scholarly journals Multi-Resolution Image Fusion Algorithm Based on Improved Regional Cross Entropy and Morphology

2012 ◽  
Vol 6-7 ◽  
pp. 589-594 ◽  
Author(s):  
Wen Ge ◽  
Jin Li Xu ◽  
Peng Li
Keyword(s):  
Image Fusion ◽  
Strong Support ◽  
Fusion Rule ◽  
Frequency Component ◽  
Cross Entropy ◽  
High Frequency Component ◽  
Fusion Method ◽  
Fusion Image ◽  
Fusion Algorithm ◽  
Edge Preserving

Based on image contents, the better to simulate the process pattern of human eyes vision, an image fusion method that emphasizing edge preserving is proposed. Through wavelet transform, an improved regional cross entropy fusion rule is used for the low-frequency component which reflects approximate contents, the fusion method for incorporation of the maximum morphology edge measuring and weighted variance analysis is used for the high-frequency component which reflects detail features of image. Finally, the fusion image is reconstructed through an inverse transform of wavelet. Experimental results show that by using this algorithm, the mutual information between the images can be fused organically, the image clarity is raised, the details of fusion image are enhanced, and the edge information are reappeared better. Strong support for the follow-up information analysis and extractive ability of the images are provided.

A New Image Fusion Method Based on Improved PCNN and Multiscale Decomposition

2013 ◽  
Vol 834-836 ◽  
pp. 1011-1015 ◽  
Author(s):  
Nian Yi Wang ◽  
Wei Lan Wang ◽  
Xiao Ran Guo
Keyword(s):  
Image Fusion ◽  
High Frequency ◽  
Low Frequency ◽  
Fusion Rule ◽  
Contourlet Transform ◽  
Fusion Method ◽  
Nonsubsampled Contourlet Transform ◽  
Cortical Model ◽  
Fusion Algorithm ◽  
Maximum Selection

A new image fusion algorithm based on nonsubsampled contourlet transform and spiking cortical model is proposed in this paper. Considering the human visual system characteristics, two different fusion rules are used to fuse the low and high frequency sub-bands of nonsubsampled contourlet transform respectively. A new maximum selection rule is defined to fuse low frequency coefficients. Spatial frequency is used for the fusion rule of high frequency coefficients. Experimental results demonstrate the effectiveness of the proposed fusion method.

An Image Fusion Algorithm Based on NSCT

2013 ◽  
Vol 427-429 ◽  
pp. 1589-1592
Author(s):  
Zhong Jie Xiao
Keyword(s):  
Image Fusion ◽  
High Frequency ◽  
Low Frequency ◽  
Fusion Rule ◽  
Fusion Method ◽  
Fusion Algorithm ◽  
Visible Image ◽  
Weighted Fusion ◽  
Scene Information ◽  
Feature Information

The study proposed an improved NSCT fusion method based on the infrared and visible light images characteristics and fusion requirement. This paper improved the high-frequency coefficient and low-frequency coefficient fusion rules. The low-frequency sub-band images adopted the pixel feature energy weighted fusion rule. The high-frequency sub-band images adopted the neighborhood variance feature information fusion rule. The fusion experiment results show that this algorithm has good robustness. It could effectively extract edges and texture information. The fused images have abundance scene information and clear target. So this algorithm is an effective infrared and visible image fusion method.

Image Fusion Method Based on Multi-scale Directional Fast Guided Filter and Convolutional Sparse Representation

2019 ◽  
Vol 12 (3) ◽  
pp. 263-269
Author(s):  
Liu Xian-Hong ◽  
Chen Zhi-Bin
Keyword(s):  
Image Fusion ◽  
Sparse Representation ◽  
Filter Bank ◽  
Guided Filter ◽  
Fusion Method ◽  
Edge Preserving ◽  
Directional Information ◽  
Multi Scale ◽  
Directional Filter ◽  
Image Fusion Method

Background: A multi-scale multidirectional image fusion method is proposed, which introduces the Nonsubsampled Directional Filter Bank (NSDFB) into the multi-scale edge-preserving decomposition based on the fast guided filter. Methods: The proposed method has the advantages of preserving edges and extracting directional information simultaneously. In order to get better-fused sub-bands coefficients, a Convolutional Sparse Representation (CSR) based approximation sub-bands fusion rule is introduced and a Pulse Coupled Neural Network (PCNN) based detail sub-bands fusion strategy with New Sum of Modified Laplacian (NSML) to be the external input is also presented simultaneously. Results: Experimental results have demonstrated the superiority of the proposed method over conventional methods in terms of visual effects and objective evaluations. Conclusion: In this paper, combining fast guided filter and nonsubsampled directional filter bank, a multi-scale directional edge-preserving filter image fusion method is proposed. The proposed method has the features of edge-preserving and extracting directional information.

An Image Fusion Algorithm Based on Pseudo-Color

2012 ◽  
Vol 433-440 ◽  
pp. 5436-5442
Author(s):  
Lei Li
Keyword(s):  
Image Fusion ◽  
Color Image ◽  
Target Identification ◽  
Fusion Image ◽  
Fusion Algorithm ◽  
Color Processing ◽  
False Color ◽  
Fused Image ◽  
Color Fusion ◽  
Pseudo Color

The pseudo-color processing for target identification and tracking is very meaningful Experimental results show that the pseudo-color image fusion is a very effective methods. This paper presents a false color image fusion based on the new method. Fusion using wavelet transform grayscale images, find the gray fused image and the difference between the original image, respectively, as the image of l, α, β components are color fusion image, and then after the color transformation, the final false color fused image. The results showed that the color fusion image colors more vivid, more in line with human visual characteristics.

An Image Fusion Algorithm Based on Redundant Wavelet Transform

2014 ◽  
Vol 687-691 ◽  
pp. 3656-3661
Author(s):  
Min Fen Shen ◽  
Zhi Fei Su ◽  
Jin Yao Yang ◽  
Li Sha Sun
Keyword(s):  
Wavelet Transform ◽  
Image Fusion ◽  
High Frequency ◽  
Low Frequency ◽  
Source Image ◽  
Fusion Image ◽  
Fusion Algorithm ◽  
Imaging Characteristics ◽  
Focus Image ◽  
Redundant Wavelet Transform

Because of the limit of the optical lens’s depth, the objects of different distance usually cannot be at the same focus in the same picture, but multi-focus image fusion can obtain fusion image with all goals clear, improving the utilization rate of the image information ,which is helpful to further computer processing. According to the imaging characteristics of multi-focus image, a multi-focus image fusion algorithm based on redundant wavelet transform is proposed in this paper. For different frequency domain of redundant wavelet decomposition, the selection principle of high-frequency coefficients and low-frequency coefficients is respectively discussed .The fusion rule is that,the selection of low frequency coefficient is based on the local area energy, and the high frequency coefficient is based on local variance combining with matching threshold. As can be seen from the simulation results, the method given in the paper is a good way to retain more useful information from the source image , getting a fusion image with all goals clear.

Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform

2013 ◽  
Vol 401-403 ◽  
pp. 1381-1384 ◽  
Author(s):  
Zi Juan Luo ◽  
Shuai Ding
Keyword(s):  
Image Fusion ◽  
Multiple Scales ◽  
Weighted Average ◽  
Fusion Rule ◽  
Contourlet Transform ◽  
Nonsubsampled Contourlet Transform ◽  
Fusion Algorithm ◽  
Fused Image ◽  
Focus Image ◽  
Limited Depth

t is mostly difficult to get an image that contains all relevant objects in focus, because of the limited depth-of-focus of optical lenses. The multifocus image fusion method can solve the problem effectively. Nonsubsampled Contourlet transform has varying directions and multiple scales. When the Nonsubsampled contourlet transform is introduced to image fusion, the characteristics of original images are taken better and more information for fusion is obtained. A new method of multi-focus image fusion based on Nonsubsampled contourlet transform (NSCT) with the fusion rule of region statistics is proposed in this paper. Firstly, different focus images are decomposed using Nonsubsampled contourlet transform. Then low-bands are integrated using the weighted average, high-bands are integrated using region statistics rule. Next the fused image will be obtained by inverse Nonsubsampled contourlet transform. Finally the experimental results are showed and compared with those of method based on Contourlet transform. Experiments show that the approach can achieve better results than the method based on contourlet transform.

Research on Image Fusion Based on Pyramid Decomposition

2013 ◽  
Vol 860-863 ◽  
pp. 2855-2858
Author(s):  
Ming Jing Li ◽  
Yu Bing Dong ◽  
Xiao Li Wang
Keyword(s):  
Image Fusion ◽  
Fusion Method ◽  
Laplacian Pyramid ◽  
Fusion Algorithm ◽  
Resolution Method ◽  
Multi Scale ◽  
Simulation Results ◽  
Spatial Fusion

Different objects could be analyzed by use of pyramid decomposition of image. Image fusion algorithm based on pyramid decomposition of image is multi-scale, multi-resolution method. Its process is completed on different scale, different resolution and different decomposition layer. Compared with spatial fusion method, fusion effects improve obviously. In this paper, principal of pyramid decomposition and process were introduced, and simulation results of image fusion based on Laplacian pyramid, gradient pyramid, ration pyramid and contrast shows that image fusion based on pyramid decomposition is improve obviously.

NSCT-Based Multi-Sensor Image Fusion Algorithm

2013 ◽  
Vol 347-350 ◽  
pp. 3212-3216
Author(s):  
Hai Feng Tan ◽  
Wen Jie Zhao ◽  
De Jun Li ◽  
Tian Wen Luo
Keyword(s):  
Image Fusion ◽  
Average Method ◽  
Low Frequency ◽  
Weighted Average ◽  
Inverse Transformation ◽  
Fusion Image ◽  
Fusion Algorithm ◽  
Regional Energy ◽  
Focus Image ◽  
Quantitative Indicators

Against the defects that the favoritism method and average method in the multi-sensor image fusion are apt to impair the image contrast, an image fusion algorithm based on NSCT is proposed. Firstly, this algorithm applied NSCT to the rectified multi-sensor images from the same scene, then different fusion strategies were adopted to fuse the low-frequency and high-frequency directional sub-band coefficients respectively: regional energy adaptive weighted method was used for low-frequency sub-band coefficient; the directional sub-band coefficient adopted a regional-energy-matching program that combined weighted average method and selection method. Finally, the fusion image was obtained by NSCT inverse transformation. Experiments were conducted to IR and visible light image and multi-focus image respectively. And the fusion image was evaluated objectively. The experimental results show that the fusion image obtained through this algorithm has better subjective visual effects and objective quantitative indicators. It is also superior to the traditional fusion method.

Contourlet Transform in the Application of the Image Fusion

2012 ◽  
Vol 239-240 ◽  
pp. 1432-1436
Author(s):  
Zhuan Zheng Zhao
Keyword(s):  
Image Fusion ◽  
Image Resolution ◽  
Contourlet Transform ◽  
Fusion Method ◽  
Fusion Algorithm ◽  
Fused Image ◽  
New Interpretation ◽  
Image Fusion Method

Image Fusion is integrating two or more sensors at the same time or at different times of image or videos equenece to generate a new interpretation of this scene. Its main purpose is increasing reliability or image resolution by redueing uncertainty through redundancy of different images.In this paper, a image fusion method based on contourlet transform is presented. The algorithm can fuse corresponding information in different resolutions and directions, which makes the fused image clearer and more abundant in details. Meanwhile, because of the fuzzy logic’s capacity of resolving uncertain problems, it overcomes the drawbacks of traditional fusion algorithm based on contourlet transform, and integrates as much information as possible into the fused image.

Sign in / Sign up

Export Citation Format

Share Document