Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197116687> ?p ?o ?g. }
- W3197116687 abstract "In this paper, we propose an efficient approach for industrial defect detection that is modeled based on anomaly detection using point pattern data. Most recent works use textit{global features} for feature extraction to summarize image content. However, global features are not robust against lighting and viewpoint changes and do not describe the image's geometrical information to be fully utilized in the manufacturing industry. To the best of our knowledge, we are the first to propose using transfer learning of local/point pattern features to overcome these limitations and capture geometrical information of the image regions. We model these local/point pattern features as a random finite set (RFS). In addition we propose RFS energy, in contrast to RFS likelihood as anomaly score. The similarity distribution of point pattern features of the normal sample has been modeled as a multivariate Gaussian. Parameters learning of the proposed RFS energy does not require any heavy computation. We evaluate the proposed approach on the MVTec AD dataset, a multi-object defect detection dataset. Experimental results show the outstanding performance of our proposed approach compared to the state-of-the-art methods, and the proposed RFS energy outperforms the state-of-the-art in the few shot learning settings." @default.
- W3197116687 created "2021-09-13" @default.
- W3197116687 creator A5015929812 @default.
- W3197116687 creator A5050176259 @default.
- W3197116687 creator A5064997605 @default.
- W3197116687 creator A5067249512 @default.
- W3197116687 date "2021-08-27" @default.
- W3197116687 modified "2023-09-26" @default.
- W3197116687 title "Anomaly Detection of Defect using Energy of Point Pattern Features within Random Finite Set Framework." @default.
- W3197116687 cites W1532362218 @default.
- W3197116687 cites W1540596182 @default.
- W3197116687 cites W1686810756 @default.
- W3197116687 cites W169539560 @default.
- W3197116687 cites W1710476689 @default.
- W3197116687 cites W1745301770 @default.
- W3197116687 cites W1945298332 @default.
- W3197116687 cites W1959608418 @default.
- W3197116687 cites W2014787937 @default.
- W3197116687 cites W2016305103 @default.
- W3197116687 cites W2034851609 @default.
- W3197116687 cites W2042316011 @default.
- W3197116687 cites W2046464073 @default.
- W3197116687 cites W2048710758 @default.
- W3197116687 cites W2111308925 @default.
- W3197116687 cites W2117228865 @default.
- W3197116687 cites W2118166339 @default.
- W3197116687 cites W2119605622 @default.
- W3197116687 cites W2122646361 @default.
- W3197116687 cites W2124404372 @default.
- W3197116687 cites W2125629257 @default.
- W3197116687 cites W2141584146 @default.
- W3197116687 cites W2151103935 @default.
- W3197116687 cites W2155541015 @default.
- W3197116687 cites W2155903085 @default.
- W3197116687 cites W2172188317 @default.
- W3197116687 cites W2320444803 @default.
- W3197116687 cites W2345643369 @default.
- W3197116687 cites W2471962767 @default.
- W3197116687 cites W2552392885 @default.
- W3197116687 cites W2553151007 @default.
- W3197116687 cites W2738401084 @default.
- W3197116687 cites W2749224737 @default.
- W3197116687 cites W2762457108 @default.
- W3197116687 cites W2782812883 @default.
- W3197116687 cites W2786088545 @default.
- W3197116687 cites W2803697594 @default.
- W3197116687 cites W2807955733 @default.
- W3197116687 cites W2840375954 @default.
- W3197116687 cites W2867167548 @default.
- W3197116687 cites W2889903120 @default.
- W3197116687 cites W2900627348 @default.
- W3197116687 cites W2902101981 @default.
- W3197116687 cites W2903701192 @default.
- W3197116687 cites W2904559969 @default.
- W3197116687 cites W2914570111 @default.
- W3197116687 cites W2916773661 @default.
- W3197116687 cites W2922243907 @default.
- W3197116687 cites W2945655544 @default.
- W3197116687 cites W2948982773 @default.
- W3197116687 cites W2949848919 @default.
- W3197116687 cites W2951870616 @default.
- W3197116687 cites W2960033181 @default.
- W3197116687 cites W2963045681 @default.
- W3197116687 cites W2963258546 @default.
- W3197116687 cites W2963324085 @default.
- W3197116687 cites W2963344330 @default.
- W3197116687 cites W2963537932 @default.
- W3197116687 cites W2963741406 @default.
- W3197116687 cites W2963773039 @default.
- W3197116687 cites W2963956526 @default.
- W3197116687 cites W2965496000 @default.
- W3197116687 cites W2970648063 @default.
- W3197116687 cites W2971198903 @default.
- W3197116687 cites W2979458572 @default.
- W3197116687 cites W2982512126 @default.
- W3197116687 cites W2984761674 @default.
- W3197116687 cites W2995085126 @default.
- W3197116687 cites W2996179709 @default.
- W3197116687 cites W3009931536 @default.
- W3197116687 cites W3019507401 @default.
- W3197116687 cites W3034916114 @default.
- W3197116687 cites W3034942609 @default.
- W3197116687 cites W3043075211 @default.
- W3197116687 cites W3110536152 @default.
- W3197116687 cites W3113273504 @default.
- W3197116687 cites W3118895125 @default.
- W3197116687 cites W3147184966 @default.
- W3197116687 cites W3160366495 @default.
- W3197116687 cites W3165012668 @default.
- W3197116687 cites W34992941 @default.
- W3197116687 cites W2997169974 @default.
- W3197116687 hasPublicationYear "2021" @default.
- W3197116687 type Work @default.
- W3197116687 sameAs 3197116687 @default.
- W3197116687 citedByCount "0" @default.
- W3197116687 crossrefType "posted-content" @default.
- W3197116687 hasAuthorship W3197116687A5015929812 @default.
- W3197116687 hasAuthorship W3197116687A5050176259 @default.
- W3197116687 hasAuthorship W3197116687A5064997605 @default.
- W3197116687 hasAuthorship W3197116687A5067249512 @default.