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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Establishing correspondences is a fundamental task in variety of imageprocessing and computer vision applications. In particular, finding thecorrespondences between a non-linearly deformed image pair induced by differentmodality conditions is a challenging problem. This paper describes a efficientbut powerful image transform called local area transform (LAT) formodality-robust correspondence estimation. Specifically, LAT transforms animage from the intensity domain to the local area domain, which is invariantunder nonlinear intensity deformations, especially radiometric, photometric,and spectral deformations. In addition, robust feature descriptors arereformulated with LAT for several practical applications. Furthermore,LAT-convolution layer and Aception block are proposed and, with these novelcomponents, deep neural network called LAT-Net is proposed especially for scenerecognition task. Experimental results show that LATransformed images provide aconsistency for nonlinearly deformed images, even under random intensitydeformations. LAT reduces the mean absolute difference as compared toconventional methods. Furthermore, the reformulation of descriptors with LATshows superiority to conventional methods, which is a promising result for thetasks of cross-spectral and modality correspondence matching. the local areacan be considered as an alternative domain to the intensity domain to achieverobust correspondence matching, image recognition, and a lot of applications:such as feature matching, stereo matching, dense correspondence matching, imagerecognition, and image retrieval.

Local Area Transform for Cross-Modality Correspondence Matching and Deep Scene Recognition