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

State-of-the-art deep neural network models have reached near perfect facerecognition accuracy rates on controlled high-resolution face images. However,their performance is drastically degraded when they are tested with verylow-resolution face images. This is particularly critical in surveillancesystems, where a low-resolution probe image is to be matched withhigh-resolution gallery images. super-resolution techniques aim at producinghigh-resolution face images from low-resolution counterparts. While they arecapable of reconstructing images that are visually appealing, theidentity-related information is not preserved. Here, we propose anidentity-preserving end-to-end image-to-image translation deep neural networkwhich is capable of super-resolving very low-resolution faces to theirhigh-resolution counterparts while preserving identity-related information. Weachieved this by training a very deep convolutional encoder-decoder networkwith a symmetric contracting path between corresponding layers. This networkwas trained with a combination of a reconstruction and an identity-preservingloss, on multi-scale low-resolution conditions. Extensive quantitativeevaluations of our proposed model demonstrated that it outperforms competingsuper-resolution and low-resolution face recognition methods on natural andartificial low-resolution face data sets and even unseen identities.

Multi Scale Identity-Preserving Image-to-Image Translation Network for Low-Resolution Face Recognition