Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Anomaly Detection and Segmentation Based on Defect Repaired Image Resynthesis

: Dai, Wenting; Erdt, Marius; Sourin, Alexei


Sourin, Alexei (Editor); Rosenberger, Christophe (Editor); Sourina, Olga (Editor) ; European Association for Computer Graphics -EUROGRAPHICS-; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
International Conference on Cyberworlds, CW 2021. Proceedings : 28-30 September 2021, Caen, France
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2021
ISBN: 978-1-6654-1164-6
ISBN: 978-1-6654-4065-3
DOI: 10.1109/CW52790.2021
International Conference on Cyberworlds (CW) <20, 2021, Online>
Conference Paper
Fraunhofer Singapore ()

Anomaly detection is a challenging task in data analysis, especially when it comes to unsupervised pixel-level segmentation of anomalies in images. In this paper, we present a novel multi-stage defect repaired image resynthesis framework for the detection and segmentation of anomalies in images. In contrast to the existing reconstruction-based approaches, our reconstruction is free from artifacts caused by defective regions so that the defects can be identified from the residual map between input samples and their resynthesized defect-eliminated outputs. Our method outperforms the state-of-art benchmarks in most categories using the publicly available MVTec dataset. Besides, the method also demonstrates an excellent capability of repairing defects in abnormal samples.