A novel ensemble approach using individual features for multi-focus image fusion. (August 2016)

• Record Type: Journal Article
• Authors: Kausar, Nabeela; Majid, Abdul; Javed, Syed Gibran
• Is Part Of: Computers & electrical engineering. Volume 54(2016)
• Page Start: 393
• Page End: 405
• Publication Date: 2016-08
• Subjects: Multi-focus -- Image fusion -- Ensemble -- Confocal microscopy and CT images; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.01.013
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: We developed Ensemble-Individual-Features (Ens-IF) approach for multi-focus image fusion by combining the decision information of individual features. The proposed Ens-IF approach is superior in comparison to the individual pixel-level and the feature-level fusion approaches. The proposed approach can be employed as a post-processor in medical imaging and confocal microscopy systems to reduce the blurring artifacts. Abstract: Image fusion combines images with complementary information to generate an informative image. In this study, we have developed Ensemble-Individual-Features (Ens-IF) for multi-focus image fusion by combining the decision information of individual features. The proposed approach is developed in two main steps. In the first step, the diverse types of features are extracted from each block of input blurred images. The useful information of these individual features indicates which image block is more focused among corresponding blocks in source images. In the second step, the ensemble decision based on individual features is employed to fuse blurred images. The performance of the proposed fusion approach is evaluated for blurred images of confocal microscopy and computed tomography. We observed that Ens-IF approach is superior in comparison to the individual pixel-level and the feature-level fusion approaches. This approach can be employed as a post-processor in medical imaging and confocal microscopy systems to reduce the blurring artifacts. Graphical abstract: