Improving the Anomaly Detection Performance of a Geometric Transform-based Convolutional Network

Using deep learning (DL) technology, neural networks have achieved great success in various fields of computer vision. Among them, anomaly detection is a promising application of image defect analysis. The purpose of the detector is to find the out-of-distribution when predicting the probability of...

Full description

Saved in:
Bibliographic Details
Published in:International journal of control, automation, and systems automation, and systems, 2023-09, Vol.21 (9), p.3105-3115
Main Authors: Kim, Hyun-Soo, Kang, Dong-Joong
Format: Article
Language:English
Subjects:
Anomalies
Computer vision
Control
Defects
Engineering
Geometric transformation
Industrial applications
Inspection
Machine learning
Mechatronics
Neural networks
Performance enhancement
Regular Papers
Robotics
Sensors
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using deep learning (DL) technology, neural networks have achieved great success in various fields of computer vision. Among them, anomaly detection is a promising application of image defect analysis. The purpose of the detector is to find the out-of-distribution when predicting the probability of a DL network for abnormal samples, after some normal sample images are given for training. Geometric transformation (GT) based anomaly detection is one of the recent best methods for classifying abnormal samples among many normal ones. However, the GT method training process is unstable and too inaccurate to be used in industrial applications. The goal of this study is to suggest a method to improve the performance of a GT-based anomaly detector (GTnet). Using observations of GTnet behavior and its training properties, we propose the addition of three techniques that can improve anomaly detection performance for defect inspection in a factory production process. Specifically, k-Winners-Take-All (k-WTA) was applied to the GTnet base model to resist data corruption such as dust on the sample, the temperature scaling method was added to consider correlations between GT classes with similar appearance, and loss redefinition was applied to improve the efficiency of optimal training. Accuracy was improved from 98.56% to 99.86% in the inspection of vehicle part assembly defects, which requires extremely high accuracy. Experimental evaluations were conducted to verify the performance improvement of the GT anomaly detector.
ISSN:1598-6446
2005-4092
DOI:10.1007/s12555-021-0981-4