scholar.google.com › citations
An image SR method is proposed to improve the accuracy of vision measurement. Curvelet transform is formulated to feature extraction in neural network. Curvelet loss is built to evaluate the recovery quality of Curvelet coefficients. Loss function is built to measure the localization accuracy of reconstructed edges.
30 Nov 2023
This paper presents a new image quality assessment based on the curvelet decomposition. The curvelet transform is introduced for its ability to represent ...
28 Jul 2015 · This paper presents a new image quality assessment based on the curvelet decomposition. The curvelet transform is introduced for its ability ...
In proposed work, MGA transforms perform excellently for reference image reconstruction, have perfect perception of orientation, are computationally tractable, ...
Abstract: We present an image resolution enhancement method based on Curvelet transform. This transform is used to decompose the input image into different ...
17 Jan 2023 · In this work, a resolution enhancement technique using the concepts of curvelet transform and iterative back projection is presented.
22 Oct 2024 · We study the efficacy of utilizing a powerful image descriptor, the curvelet transform, to learn a no-reference (NR) image quality ...
Abstract: Super-resolution techniques are used to reconstruct an image with a high resolution from one or more low-resolution image(s).
The curvelet transform represents edges better than wavelets, and is therefore well-suited for multiscale edge enhancement. We compare this approach with ...
26 Feb 2015 · Higher the PSNR better the quality of the image. The Curvelet transform is a higher dimensional generalization of the Wavelet transform designed ...