Human-machine knowledge hybrid augmentation method for surface defect detection based few-data learning

TL;DR

This paper introduces a human-machine hybrid augmentation approach for surface defect detection that significantly improves performance in low-data scenarios by leveraging expert knowledge to generate rich training data.

Contribution

It proposes a novel hybrid augmentation method combining expert knowledge with machine learning to enhance defect detection with minimal data in industrial settings.

Findings

Achieved up to 82.81% F1-score with only 15 training images.

Outperformed traditional augmentation by 18.22% in F1-score.

Validated on magnetic tile dataset demonstrating effectiveness in few-data conditions.

Abstract

Visual-based defect detection is a crucial but challenging task in industrial quality control. Most mainstream methods rely on large amounts of existing or related domain data as auxiliary information. However, in actual industrial production, there are often multi-batch, low-volume manufacturing scenarios with rapidly changing task demands, making it difficult to obtain sufficient and diverse defect data. This paper proposes a parallel solution that uses a human-machine knowledge hybrid augmentation method to help the model extract unknown important features. Specifically, by incorporating experts' knowledge of abnormality to create data with rich features, positions, sizes, and backgrounds, we can quickly accumulate an amount of data from scratch and provide it to the model as prior knowledge for few-data learning. The proposed method was evaluated on the magnetic tile dataset and achieved F1-scores of 60.73%, 70.82%, 77.09%, and 82.81% when using 2, 5, 10, and 15 training images, respectively. Compared to the traditional augmentation method's F1-score of 64.59%, the proposed method achieved an 18.22% increase in the best result, demonstrating its feasibility and effectiveness in few-data industrial defect detection.