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

The utilization of biometric authentication with pattern images isincreasingly popular in compact Internet of Things (IoT) devices. However, thereliability of such systems can be compromised by image quality issues,particularly in the presence of high levels of noise. While state-of-the-artdeep learning algorithms designed for generic image denoising have shownpromise, their large number of parameters and lack of optimization for uniquebiometric pattern retrieval make them unsuitable for these devices andscenarios. In response to these challenges, this paper proposes a lightweightand robust deep learning architecture, the Residual Wavelet-ConditionedConvolutional Autoencoder (Res-WCAE) with a Kullback-Leibler divergence (KLD)regularization, designed specifically for fingerprint image denoising. Res-WCAEcomprises two encoders - an image encoder and a wavelet encoder - and onedecoder. Residual connections between the image encoder and decoder areleveraged to preserve fine-grained spatial features, where the bottleneck layerconditioned on the compressed representation of features obtained from thewavelet encoder using approximation and detail subimages in thewavelet-transform domain. The effectiveness of Res-WCAE is evaluated againstseveral state-of-the-art denoising methods, and the experimental resultsdemonstrate that Res-WCAE outperforms these methods, particularly for heavilydegraded fingerprint images in the presence of high levels of noise. Overall,Res-WCAE shows promise as a solution to the challenges faced by biometricauthentication systems in compact IoT devices.

ResWCAE: Biometric Pattern Image Denoising Using Residual Wavelet-Conditioned Autoencoder