English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Anomalies in images occur in various scales from a small hole on a carpet toa large stain. However, anomaly detection based on sparse coding, one of thewidely used anomaly detection methods, has an issue in dealing with anomaliesthat are out of the patch size employed to sparsely represent images. A largeanomaly can be considered normal if seen in a small scale, but it is not easyto determine a single scale (patch size) that works well for all images. Then,we propose to incorporate multi-scale features to sparse coding and improve theperformance of anomaly detection. The proposed method, multi-layer featuresparse coding (MLF-SC), employs a neural network for feature extraction, andfeature maps from intermediate layers of the network are given to sparsecoding, whereas the standard sparse-coding-based anomaly detection methoddirectly works on given images. We show that MLF-SC outperformsstate-of-the-art anomaly detection methods including those employing deeplearning. Our target data are the texture categories of the MVTec AnomalyDetection (MVTec AD) dataset, which is a modern benchmark dataset consisting ofimages from the real world. Our idea can be a simple and practical option todeal with practical data.

MLF-SC: Incorporating multi-layer features to sparse coding for anomaly detection