SEAD: Segment Element-Based Anomaly Detection

Anomaly detection in images is crucial for the quality control process in manufacturing. Existing anomaly detection methods have achieved high accuracy on many public datasets, which typically include structural anomalies that affect part of the image. However, in real-world scenarios, in addition t...

Full description

Saved in:
Bibliographic Details
Main Authors: Kosaburo Hattori, Ryuto Ishibashi, Hayata Kaneko, Tomonori Izumi, Lin Meng
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10807229/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846109935836856320
author Kosaburo Hattori
Ryuto Ishibashi
Hayata Kaneko
Tomonori Izumi
Lin Meng
author_facet Kosaburo Hattori
Ryuto Ishibashi
Hayata Kaneko
Tomonori Izumi
Lin Meng
author_sort Kosaburo Hattori
collection DOAJ
description Anomaly detection in images is crucial for the quality control process in manufacturing. Existing anomaly detection methods have achieved high accuracy on many public datasets, which typically include structural anomalies that affect part of the image. However, in real-world scenarios, in addition to structural anomalies, logical anomalies that affect the entire image can occur, and these methods often struggle to detect them. Therefore, this paper proposes an anomaly detection method called “SEAD”, based on the conventional “ComAD”, which can detect structural and logical anomalies with higher accuracy while segmenting each element of the image more flexibly. Specifically, SEAD involves annotating each MVTec LOCO dataset category which contains structural and logical anomalies with five images per category. SEAD then employs the few-shot segmentation model “SegGPT” to segment each image into multiple elements. Following this, SEAD constructs the memory bank that stores the color and pixel count of each element in normal images and detects anomalies by measuring the Euclidean distance from the test images. Additionally, SEAD normalises the anomaly scores using the evaluation dataset to align the anomaly score scales of the conventional anomaly detection model with those of the proposed model. Experiments validate the proposed method by comparing it to previous anomaly detection methods on the MVTec LOCO dataset. The experimental results show that the proposed method achieves an AUROC of 91.2% (an improvement of 2.2%), demonstrating its superiority over existing methods.
format Article
id doaj-art-92bda988b4134a1e974faf53973e40e6
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-92bda988b4134a1e974faf53973e40e62024-12-25T00:01:06ZengIEEEIEEE Access2169-35362024-01-011219365319366210.1109/ACCESS.2024.352034310807229SEAD: Segment Element-Based Anomaly DetectionKosaburo Hattori0https://orcid.org/0009-0009-7696-1047Ryuto Ishibashi1Hayata Kaneko2Tomonori Izumi3https://orcid.org/0000-0002-3404-5632Lin Meng4https://orcid.org/0000-0003-4351-6923College of Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, JapanCollege of Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, JapanCollege of Science and Engineering, Ritsumeikan University, Kusatsu, Shiga, JapanDepartment of Electronic and Computer Engineering, Ritsumeikan University, Kusatsu, Shiga, JapanDepartment of Electronic and Computer Engineering, Ritsumeikan University, Kusatsu, Shiga, JapanAnomaly detection in images is crucial for the quality control process in manufacturing. Existing anomaly detection methods have achieved high accuracy on many public datasets, which typically include structural anomalies that affect part of the image. However, in real-world scenarios, in addition to structural anomalies, logical anomalies that affect the entire image can occur, and these methods often struggle to detect them. Therefore, this paper proposes an anomaly detection method called “SEAD”, based on the conventional “ComAD”, which can detect structural and logical anomalies with higher accuracy while segmenting each element of the image more flexibly. Specifically, SEAD involves annotating each MVTec LOCO dataset category which contains structural and logical anomalies with five images per category. SEAD then employs the few-shot segmentation model “SegGPT” to segment each image into multiple elements. Following this, SEAD constructs the memory bank that stores the color and pixel count of each element in normal images and detects anomalies by measuring the Euclidean distance from the test images. Additionally, SEAD normalises the anomaly scores using the evaluation dataset to align the anomaly score scales of the conventional anomaly detection model with those of the proposed model. Experiments validate the proposed method by comparing it to previous anomaly detection methods on the MVTec LOCO dataset. The experimental results show that the proposed method achieves an AUROC of 91.2% (an improvement of 2.2%), demonstrating its superiority over existing methods.https://ieeexplore.ieee.org/document/10807229/Anomaly detectionlogical anomaliesSegGPTdeep learning
spellingShingle Kosaburo Hattori
Ryuto Ishibashi
Hayata Kaneko
Tomonori Izumi
Lin Meng
SEAD: Segment Element-Based Anomaly Detection
IEEE Access
Anomaly detection
logical anomalies
SegGPT
deep learning
title SEAD: Segment Element-Based Anomaly Detection
title_full SEAD: Segment Element-Based Anomaly Detection
title_fullStr SEAD: Segment Element-Based Anomaly Detection
title_full_unstemmed SEAD: Segment Element-Based Anomaly Detection
title_short SEAD: Segment Element-Based Anomaly Detection
title_sort sead segment element based anomaly detection
topic Anomaly detection
logical anomalies
SegGPT
deep learning
url https://ieeexplore.ieee.org/document/10807229/
work_keys_str_mv AT kosaburohattori seadsegmentelementbasedanomalydetection
AT ryutoishibashi seadsegmentelementbasedanomalydetection
AT hayatakaneko seadsegmentelementbasedanomalydetection
AT tomonoriizumi seadsegmentelementbasedanomalydetection
AT linmeng seadsegmentelementbasedanomalydetection