Abstract
In this paper, a novel compressive super-resolution algorithm based on pre-classification learning is proposed to solve the low resolution problem of Passive Millimeter Wave (PMMW) images. In order to lower the computation costs and mismatching probability of training samples, this proposed algorithm introduces three main improvements to the traditional framework of neighbor embedding method. First, the joint feature vector is extracted for each image patch to obtain a better description of the image. Second, a very sparse measurement matrix is used to compress the joint feature vector into a low-dimensional one. Third, a novel pre-classification method is proposed. Experimental results demonstrate that the proposed algorithm improves the resolution of PMMW images and has much higher running efficiency.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
