# Image Quality Assessment for Machines: Paradigm, Large-scale Database, and Models

## TL;DR

This paper introduces a new framework and large-scale database for assessing image quality specifically for machine vision systems, highlighting the limitations of human-centric metrics and proposing a region-aware model that improves performance across various tasks.

## Contribution

The paper presents a comprehensive MIQA paradigm, a large-scale MIQD-2.5M database, and a novel RA-MIQA model, advancing machine-centric image quality assessment methods.

## Key findings

- RA-MIQA outperforms human visual system-based IQA metrics.
- Significant SRCC improvements in classification accuracy and consistency.
- HVS-based metrics are inadequate for MVS quality prediction.

## Abstract

Machine vision systems (MVS) are intrinsically vulnerable to performance degradation under adverse visual conditions. To address this, we propose a machine-centric image quality assessment (MIQA) framework that quantifies the impact of image degradations on MVS performance. We establish an MIQA paradigm encompassing the end-to-end assessment workflow. To support this, we construct a machine-centric image quality database (MIQD-2.5M), comprising 2.5 million samples that capture distinctive degradation responses in both consistency and accuracy metrics, spanning 75 vision models, 250 degradation types, and three representative vision tasks. We further propose a region-aware MIQA (RA-MIQA) model to evaluate MVS visual quality through fine-grained spatial degradation analysis. Extensive experiments benchmark the proposed RA-MIQA against seven human visual system (HVS)-based IQA metrics and five retrained classical backbones. Results demonstrate RA-MIQA's superior performance in multiple dimensions, e.g., achieving SRCC gains of 13.56% on consistency and 13.37% on accuracy for image classification, while also revealing task-specific degradation sensitivities. Critically, HVS-based metrics prove inadequate for MVS quality prediction, while even specialized MIQA models struggle with background degradations, accuracy-oriented estimation, and subtle distortions. This study can advance MVS reliability and establish foundations for machine-centric image processing and optimization. The model and code are available at: https://github.com/XiaoqiWang/MIQA.