reading accuracy. MeterFL is publicly available at https://github.com/weidazhaoooo/Meter-FL.

Problem

• Federated Learning
• Analog Meter Reading
• Data Privacy
• Distributed Data
• Image Segmentation

Innovation

• Federated Learning
• Analog Meter Reading
• Thin-Structure Segmentation
• Polar Unwrapping
• MeterFL Dataset