Multifocus Image Fusion by Establishing Focal Connectivity

Abstract

Multifocus fusion is the process of unifying focal information from a set of input images acquired with limited depth of field. In this effort, we present a general purpose multifocus fusion algorithm, which can be applied to varied applications ranging from microscopic to long range scenes. The main contribution in this paper is the segmentation of the input images into partitions based on focal connectivity. Focal connectivity is established by isolating regions in an input image that fall on the same focal plane. Our method uses focal connectivity and does not rely on physical properties like edges directly for segmentation. Our method establishes sharpness maps to the input images, which are used to isolate and attribute image partitions to input images. The partitions are mosaiced seamlessly to form the fused image. Illustrative examples of multifocus fusion using our method are shown. Comparisons against existing methods are made and the results are discussed.

Extended depth-of-field via focus stacking and graph cuts

“…The "Tenengrad" sharpness is defined as S = M i=1 N j=1 y) where,the size of image is M × N and x and y denote directional gradient operations.The objective result are consistent with visual inspection and show that our method produces images with better overall sharpness.The results of objective tests are list in Table our method indeed outperforms the methods in [2] and [3]. Additional results and supporting materials are presented at: http://cs.adelaide.edu.au/˜chhshen/projects/ N9.…”

“…In Fig. 6, we compare our fusion method with spatial domainbased method [2] and multiscale transform domain method [3] on dataset "Face" and "Pen". The test image sequences are downloaded from http://web.eecs.utk.edu/˜hharihar/fusion.…”

“…The first category is the spatial domain-based methods [1,2]. One of the basic approach in spacial domain is to divide the images into a set of regions.…”

“…The comparison with spatial domain-based method[2] and multiscale transform domain method[3] on datasets "Face" and "Pen". (a) and (d): Results from method of [2]; (b) and (e): Results from method of [3]; (c) and (f): Our focus stacking results.…”

Learning based automatic detection of myonuclei in isolated single skeletal muscle fibers using multi-focus image fusion

“…In our approach we apply a modified version of the gradient-based method originally proposed in [7] to compose a multi-focus image from the input z-stack images. The magnitude of gradients for the i-th image can be calculated as: Fig.…”