An Autoencoder with Convolutional Neural Network for Surface Defect Detection on Cast Components

Chamberland, Olivia; Reckzin, Mark; Hashim, Hashim A.

doi:10.1007/s11668-023-01695-8

Cited by 1 publication

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bionda et al [26] proposed a deep autoencoder for anomaly detection based on Complex Wavelet Structural Similarity (CW-SSIM). Chamberland et al [27] proposed a method to detect defects on cast components using a convolution neural network (CNN) autoencoder. While effective at detecting and localizing most defects, these methods face challenges when dealing with defects that closely resemble the normal background and do not achieve a noise-free reconstruction of the normal background.…”

Section: Introductionmentioning

confidence: 99%

Autoencoder-Based Unsupervised Surface Defect Detection Using Two-Stage Training

Getachew Shiferaw,

Yao

2024

J. Imaging

View full text Add to dashboard Cite

Accurately detecting defects while reconstructing a high-quality normal background in surface defect detection using unsupervised methods remains a significant challenge. This study proposes an unsupervised method that effectively addresses this challenge by achieving both accurate defect detection and a high-quality normal background reconstruction without noise. We propose an adaptive weighted structural similarity (AW-SSIM) loss for focused feature learning. AW-SSIM improves structural similarity (SSIM) loss by assigning different weights to its sub-functions of luminance, contrast, and structure based on their relative importance for a specific training sample. Moreover, it dynamically adjusts the Gaussian window’s standard deviation (σ) during loss calculation to balance noise reduction and detail preservation. An artificial defect generation algorithm (ADGA) is proposed to generate an artificial defect closely resembling real ones. We use a two-stage training strategy. In the first stage, the model trains only on normal samples using AW-SSIM loss, allowing it to learn robust representations of normal features. In the second stage of training, the weights obtained from the first stage are used to train the model on both normal and artificially defective training samples. Additionally, the second stage employs a combined learned Perceptual Image Patch Similarity (LPIPS) and AW-SSIM loss. The combined loss helps the model in achieving high-quality normal background reconstruction while maintaining accurate defect detection. Extensive experimental results demonstrate that our proposed method achieves a state-of-the-art defect detection accuracy. The proposed method achieved an average area under the receiver operating characteristic curve (AuROC) of 97.69% on six samples from the MVTec anomaly detection dataset.

show abstract

Section: Introductionmentioning

confidence: 99%