Multi-focus image fusion using sharpness criteria for visual sensor networks in wavelet domain

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. © 2016 Elsevier Ltd. All rights reserved.