Recognition of Defective Mineral Wool Using Pruned ResNet Models

TL;DR

This paper presents a lightweight, pruned ResNet-based visual inspection system that accurately detects defective mineral wool from X-ray images, improving defect recognition rates over current methods.

Contribution

It introduces a pruned ResNet model tailored for mineral wool defect detection, achieving high accuracy with reduced model size for real-time industrial application.

Findings

Over 98% detection accuracy

20% improvement in defective product recognition

Effective use of pruning and data augmentation techniques

Abstract

Mineral wool production is a non-linear process that makes it hard to control the final quality. Therefore, having a non-destructive method to analyze the product quality and recognize defective products is critical. For this purpose, we developed a visual quality control system for mineral wool. X-ray images of wool specimens were collected to create a training set of defective and non-defective samples. Afterward, we developed several recognition models based on the ResNet architecture to find the most efficient model. In order to have a light-weight and fast inference model for real-life applicability, two structural pruning methods are applied to the classifiers. Considering the low quantity of the dataset, cross-validation and augmentation methods are used during the training. As a result, we obtained a model with more than 98% accuracy, which in comparison to the current procedure used at the company, it can recognize 20% more defective products.