DialBench: Towards Accurate Reading Recognition of Pointer Meter using Large Foundation Models

TL;DR

This paper introduces DialBench, a large-scale dataset and a novel vision-language model that explicitly encodes physical relationships for accurate pointer meter reading, addressing challenges like reflections and occlusions.

Contribution

The paper presents RPM-10K, a new large-scale dial reading dataset, and MRLM, a physical relation-aware model that improves reading accuracy by encoding geometric and causal relationships.

Findings

The dataset contains 10,730 images reflecting real-world challenges.

MRLM outperforms existing methods on the benchmark.

Explicit physical relation encoding enhances reading accuracy.

Abstract

The precise reading recognition of pointer meters plays a key role in smart power systems, but existing approaches remain fragile due to challenges like reflections, occlusions, dynamic viewing angles, and overly between thin pointers and scale markings. Up to now, this area still lacks large-scale datasets to support the development of robust algorithms. To address these challenges, this paper first presents a new large-scale benchmark dataset for dial reading, termed RPM-10K, which contains 10730 meter images that fully reflect the aforementioned key challenges. Built upon the dataset, we propose a novel vision-language model for pointer meter reading recognition, termed MRLM, based on physical relation injection. Instead of exhaustively learning image-level correlations, MRLM explicitly encodes the geometric and causal relationships between the pointer and the scale, aligning perception with physical reasoning in the spirit of world-model perspectives. Through cross-attentional fusion and adaptive expert selection, the model learns to interpret dial configurations and generate precise numeric readings. Extensive experiments fully validated the effectiveness of our proposed framework on the newly proposed benchmark dataset. Both the dataset and source code will be released on https://github.com/Event-AHU/DialBench