Multi-focus image fusion using sharpness criteria for visual sensor networks in wavelet domain. (April 2016)

• Record Type: Journal Article
• Authors: Abdipour, Mohammad; Nooshyar, Mehdi
• Is Part Of: Computers & electrical engineering. Volume 51(2016)
• Page Start: 74
• Page End: 88
• Publication Date: 2016-04
• Subjects: Multi-focus -- Image fusion -- Sharpness criteria -- Wavelet transform -- Visual sensor network; 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.2016.03.011
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: A new method of fusion using sharpness criteria in wavelet domain is used in this paper. The suggested method uses the two criteria of spatial frequency and variance for fusion. A lot of experiments indicate the efficiency of the recommended method both in quality and complexity. Abstract: The aim of multi-focus image fusion is to combine several images taken by different sensors and with different focuses to increase the perception of scene. The proposed methods suffer from some undesirable side effects like blurring artifact and/or blocking which decreases the quality of the output image. This paper presents an efficient approach for multi-focus image fusion based on variance and spatial frequency calculated in the wavelet domain. The proposed method remarkably reduces the amount of distortion artifacts and contrast loss due to the fact that variance and spatial frequency-based fusion significantly enhances reliability in feature selection and data fusion procedures. The algorithm ensures to a great extant the access to the data of the images. The experimental results verify the efficiency of the proposed method in the output image quality, as well as its lower complexity, in comparison with several recently related works. Graph Abstract: