Abstract
In this paper, a Spare Representation (SR) based fusion quality evaluation and analysis method is proposed. This method employs Joint Sparse Representation (JSR) to extract the source image remnants after fusion. These atom-level remnants indicate the fusion quality intuitively, and permit the analysis of fusion effect in learned feature space. Our analysis results indicate that high salient atoms always present poor expressions in fusion results. An improved fusion rule is designed to emphasis high salient atoms accordingly. In experiments, the effectiveness of our method was verified and the characteristics of atom JSR remnants were investigated in detail first. Then the new fusion rule was tested to demonstrate the value of JSR remnant analysis. The objective and subjective comparison results indicate that the proposed analytical evaluation metric can measure fusion quality and analysis atom fusion effect accurately. The new fusion rule provides a valuable alternative for SR fusion algorithm design.
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 callMore From: Journal of Visual Communication and Image Representation
Disclaimer: 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.
