Academia.eduAcademia.edu

Outline

Title
Abstract
Key Takeaways
Figures
Introduction
Related Works
Proposed Method
Subjective Analysis of Results
Objective Analysis of Results
Conclusion
References
All Topics
Computer Science
Computer Vision

Discrete Wavelet Transform-Based Image Fusion in Remote Sensing

Profile image of Swati JunejaSwati Juneja

2023, Lecture notes in networks and systems

https://doi.org/10.1007/978-981-19-7982-8_49
visibility

…

description

10 pages

link

1 file

Abstract

Nowadays the result of infrared and visible image fusion has been utilized in significant applications like military, surveillance, remote sensing and medical imaging applications. Discrete wavelet transform based image fusion using unsharp masking is presented. DWT is used for decomposing input images (infrared, visible). Approximation and detailed coefficients are generated. For improving contrast unsharp masking has been applied on approximation coefficients. Then for merging approximation coefficients produced after unsharp masking average fusion rule is used. The rule that is used for merging detailed coefficients is max fusion rule. Finally, IDWT is used for generating a fused image. The result produced using the proposed fusion method is providing good contrast and also giving better performance results in reference to mean, entropy and standard deviation when compared with existing techniques.

Key takeaways
sparkles

AI

  1. The proposed method improves image fusion quality using discrete wavelet transform (DWT) and unsharp masking.
  2. Unsharp masking enhances contrast on approximation coefficients to retain edge and texture information.
  3. Average and max fusion rules merge approximation and detailed coefficients, respectively, in DWT-based fusion.
  4. The method significantly outperforms existing techniques in mean, entropy, and standard deviation metrics.
  5. Image fusion is crucial for applications in military, surveillance, remote sensing, and medical imaging.
Figures (14)
Fig. 1 Block diagram for the proposed method
Fig. 1 Block diagram for the proposed method
Fig. 2 3 x 3 sharpen filter 1. The process for Implementation of fusion algorithm in spatial domain using PCA, Histogram Equalization, ny 2; ee i, ce a ee, | ee, ae oe
Fig. 2 3 x 3 sharpen filter 1. The process for Implementation of fusion algorithm in spatial domain using PCA, Histogram Equalization, ny 2; ee i, ce a ee, | ee, ae oe
Fig. 3 3 x 3 sharpen filter 2. Fig. 4 shows the fused results of "Single person image", where Fig. 4 (a) shows an Infrared image, Fig. 4 (b) shows a visible image, Fig. 4 (c) shows sharpen fused-image which ble images are of "Forest image" is shown in Fig. 6. The dataset used for the experiment is TNO image fusion dataset. The experiment is conducted using MATLAB software. For doing the experiment the source images uti- lized are, first set of input infrared and visible images are of "Single person image" is shown in Fig. 4. The second set of input infrared and visible images are of "Two-person image" is shown in Fig. 5. And the third set of input infrared and vis- ible images are of "Forest image" is shown in Fig. 6.
Fig. 3 3 x 3 sharpen filter 2. Fig. 4 shows the fused results of "Single person image", where Fig. 4 (a) shows an Infrared image, Fig. 4 (b) shows a visible image, Fig. 4 (c) shows sharpen fused-image which ble images are of "Forest image" is shown in Fig. 6. The dataset used for the experiment is TNO image fusion dataset. The experiment is conducted using MATLAB software. For doing the experiment the source images uti- lized are, first set of input infrared and visible images are of "Single person image" is shown in Fig. 4. The second set of input infrared and visible images are of "Two-person image" is shown in Fig. 5. And the third set of input infrared and vis- ible images are of "Forest image" is shown in Fig. 6.
The process for Implementation of fusion algorithm in spatial domain using Histogram Equalization, Sharpen infrared source image and visible source image are scaled into 256 <x 256 images. Principle Component Analysis (PCA) has been applied to the scaled infrared image and visible image. PCA is mainly used for dimensional reduc- tion. Histogram equalization is applied to the result of PCA of visible image. Histogram equalization is an enhance- ment technique that improves contrast of the image. Sharpen filter is applied to result of PCA of infrared image. Weighted average Fusion has been applied to results of his- togram equalization and sharpen filter. The 3 x 3 sharpen filter used in above method is shown in Fig. 3.
The process for Implementation of fusion algorithm in spatial domain using Histogram Equalization, Sharpen infrared source image and visible source image are scaled into 256 <x 256 images. Principle Component Analysis (PCA) has been applied to the scaled infrared image and visible image. PCA is mainly used for dimensional reduc- tion. Histogram equalization is applied to the result of PCA of visible image. Histogram equalization is an enhance- ment technique that improves contrast of the image. Sharpen filter is applied to result of PCA of infrared image. Weighted average Fusion has been applied to results of his- togram equalization and sharpen filter. The 3 x 3 sharpen filter used in above method is shown in Fig. 3.
average fusion rule is applied in spatial domain due to that low brightness, low contrast and less quality fused images are produced. is obtained after Implementation of DWT based fusion algorithm using sharpen filter, Fig. 4 (d) shows PCAI fused-image which is obtained after Implementation of fusion algorithm in spatial domain using PCA, Histogram Equalization, Sharpen filter and Weighted average fusion tule, Fig. 4 (e) shows PCA2 fused-image which is obtained after Implementation of fusion algorithm in spatial domain using Histogram Equalization, Sharpen filter, PCA and Weighted average fusion rule and Fig. 4 (f) shows the pro- posed fused-image of "Single person image". Similarly Fig. 5 shows the fused results of "Two-person image", where Fig. 5 (a) shows an Infrared image, Fig. 5 (b) shows a visible image, Fig. 5 (c) shows sharpen fused-im- age which is ob fusion algorithm using sharpen filter, Fig. 5 (d) shows PCA1 fused -image w ained after Implementation of DWT based hich is obtained after Implementation of fusion algorithm in spatial domain using PCA, Histogram Equa rule, after using Weig ization, S Fig. 5 (e) s mplemen posed harpen filter and Weighted average fusion hows PCA2 fused-image which is obtained ation of fusion algorithm in spatial domain Histogram Equalization, Sharpen filter, PCA and hted average fusion rule and Fig. 5 (f) shows the pro- fused-image of "Two-person image".
average fusion rule is applied in spatial domain due to that low brightness, low contrast and less quality fused images are produced. is obtained after Implementation of DWT based fusion algorithm using sharpen filter, Fig. 4 (d) shows PCAI fused-image which is obtained after Implementation of fusion algorithm in spatial domain using PCA, Histogram Equalization, Sharpen filter and Weighted average fusion tule, Fig. 4 (e) shows PCA2 fused-image which is obtained after Implementation of fusion algorithm in spatial domain using Histogram Equalization, Sharpen filter, PCA and Weighted average fusion rule and Fig. 4 (f) shows the pro- posed fused-image of "Single person image". Similarly Fig. 5 shows the fused results of "Two-person image", where Fig. 5 (a) shows an Infrared image, Fig. 5 (b) shows a visible image, Fig. 5 (c) shows sharpen fused-im- age which is ob fusion algorithm using sharpen filter, Fig. 5 (d) shows PCA1 fused -image w ained after Implementation of DWT based hich is obtained after Implementation of fusion algorithm in spatial domain using PCA, Histogram Equa rule, after using Weig ization, S Fig. 5 (e) s mplemen posed harpen filter and Weighted average fusion hows PCA2 fused-image which is obtained ation of fusion algorithm in spatial domain Histogram Equalization, Sharpen filter, PCA and hted average fusion rule and Fig. 5 (f) shows the pro- fused-image of "Two-person image".
Fused-image obtained using the proposed method is providing good contrast, texture, and edge information because of that person, house, board and tree details are clearly seen in Fig. 5 (f).
Fused-image obtained using the proposed method is providing good contrast, texture, and edge information because of that person, house, board and tree details are clearly seen in Fig. 5 (f).
Table 1 Comparison results for "Single person image" Table 2 Comparison results for "Two-person image"
Table 1 Comparison results for "Single person image" Table 2 Comparison results for "Two-person image"
Table 3 Comparison results for "Forest image"
Table 3 Comparison results for "Forest image"
Table 4 Comparison of average results of different fusion methods
Table 4 Comparison of average results of different fusion methods
Fig. 8 Different fusion methods comparison with reference to Entropy Fig. 7 Different fusion methods comparison with reference to Mean
Fig. 8 Different fusion methods comparison with reference to Entropy Fig. 7 Different fusion methods comparison with reference to Mean
Fig. 9 Different fusion methods comparison with reference to Standard deviation
Fig. 9 Different fusion methods comparison with reference to Standard deviation
Fig. 10 Different fusion methods comparison with reference to Mean gradient
Fig. 10 Different fusion methods comparison with reference to Mean gradient

Related papers

Image fusion using multi-decomposition levels of discrete wavelet transform
Nabil Ismail

International Conference on Visual Information Engineering (VIE 2003). Ideas, Applications, Experience, 2003

Many researchers are concerning with using powerful image processing tools to achieve high quality images for their applications. Recently, great interest has been arisen on using wavelet transforms [I-IO] to analysis multi-resolution images and to fuse remote sensing images. Image fusion especially in remote sensing applications is one of the fields that growing continuously. Many methods have been proposed to fuse panchromatic and multi-spectral images [ I-71. This work presents a proposed scheme to fuse the Landsat-7 low-resolution (30m) multi-spectral images and its high-resolution (Ism) panchromatic images. The proposed image fusion method is based on Two Dimensional Discrete Wavelet Transform (2D-DWT). The method aims to fuse two images in order to produce high resolution (15m) multi-spectral image. It also presents a comparison between the implemented 2D-DWT method and other conventional methods of image fusion using correlation between the output image and the two input images to ascertain the best possible technique that can result in better results of multi-sensor image fusion. The output image of the 2D-DWT technique contains 86.6 % of spectral content of the multi-spectral image and 97.08 % of the spatial content of panchromatic image.

View PDFchevron_right
An Efficient Image Fusion Method For Fusion of Low Resolution Infrared And Visual Image.
Ijesrt Journal

International Journal of Engineering Sciences & Research Technology, 2012

Due to the fast development of digital image processing the growth of feature extraction of images which leads to the development of image fusion. The process of co retaining salient features from each image with extended information content is known as image fusion, wherein the resultant fused image will be more informative and complete than any of the input ima fusion are spatial fusion and transform fusion. In this paper I proposed an image fusion method for fusion of low resolution infrared camera image with visual image, the focus of this paper is to propose an efficient algorithm fuse a visual image and a corresponding low resolution IR image such a concealed weapon detection application. Discrete wavelet transform plays a vital role in image fusion since it minimizes structural distortions among the various other transforms. Lack of shift invariance, poor directional selectivity and the absence of phase information are the drawbacks of discrete wavelet transform. These drawbacks are overcome by dual tree complex wavelet transform. The fused image obtained by the proposed algorit incorporate any single image. The feasibility of the proposed fusion technique is tested and demonstrated by some experimental results in form of visual, mathematical output and various fusion assess noise ratio (SNR), peak signal to noise ratio (PSNR), root mean square error (RMSE) and correlation coefficient. Those outputs are compared with various popular image fusion techniques.

View PDFchevron_right
Remotely Sensed Image Fusion Using The Wavelet Transform
Fernando Ventura

Image fusion aims at the integration of complementary information from multisensor data so that the new images are more suitable for computerprocessing tasks and visual interpretation. This paper presents a variation of an image fusion method that uses a multi-resolution analysis based upon the wavelet transform. In order to evaluate its performance the proposed method is compared with the IHS and another wavelet method.

View PDFchevron_right
Wavelet Based Image Fusion
International Journal of Scientific Research in Science and Technology IJSRST

Extracting more information from multi-source images is an attractive thing in remotely sensed image processing, which is recently called image fusion. In the paper, the image fusion algorithm based on wavelet transform is proposed to improve the geometric resolution of the images, in which two images to be processed are firstly decomposed into sub images with different frequency, and then the information fusion is performed using these images under certain criterion, and finally these sub-images are reconstructed into the result image with plentiful information.

View PDFchevron_right
Performance Analysis of Image Fusion for Different Wavelet Families
Chandrasekhar Savalam

2016 International Conference on Innovations in information Embedded and Communication Systems (ICIIECS’16, 2016

In Image processing it requires high spatial and spectral resolution in a single image at several situations. However, the instruments are not capable of providing an image of good resolution. So, one of the possible solution is IMAGE FUSION. It is a process of combining the relevant information from a set of images into a single image which contains more informative and resolution than input images. Image fusion increases the quality of image. Several applications of image fusion such as medical diagnosis, remote sensing, military and security for surveillance areas etc., It is not possible to develop a universal technique for all applications. Hence a specific image fusion technique is employed for specific application. Now, image fusion techniques such as filtering methods and DWT technique are employed in medical application. The performance analysis of proposed methods is obtained and compared through various quality evaluation parameters.

View PDFchevron_right
Fusion Algorithm for Images based on Discrete Multi-wavelet Transform
IOSR Journals
View PDFchevron_right
A Novel Image Fusion Method Based on Wavelet Packet Transform
syfe saad

A novel image fusion method based on discrete wavelet packet transform (DWPT) is proposed. First, after the registration of multi-source sensor images, the obtained images are decomposed into several sub-images of different frequency bands by using wavelet packet transform. Second, aiming at the characteristic of the sub-images after decompositions, fusion rules based on local region are chosen to fuse the coefficients of the sub-images, and a serial of fusion sub-images are obtained. Finally, the fusion image can be obtained by inverse discrete wavelet packet transform (IDWPT). By means of designing simulation experiments using visible and infrared image, the image fusion method based on wavelet packet transform is compared qualitatively and quantitatively with other five kinds of image fusion methods including weighted average, selecting maximum pixel gray value, selecting minimum pixel value, Laplacian pyramid transform and wavelet transform. Lots of experiments and comparisons with other fusion methods show that the effectiveness and superiority of image fusion method based on wavelet packet transform.

View PDFchevron_right
Advanced discrete wavelet transform fusion algorithm and its optimization by using the metric of image quality index
Bruce C Hansen

Optical Engineering, 2005

Of the many image fusion methods, the discrete wavelet transform (DWT) and various pyramids (e.g., the Laplacian pyramid) are among the most common and effective. For quantitative evaluation of the quality of fused imagery, the root mean square error (RMSE) is the most reasonable measure of quality if a "ground truth" image is available; otherwise, the entropy, spatial frequency, or image quality index (0) can be calculated and evaluated. Here, an advanced discrete wavelet transform (aDWT) method that incorporates principal component analysis (PCA) and morphological processing into a regular DWT fusion algorithm is presented. Specifically, a principle vector is derived from two ' approximation co-input images and then applied to two of the images efficients at the highest DWT transform scale. For the detail coefficients at each transform scale, the larger absolute values are chosen and subjected to a neighborhood morphological processing procedure that serves to verify the selected pixels by using a "filling" and "cleaning" operation. Furthermore, the aDWT has two adjustable parameters-the number of DWT decomposition levels and the length of the selected wavelet that cleterminately affect the fusion result. An iterative fusion process that was optimized with the established metric-IQI-is then implemented. Experimental results tested on four types of inhomogeneous imagery show that the iterative aDWT achieves the best fusion compared to the pyramid or the DWT methods judged on both the IQI metric and visual inspection.

View PDFchevron_right
Thermal and Visible Satellite Image Fusion Using Wavelet in Remote Sensing and Satellite Image Processing
Majid Kiavarz

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017

Multimodal remote sensing approach is based on merging different data in different portions of electromagnetic radiation that improves the accuracy in satellite image processing and interpretations. Remote Sensing Visible and thermal infrared bands independently contain valuable spatial and spectral information. Visible bands make enough information spatially and thermal makes more different radiometric and spectral information than visible. However low spatial resolution is the most important limitation in thermal infrared bands. Using satellite image fusion, it is possible to merge them as a single thermal image that contains high spectral and spatial information at the same time. The aim of this study is a performance assessment of thermal and visible image fusion quantitatively and qualitatively with wavelet transform and different filters. In this research, wavelet algorithm (Haar) and different decomposition filters (mean.linear,ma,min and rand) for thermal and panchromatic bands of Landast8 Satellite were applied as shortwave and longwave fusion method. Finally, quality assessment has been done with quantitative and qualitative approaches. Quantitative parameters such as Entropy, Standard Deviation, Cross Correlation, Q Factor and Mutual Information were used. For thermal and visible image fusion accuracy assessment, all parameters (quantitative and qualitative) must be analysed with respect to each other. Among all relevant statistical factors, correlation has the most meaningful result and similarity to the qualitative assessment. Results showed that mean and linear filters make better fused images against the other filters in Haar algorithm. Linear and mean filters have same performance and there is not any difference between their qualitative and quantitative results.

View PDFchevron_right
A wavelet-based image fusion tutorial
Gonzalo Pajares

Pattern Recognition, 2004

The objective of image fusion is to combine information from multiple images of the same scene. The result of image fusion is a new image which is more suitable for human and machine perception or further image-processing tasks such as segmentation, feature extraction and object recognition. Di erent fusion methods have been proposed in literature, including multiresolution analysis. This paper is an image fusion tutorial based on wavelet decomposition, i.e. a multiresolution image fusion approach. We can fuse images with the same or di erent resolution level, i.e. range sensing, visual CCD, infrared, thermal or medical. The tutorial performs a synthesis between the multiscale-decomposition-based image approach (Proc. IEEE 87 (1999) 1315), the ARSIS concept (Photogramm. Eng. Remote Sensing 66 (1) (2000) 49) and a multisensor scheme (Graphical Models Image Process. 57 (3) (1995) 235). Some image fusion examples illustrate the proposed fusion approach. A comparative analysis is carried out against classical existing strategies, including those of multiresolution.

View PDFchevron_right

References (23)

  1. Xu, F., Zeng, D., Zhang, J., Zheng, Z., Wei, F., Wang, T. "Detail enhancement of blurred infrared images based on frequency extrap- olation", Infrared Physics & Technology, 76, pp. 560-568, 2016. https://doi.org/10.1016/j.infrared.2016.04.008
  2. Liu, Z., Feng, Y., Zhang, Y., Li, X. "A fusion algorithm for infrared and visible images based on RDU-PCNN and ICA-bases in NSST domain", Infrared Physics & Technology, 79, pp. 183-190, 2016. https://doi.org/10.1016/j.infrared.2016.10.015
  3. Ma, J., Ma, Y., Li, C. "Infrared and visible image fusion methods and applications: A survey", Information Fusion, 45, pp. 153-178, 2019. https://doi.org/10.1016/j.inffus.2018.02.004
  4. Muller, A. C., Narayanan, S. "Cognitively-engineered multisensor image fusion for military applications", Information Fusion, 10(2), pp. 137-149, 2009. https://doi.org/10.1016/j.inffus.2008.08.008
  5. Feng, Z. J., Zhang, X. L., Yuan, L. Y., Wang, J. N. "Infrared Target Detection and Location for Visual Surveillance Using Fusion Scheme of Visible and Infrared Images", Mathematical Problems in Engineering, 2013, Article ID: 720979, 2013. https://doi.org/10.1155/2013/720979
  6. Chang, X., Jiao, L., Liu, F., Xin, F. "Multicontourlet-Based Adaptive Fusion of Infrared and Visible Remote Sensing Images", IEEE Geoscience and Remote Sensing Letters, 7(3), pp. 549-553, 2010. https://doi.org/10.1109/LGRS.2010.2041323
  7. Hanna, B. V., Gorbach, A. M., Gage, F. A., Pinto, P. A., Silva, J. S., Gilfillan, L. G., Kirk, A. D., Elster, E. A. "Intraoperative Assessment of Critical Biliary Structures with Visible Range/ Infrared Image Fusion", Journal of the American College of Surgeons, 206(6), pp. 1227-1231, 2008. https://doi.org/10.1016/j.jamcollsurg.2007.10.012
  8. May, K. A., Georgeson, M. A. "Blurred edges look faint, and faint edges look sharp: The effect of a gradient threshold in a multi-scale edge coding model", Vision Research, 47(13), pp. 1705-1720, 2007. https://doi.org/10.1016/j.visres.2007.02.012
  9. Li, H., Liu, L., Huang, W., Yue, C. "An improved fusion algorithm for infrared and visible images based on multi-scale transform", Infrared Physics and Technology, 74, pp. 28-37, 2016. https://doi.org/10.1016/j.infrared.2015.11.002
  10. Zhan, L., Zhuang, Y., Huang, L. "Infrared and Visible Images Fusion Method Based On Discrete Wavelet Transform", Journal of Computers, 28(2), pp. 57-71, 2017. https://doi.org/10.3966/199115592017042802005
  11. Zhou, Z., Lin, J., Jin, W., Peng, Z., Pinglv, Y. "Image fusion by com- bining SWT and variational model", In: 2011 4th International Congress on Image and Signal Processing, Shanghai, China, 2011, pp. 1907-1910. https://doi.org/10.1109/CISP.2011.6100633
  12. Paramanandham, N., Rajendiran, K. "Infrared and visible image fusion using discrete cosine transform and swarm intelligence for surveillance applications", Infrared Physics & Technology, 88, pp. 13-22, 2018. https://doi.org/10.1016/j.infrared.2017.11.006
  13. Liu, Z., Feng, Y., Chen, H., Jaio, L. "A fusion algorithm for infrared and visible based on guided filtering and phase congruency in NSST domain", Optics and Lasers in Engineering, 97, pp. 71-77, 2017. https://doi.org/10.1016/j.optlaseng.2017.05.007
  14. Li, H., Manjunath, B. S., Mitra, S. K. "Multisensor Image Fusion Using the Wavelet Transform", Graphical Models and Image Processing, 57(3), pp. 235-245, 1995. https://doi.org/10.1006/gmip.1995.1022
  15. Fan, L., Zhang, Y., Zhou, Z., Semanek, D. P., Wang, S., Wu, L. "An Improved Image Fusion Algorithm Based on Wavelet Decomposition", Journal of Convergence Information Technology, 5(10), pp. 15-21, 2010. [online] Available at: http://citeseerx.ist.psu. edu/viewdoc/download;jsessionid=511E898EA66A614FE4487D- 510 483325A?d oi=10.1.1. 501.9698& r e p = r e p1& t y p e = p d f [Accessed: 08 June 2019]
  16. Godse, D. A., Bormane, D. S. "Wavelet based image fusion using pixel based maximum selection rule", International Journal of Engineering Science and Technology, 3(7), pp. 5572-5577, 2011. [online] Available at: https://www.researchgate.net/pro- file/D_Bormane/publication/266016648_WAVELET_BASED_ IMAGE_FUSION_USING_PIXEL_BASED_MAXIMUM_ SELECTION_ RU LE/ li n ks/552d 23360cf 21acb092137 bb/ WAVELET-BASED-IMAGE-FUSION-USING-PIXEL-BASED- MAXIMUM-SELECTION-RULE.pdf [Accessed: 11 June 2019]
  17. Xu, F., Su, S. "An Enhanced Infrared and Visible Image Fusion Method Based on Wavelet Transform", In: 2013 5th International Conference on Intelligent Human-Machine Systems and Cybernetics, Hangzhou, China, 2013, pp. 453-456. https://doi.org/10.1109/IHMSC.2013.255
  18. Zhou, Z. H., Tan, M. "Infrared Image and Visible Image Fusion Based on Wavelet Transform", Advanced Materials Research, 756- 759, pp. 2850-2856, 2013. https://doi.org/10.4028/www.scientific.net/AMR.756-759.2850
  19. Vijayarajan, R., Muttan, S. "Discrete wavelet transform based principal component averaging fusion for medical images", AEU-International Journal of Electronics and Communications, 69(6), pp. 896-902, 2015. https://doi.org/10.1016/j.aeue.2015.02.007
  20. Han, X., Zhang, L. L., Du, L. Y., Huan, K. W., Shi, X. G. "Fusion of infrared and visible images based on discrete wavelet transform", In: Selected Papers of the Photoelectronic Technology Committee Conferences, Hefei, Suzhou, and Harbin, China, Vol. 9795, 2015, Article number: 979510. https://doi.org/10.1117/12.2216054
  21. Habeeb, N. J., Omran, S. H., Radih, D. A. "Contrast Enhancement for Image Using Image Fusion and Sharpen Filters", In: 2018 International Conference on Advanced Science and Engineering (ICOASE), Duhok, Iraq, 2018, pp. 64-69. https://doi.org/10.1109/ICOASE.2018.8548898
  22. Habeeb, N. J., Al-Taei, A., Fadhil-Ibrahim, M. "Contrast Enhancement for Multi-Modality Image Fusion in Spatial Domain", Journal of Theoretical and Applied Information Technology, 96(20), pp. 6926-6936, 2018. [online] Available at: https://www.semanticscholar.org/paper/CONTRAST-
  23. E N H A N C E M E N T-F O R-M U LT I M O DA L I T Y-I M AG E - FUSION-Habeeb-Al-Taei/355a748c9d7f5adf8f87c9e93092adaf5 b609b0b [Accessed: 13 September 2019]

Related papers

Image Fusion by Shift Invariant Discrete Wavelet Transform for Remote Sensing Applications
Abdalrahman Qubaa

2020

The fusion technique of the spectral bands captured by the sensors carried onboard satellites is one digital processing method for extracting information and detecting ground targets. Image fusion also known as pan-sharpening-provides the necessary means to combine many images into a single composite image that is suitable in visual interpretation processes or in digital interpretation. The principal objective of this study is to find the best suitable algorithms for obtaining integrative information from several separate images in one combined image. Based on the above, a special software system was designed to implement and test the fusion methods used in remote sensing applications by selecting and applying a Shift Invariant Wavelet Transform (SIWT) method to the remote sensing images and then comparing with four other different image fusion algorithms. Two objective mathematical methods were also used to measure the amount of shared information obtained in the images resulting f...

View PDFchevron_right
Satellite Image Fusion Technique using Integration of IHS Transform and Contrast based Wavelet Packets
dheepa thiyagu

The development of new imaging methods in various fields arise the need of meaningful combination of all available image datasets. Image fusion is the process of integrating complementary information from multiple image sensor data to create a fused image output. The new image generated should contain a more accurate description of the scene than any of the individual source images and is more suitable for human visual and machine perception or further image processing and analysis tasks. This technique is used in satellite remote sensor images to fuse high resolution panchromatic (PAN) image with the low resolution multispectral (MS) image to form a single high resolution multispectral image. Among the existing fusion techniques, wavelet based methods have proved to produce improved results. This paper proposes a novel method to fuse PAN image and MS image by integrating Contrast based Discrete Wavelet Packet Transform (DWPT) and Intensity Hue Saturation (IHS) technique. Firstly, the advantages of using DWPT over DWT are given in brief. Then the proposed algorithm is explained. Finally, its performance is evaluated using various quality assessment metrics which shows that the proposed method is superior to the other existing methods.

View PDFchevron_right
Hybrid Infrared and Visible Image Fusion using DWT, LWT and SWT
IJIRMPS International Journal

IJIRMPS, 2020

To create a quality output image by fusing, the features from both infrared and visible image for target detection in military applications. Image fusion is the amalgamation of two or more images of the same scene taken at different times, different focal length or at different sensors. The proposed work includes hybrid image fusion in transform domain by the combination of DWT (Discrete Wavelet Transform) and LWT (Lifting Wavelet Transform) and SWT (Shearlet Wavelet Transform). The source images are first decomposed using DWT and the low pass information is further decomposed by LWT or SWT and fused by weighted sum method and the high pass information is fused by max method. The performance evaluation metrics such as PSNR, Edge association, Entropy, Root Mean squared error, Correlation coefficient, Structural Similarity Index are used to compare the fused result of DWT, LWT, SWT and hybrid combination of DWT, LWT and DWT, SWT both quantitatively and qualitatively. Among the results hybrid combination of DWT and LWT performs better.

View PDFchevron_right
Evaluation of Satellite Image Fusion Using Wavelet Transform
oguz gungor

2004

This paper addresses the principles, implementation and evaluation of wavelet transformation based image fusion. 2-D discrete wavelet transformation is presented concisely to facility the understanding of the wavelet based image fusion method. To best retain the quality of the input images, we propose a strategy that minimizes the necessary resampling operations to limit potential image quality deterioration. In the proposed fusion approach, the wavelet coefficients for the fused images are selected based on the suggested maximum magnitude criterion. To evaluate the outcome images, other popular fusion methods including principal component transformation, Brovey and multiplicative transformation approaches are applied to the same images and the results are compared to the ones from the wavelet based approach. Fusion results are evaluated both visually and numerically. A quality matrix is calculated based on the correlation coefficients between the fused image and the original image....

View PDFchevron_right
Performance of Spatial Frequency Discrete Wavelet Transform Based Remote Sensing Image Fusion Algorithm
Ms. Jinju Joy LMCST

International Journal of Recent Technology and Engineering (IJRTE), 2019

The high sensor cost for producing images with superior spectral and spatial qualities in remote sensing application have led to the development of image fusion algorithms. Image fusion technique combines a Panchromatic image and a Multispectral image with an aim to produce images with excellent spatial and spectral qualities. One of the major factors that affect the performance of any image fusion algorithm is the capability of the algorithm in extracting the spatial and spectral data from the respective images and how effective the so extracted information is blended together. One of the recently developed spectral domain algorithm to perform image fusion in remote sensing applications is Spatial Frequency Discrete Wavelet Transform abbreviated as SFDWT. The excellence of SFDWT image fusion algorithm is already proven better than the prevailing algorithms based on Discrete Wavelet Transform. This paper is coined with an eye to realize the performance of SFDWT based image fusion al...

View PDFchevron_right

Related topics

  • Artificial Intelligence
  • Computer Vision
  • Image fusion
    • 580 California St., Suite 400
    San Francisco, CA, 94104
    © 2025 Academia. All rights reserved