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

In this paper, we present a deep coupled framework to address the problem ofmatching sketch image against a gallery of mugshots. Face sketches have theessential in- formation about the spatial topology and geometric details offaces while missing some important facial attributes such as ethnicity, hair,eye, and skin color. We propose a cou- pled deep neural network architecturewhich utilizes facial attributes in order to improve the sketch-photorecognition performance. The proposed Attribute-Assisted Deep Con- volutionalNeural Network (AADCNN) method exploits the facial attributes and leverages theloss functions from the facial attributes identification and face verificationtasks in order to learn rich discriminative features in a common em- beddingsubspace. The facial attribute identification task increases the inter-personalvariations by pushing apart the embedded features extracted from individualswith differ- ent facial attributes, while the verification task reduces theintra-personal variations by pulling together all the fea- tures that arerelated to one person. The learned discrim- inative features can be wellgeneralized to new identities not seen in the training data. The proposedarchitecture is able to make full use of the sketch and complementary fa- cialattribute information to train a deep model compared to the conventionalsketch-photo recognition methods. Exten- sive experiments are performed oncomposite (E-PRIP) and semi-forensic (IIIT-D semi-forensic) datasets. Theresults show the superiority of our method compared to the state- of-the-artmodels in sketch-photo recognition algorithms

Deep Sketch-Photo Face Recognition Assisted by Facial Attributes