Abstract
Defect detection in the manufacturing industry is of utmost importance for product quality inspection. Recently, optical defect detection has been investigated as an anomaly detection using different deep learning methods. However, the recent works do not explore the use of point pattern features, such as SIFT for anomaly detection using the recently developed set-based methods. In this paper, we present an evaluation of different point pattern feature detectors and descriptors for defect detection application. The evaluation is performed within the random finite set framework. Handcrafted point pattern features, such as SIFT as well as deep features are used in this evaluation. Random finite set-based defect detection is compared with state-of-the-arts anomaly detection methods. The results show that using point pattern features, such as SIFT as data points for random finite set-based anomaly detection achieves the most consistent defect detection accuracy on the MVTec-AD dataset.
Highlights
UTOMATED visual inspection is a common part of the local order binary pattern for fabric defect detection [14], and quality control process in many modern manufactur- scale-invariant keypoint features for PCB inspection [15]
We propose the use of transfer learning of deep local the definition of defect detection stated by Newman et al [26] 103 point pattern features for anomaly detection of defect
Existing works [27], [28] in this domain mainly The primary goal of this paper is to explore the advantage concentrate on performing anomaly detection by looking at of using point pattern features within the Random Finite Set (RFS)-based anomaly the whole image through extracting a single feature vector detection framework for defect detection and examine the and its deviation from the “normal” samples, summarizing effectiveness of this approach compared with other statethe entire image by one feature vector commonly referred to of-the-art global-based deep anomaly detection approaches
Summary
UTOMATED visual inspection is a common part of the local order binary pattern for fabric defect detection [14], and quality control process in many modern manufactur- scale-invariant keypoint features for PCB inspection [15]. image processing techniques is the need for implicit engi Different data-driven methods based on deep learning have neered features, which can be challenging when applied to 12 been proposed for visual inspection in different application 28 complex cases. An attempt to address this issue has been to 13 areas, such as manufacturing [2]–[5], construction [6]–[8], 29 employ deep learning-based solutions for automated defect 14 transportation [9], [10] and computing systems [11], [12]. Kamoona et al.: Point Pattern Feature-Based Anomaly Detection for Manufacturing Defects, in the Random Finite Set Framework representation learning to perform different tasks, where the goal is to transform complex data into abstract representations known as features. Various deep learning techniques have been proposed to deal with different surface defects [20],
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
