Multimodal sensor medical image fusion based on mutual‐structure for joint filtering using sparse representation

• Published in: International journal of imaging systems and technology Vol. 28; no. 1; pp. 3 - 14
• Main Authors: Li, Weisheng, Xu, Xiaofan, Du, Jiao
• Format: Journal Article
• Language: English
• Published: New York Wiley Subscription Services, Inc 01.03.2018
• Subjects: Computer vision; Defense industry; Filtration; Image contrast; Image processing; Image reconstruction; joint filtering; medical image fusion; mutual‐structure; Representations; sparse representation
• ISSN: 0899-9457; 1098-1098
• DOI: 10.1002/ima.22251

Multimodal sensor medical image fusion has been widely reported in recent years, but the fused image by the existing methods introduces low contrast information and little detail information. To overcome this problem, the new image fusion method is proposed based on mutual‐structure for joint filtering and sparse representation in this article. First, the source image is decomposed into a series of detail images and coarse images by mutual‐structure for joint filtering. Second, sparse representation is adopted to fuse coarse images and then local contrast is applied for fusing detail images. Finally, the fused image is reconstructed by the addition of the fused coarse images and the fused detail images. By experimental results, the proposed method shows the best performance on preserving detail information and contrast information in the views of subjective and objective evaluations.