Efficient fusion scheme for multi-focus images by using blurring measure

doi:10.1016/j.dsp.2008.11.002

Digital Signal Processing

Volume 19, Issue 2, March 2009, Pages 186-193

https://doi.org/10.1016/j.dsp.2008.11.002 Get rights and content

Abstract

In this paper, a simple and efficient multi-focus image fusion approach is proposed. As for the multi-focus images, all of them are obtained from the same scene with different focuses. So the images can be segmented into two kinds regions based on out of and on the focus, which directly leads to a region based fusion, i.e., finding out all of the regions on the focus from the source images, and merging them into a combination image. This poses the question of how to locate the regions on the focus from the input images. Considering that the details or scales are different in the regions which are not and on the focuses, blurring measure method in this paper is used to locate the regions based on the blocking degree. This new fusion method can significantly reduce the amount of distortion artifacts and the loss of contrast information. These are usually observed in fused images in the conventional fusion schemes. The fusion performance of proposed method has been evaluated through informal visual inspection and objective fusion performance measurements, and results show the advantages of the approach compared to conventional fusion approaches.

Section snippets

Yingjie Zhang was born in 1962. He obtained the Ph.D. degree in computer-aided design and computer-aided manufacturing from Northwestern Polytechnic University, and the M.S. degree in mechanical manufacture from Xi'an University of Technology. He is currently an Assistant Professor in the School of Mechanical Engineering at the Xi'an Jiaotong University. His research interests are image processing and 3D visualization.

References (15)

S. Mukhopadhyay et al.
Fusion of 2D gray scale images using multiscale morphology
Pattern Recogn.
(2001)
V.S. Petrovic et al.
Sensor noise effects on signal-level image fusion performance
Informat. Fusion
(2003)
L. Rudin et al.
Nonlinear total variation based noise removal algorithms
Physica
(1992)
J.G. Liu
Smoothing filter-based modulation: A spectral preserve image fusion technique for improving spatial details
Int. J. Remote Sens.
(2000)
D.A. Mouat et al.
Remote sensing techniques in the analysis of change detection
Geocarto Internat.
(1993)
S. Mallat
A Wavelet Tour of Signal Processing
(1998)
R.L. Claypoole et al.
Nonlinear wavelet transforms for image coding via lifting
IEEE Trans. Image Process.
(2003)

There are more references available in the full text version of this article.

Cited by (49)

Developing learning based intelligent fusion for deblurring confocal microscopic images
2016, Engineering Applications of Artificial Intelligence
The demand of high quality confocal microscopic images is increasing for critical tasks such as study of living tissues at cellular resolution and disease diagnosis. The results of such tasks are often affected by the blur introduced in microscopic images. Removal of blur from multi-focus microscopic images without deteriorating their visual quality is a challenging task. The confocal microscopic images are obtained by averaging their frames. This process introduces the blurring artefacts that degrade the quality of microscopic images. In this work, we presented learning-based intelligent fusion to minimize the blurring artefacts of confocal microscopic images. The quality of these images is improved using the proposed individual and ensemble fusion models. In the proposed scheme, block-based features are extracted from the blurred images. These informative features are then used to develop the individual models that construct the fused images using their fusion maps. The predicted information of the individual fusion maps is then combined to construct the ensemble-based fused image. The proposed learning-based approach has demonstrated improved quantitative and qualitative results compared to rule-based fusion approaches. The proposed fusion models can be employed as a useful tool in confocal microscopy frames to generate the improved quality images with reduced blurring artefacts.
A novel ensemble approach using individual features for multi-focus image fusion
2016, Computers and Electrical Engineering
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.
Multi-focus image fusion algorithm based on focused region extraction
2016, Neurocomputing
Detection of the focused region is the key issue of the multi-focus image fusion algorithm. The blurred boundary of the focused region increases the difficulty of identifying focused regions accurately. According to the principles that the focused region of the source image should be directly fused as much as possible, this paper proposes a novel multi-focus image fusion algorithm based on saliency analysis, Graph-based visual saliency (GBVS) algorithm is used to locate the focused region in the source image. Then, watershed and morphological methods are used to get the enclosed region of the saliency map and remove the pseudo-focus region. Finally, the focused region is fused directly and the remaining regions are fused based on the Shearlet transform. Experiments demonstrate that the proposed approach can accurately extract the focused region, the fused image preserves more features and it is superior to traditional methods in subjective and objective evaluations.
Quadtree-based multi-focus image fusion using a weighted focus-measure
2015, Information Fusion
Citation Excerpt :
Usually, there may exist some small isolated regions inside a focused region. To handle this problem, we utilize a small region filter to delete the small isolated regions or fill the holes in the focused regions detected from each source image [15]. Suppose that the size of the source images is M × N. Based on the visual observation, if the area of an image region is less than (M × N)/40, this region is a very small region comparing with the whole image.
The purpose of multi-focus image fusion is integrating the partially focused images into one single image which is focused everywhere. To achieve this purpose, we propose a new quadtree-based algorithm for multi-focus image fusion. In this work, an effective quadtree decomposition strategy is presented. According to the proposed decomposition strategy, the source images are decomposed into blocks with optimal sizes in a quadtree structure. And in this tree structure, the focused regions are detected by using a new weighted focus-measure, named as the sum of the weighted modified Laplacian. Finally, the focused regions could be well extracted from the source images and reconstructed to produce one fully focused image. Moreover, the new weighted focus-measure performs better than the commonly used focus-measures on the detection of the focused regions, since it is sensitive to the homogeneous regions. The proposed algorithm is simple yet effective, because of the quadtree decomposition strategy and the new weighted focus-measure. To do the comparison, the proposed algorithm is compared with several existing fusion algorithms, in both the qualitative and quantitative ways. The experimental results show that the proposed algorithm yields good results.
A novel multi-focus image fusion algorithm based on random walks
2014, Journal of Visual Communication and Image Representation
In multi-focus image fusion, the aim is to create a single image where the whole scene is focused by fusing multiple images captured with different focus distances. The fused image has greater depth of field than each of the input images. In this paper, we present a new method for multi-focus image fusion via random walks on graphs. The proposed method first evaluates the focus areas in a local sense and identifies nodes corresponding to consistency of nodes in a global sense. Several popular feature sets based on focus measure and color consistency are evaluated and employed to create a fully connected graph to model the global and local characteristics, respectively, of the random walks. The behavior of random walks on the graph is utilized to compute the weighting factor for each of the shallow depth-of-field input image. Experimental results show that the proposed method outperforms many state-of-the-art techniques in both subjective and objective image quality measures.
Region level based multi-focus image fusion using quaternion wavelet and normalized cut
2014, Signal Processing
Citation Excerpt :
Compared pixel level methods are Laplacian pyramid (LP) and nonsubsampled contourlet transform based fusion (NSCT) [17] which is usually performed best [33] in contrast with DWT, dual tree complex wavelet, stationary wavelet, curvelet and contourlet transform. Also, we compare the proposed fusion result with region level fusion methods using DWT which substitutes QWT in our framework, blur measure (BM) [9] and similarity characteristics (SC) [11]. In this section, we compare the proposed fusion method with others from visual perception.
Region level based methods are popular in recent years for multifocus image fusion as they are the most direct fusion ways. However, the fusion result is not ideal due to the difficulty in focus region segmentation. In this paper, we propose a novel region level based multifocus image fusion method that can locate the boundary of the focus region accurately. As a novel tool of image analysis, phases in the quaternion wavelet transform (QWT) are capable of representing the texture information in the image. We use the local variance of the phases to detect the focus or defocus for every pixel initially. Then, we segment the focus detection result by the normalized cut to remove detection errors, thus initial fusion result is acquired through copying from source images according to the focus detection results. Next, we compare initial fusion result with spatial frequency weighted fusion result to accurately locate the boundary of the focus region by structural similarity. Finally, the fusion result is obtained using spatial frequency as fusion weight along the boundary of the focus region. Furthermore, we conduct several experiments to verify the feasibility of the fusion framework. The proposed algorithm is demonstrated superior to the reference methods.

View all citing articles on Scopus

Liling Ge was born in 1961. She obtained the Bachelor degree in computer science from Xi'an Jiaotong University. She is currently an Assistant Professor in the School of Material Science and Engineering at the Xi'an University of Technology. Her research interests are image processing and visual simulation.

View full text

Efficient fusion scheme for multi-focus images by using blurring measure

Abstract

Section snippets

Pattern Recogn.

Informat. Fusion

Physica

Smoothing filter-based modulation: A spectral preserve image fusion technique for improving spatial details

Int. J. Remote Sens.

Remote sensing techniques in the analysis of change detection

Geocarto Internat.

A Wavelet Tour of Signal Processing

Nonlinear wavelet transforms for image coding via lifting

IEEE Trans. Image Process.