A Cascaded Zoom-In Network for Patterned Fabric Defect Detection

TL;DR

This paper introduces a two-step Cascaded Zoom-In Network (CZI-Net) for patterned fabric defect detection that leverages feature extraction methods like A-HOG and SIFT, enabling fast and accurate detection with reduced computational costs.

Contribution

The paper proposes a novel two-step CZI-Net that combines traditional feature descriptors with new coding methods, improving detection speed and accuracy in fabric defect detection.

Findings

High detection accuracy on real-world datasets

Reduced computational cost compared to traditional CNNs

Effective in identifying defect-free fabrics quickly

Abstract

Nowadays, Deep Convolutional Neural Networks (DCNNs) are widely used in fabric defect detection, which come with the cost of expensive training and complex model parameters. With the observation that most fabrics are defect free in practice, a two-step Cascaded Zoom-In Network (CZI-Net) is proposed for patterned fabric defect detection. In the CZI-Net, the Aggregated HOG (A-HOG) and SIFT features are used to instead of simple convolution filters for feature extraction. Moreover, in order to extract more distinctive features, the feature representation layer and full connection layer are included in the CZI-Net. In practice, Most defect-free fabrics only involve in the first step of our method and avoid a costive computation in the second step, which makes very fast fabric detection. More importantly, we propose the Locality-constrained Reconstruction Error (LCRE) in the first step and Restrictive Locality-constrained Coding (RLC), Bag-of-Indexes (BoI) methods in the second step. We also analyse the connections between different coding methods and conclude that the index of visual words plays an essential role in the coding methods. In conclusion, experiments based on real-world datasets are implemented and demonstrate that our proposed method is not only computationally simple but also with high detection accuracy.