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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Biometric-based personal authentication systems have seen a strong demandmainly due to the increasing concern in various privacy and securityapplications. Although the use of each biometric trait is problem dependent,the human ear has been found to have enough discriminating characteristics toallow its use as a strong biometric measure. To locate an ear in a 2D side faceimage is a challenging task, numerous existing approaches have achievedsignificant performance, but the majority of studies are based on theconstrained environment. However, ear biometrics possess a great level ofdifficulties in the unconstrained environment, where pose, scale, occlusion,illuminations, background clutter etc. varies to a great extent. To address theproblem of ear localization in the wild, we have proposed two high-performanceregion of interest (ROI) segmentation models UESegNet-1 and UESegNet-2, whichare fundamentally based on deep convolutional neural networks and primarilyuses contextual information to localize ear in the unconstrained environment.Additionally, we have applied state-of-the-art deep learning models viz; FRCNN(Faster Region Proposal Network) and SSD (Single Shot MultiBox Detecor) for earlocalization task. To test the model's generalization, they are evaluated onsix different benchmark datasets viz; IITD, IITK, USTB-DB3, UND-E, UND-J2 andUBEAR, all of which contain challenging images. The performance of the modelsis compared on the basis of object detection performance measure parameterssuch as IOU (Intersection Over Union), Accuracy, Precision, Recall, andF1-Score. It has been observed that the proposed models UESegNet-1 andUESegNet-2 outperformed the FRCNN and SSD at higher values of IOUs i.e. anaccuracy of 100\% is achieved at IOU 0.5 on majority of the databases.

UESegNet: Context Aware Unconstrained ROI Segmentation Networks for Ear Biometric