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/

Zendy Plus

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

Zendy Tools

Zendy Open

Multispectral and multimodal images are of important usage in the field ofmulti-source visual information fusion. Due to the alternation or movement ofimage devices, the acquired multispectral and multimodal images are usuallymisaligned, and hence image registration is pre-requisite. Different from theregistration of common images, the registration of multispectral or multimodalimages is a challenging problem due to the nonlinear variation of intensity andgradient. To cope with this challenge, we propose the phase congruency network(PCNet) to enhance the structure similarity of multispectral or multimodalimages. The images can then be aligned using the similarity-enhanced featuremaps produced by the network. PCNet is constructed under the inspiration of thewell-known phase congruency. The network embeds the phase congruency prior intotwo simple trainable layers and series of modified learnable Gabor kernels.Thanks to the prior knowledge, once trained, PCNet is applicable on a varietyof multispectral and multimodal data such as flash/no-flash and RGB/NIR imageswithout additional further tuning. The prior also makes the networklightweight. The trainable parameters of PCNet are 2400 times less than thedeep-learning registration method DHN, while its registration performancesurpasses DHN. Experimental results validate that PCNet outperforms currentstate-of-the-art conventional multimodal registration algorithms. Besides,PCNet can act as a complementary part of the deep-learning registrationmethods, which significantly boosts their registration accuracy. The percentageof the number of images under 1 pixel average corner error (ACE) of UDHN israised from 0.2% to 89.9% after the processing of PCNet.

PCNet: A Structure Similarity Enhancement Method for Multispectral and Multimodal Image Registration