Deep SVDD 알고리즘 기반의 품질 검사 시스템 설계 = Designing a quality inspection system using Deep SVDD 1)

다국어 초록 (Multilingual Abstract)

In manufacturing companies that focus on small-scale production of multiple product varieties, defective products are manually selected by workers rather than relying on automated inspection.
Consequently, there is a higher risk of incorrect sorting due to variations in selection criteria based on the workers' experience and expertise, without consistent standards. Moreover, for non-standardized flexible objects with varying sizes and shapes, there can be even greater deviations in the selection criteria. To address these issues, this paper designs a quality inspection system using artificial intelligence-based unsupervised learning methods and conducts research by experimenting with accuracy using a dataset obtained from real manufacturing environments.

참고문헌 (Reference)

1 Tolga Ergen, "Unsupervised Anomaly Detection With LSTM Neural Networks" Institute of Electrical and Electronics Engineers (IEEE) 31 (31): 3127-3141, 2019

2 LIU, Wenqian, "Towards visually explaining variational autoencoders" 8642-8651, 2020

3 Roth, Karsten, "Towards total recall in industrial anomaly detection" 14318-14328, 2022

4 Papernot, Nicolas, "The limitations of deep learning in adversarial settings" IEEE 372-387, 2016

5 AKCAY, Samet, "Semi-supervised anomaly detection via adversarial training" Springer International Publishing 622-637, 2019

6 Huang, Chaoqin, "Registration based few-shot anomaly detection" Springer Nature Switzerland 303-319, 2022

7 SULTANI, Waqas, "Real-world anomaly detection in surveillance videos" 6479-6488, 2018

8 PERERA, Pramuditha, "Ocgan: One-class novelty detection using gans with constrained latent representations" 2898-2906, 2019

9 Kang Zhou, "Memorizing Structure-Texture Correspondence for Image Anomaly Detection" Institute of Electrical and Electronics Engineers (IEEE) 33 (33): 2335-2349, 2021

10 El Hajjami, S., "Machine learning for anomaly detection. performance study considering anomaly distribution in an imbalanced dataset" IEEE 1-8, 2020

11 BERGMANN, Paul, "MVTec AD--A comprehensive real-world dataset for unsupervised anomaly detection" 9592-9600, 2019

12 Zheng, Ye, "Focus your distribution: Coarse-to-fine non-contrastive learning for anomaly detection and localization" IEEE 1-6, 2022

13 Mohammad Sabokrou, "Deep-Cascade: Cascading 3D Deep Neural Networks for Fast Anomaly Detection and Localization in Crowded Scenes" Institute of Electrical and Electronics Engineers (IEEE) 26 (26): 1992-2004, 2017

14 RUFF, Lukas, "Deep one-class classification. In: International conference on machine learning" 4393-4402, 2018

15 ZHOU, Chong, "Anomaly detection with robust deep autoencoders" 665-674, 2017

16 Naveen Paluru, "Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images" Institute of Electrical and Electronics Engineers (IEEE) 32 (32): 932-946, 2021

17 Raj, S, "Analysis on credit card fraud detection methods" IEEE 152-156, 2011

18 LUO, Weixin, "A revisit of sparse coding based anomaly detection in stacked rnn framework" 341-349, 2017