Image Fusion Techniques: A Review

Mishra, Durgesh Kumar; Palkar, Bhakti

doi:10.5120/ijca2015907084

Cited by 43 publications

(25 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have presented results in visual form for one case and in tabular form for ten cases. Tables 1, 2, 3 and 4 show the quantitative assessment of fused images using four quality parameters: entropy, standard deviation, spatial frequency [2] and universal quality index [15] respectively. Entropy ( E) indicates the amount of information contained in the image.…”

Section: B Fusionmentioning

confidence: 99%

“…Among all the three types, pixel level fusion methods are simple, efficient and they preserve the information content in original images more accurately. Existing pixel level image fusion methods can be divided into three major types: 1) spatial domain techniques, 2) multi-scale decomposition based techniques, 3) sparse representation based techniques Spatial domain techniques which work on the original pixel intensities of images suffer from low contrast or colour distortion [2].The most commonly used multi-scale decomposition based techniques are divided into two types: 1) pyramid based fusion and 2) wavelet transform based fusion. Since the input images are different from each other in various aspects such as content, size, shape and noise, these factors greatly affect the performance of pyramid based fusion methods [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fusion of Multi Modal Lumber Spine Scans using Wavelet and Convolutional Neural Network

Palkar¹,

Mishra²

2019

IJITEE

Self Cite

View full text Add to dashboard Cite

Multiple medical images of different modalities are fused together to generate a new more informative image thereby reducing the treatment planning time of medical practitioners. In recent years, wavelets and deep learning methods have been widely used in various image processing applications. In this study, we present convolutional neural network and wavelet based fusion of MR and CT images of lumber spine to generate a single image which comprises all the important features of MR and CT images. Both CT and MR images are first decomposed into detail and approximate coefficients using wavelets. Then the corresponding detail and approximate coefficients are fused using convolutional neural network framework. Inverse wavelet transform is then used to generate fused image. The experimental results indicate that the proposed approach achieves good performance as compared to conventional methods

show abstract

Section: B Fusionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fusion of Multi Modal Lumber Spine Scans using Wavelet and Convolutional Neural Network

Palkar¹,

Mishra²

2019

IJITEE

Self Cite

View full text Add to dashboard Cite

show abstract

“…As highlighted in [23], image fusion started with simple spatial domain techniques such as averaging or principal component analysis. Almost all classical approaches now involve multiscale decomposition techniques in spatial or spectral domain, such as, for instance, wavelet [26] and Laplacian pyramid decomposition [6], see also [1] for a review.…”

Section: Introductionmentioning

confidence: 99%

Variational Osmosis for Non-Linear Image Fusion

Parisotto

Calatroni

Bugeau

et al. 2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

We propose a new variational model for nonlinear image fusion. Our approach incorporates the osmosis model proposed in and as an energy term in a variational model. The osmosis energy is known to realize visually plausible image data fusion. As a consequence, our method is invariant to multiplicative brightness changes. On the practical side, it requires minimal supervision and parameter tuning and can encode prior information on the structure of the images to be fused. We develop a primaldual algorithm for solving this new image fusion model and we apply the resulting minimisation scheme to multi-modal image fusion for face fusion, colour transfer and some cultural heritage conservation challenges. Visual comparison to state-of-the-art proves the quality and flexibility of our method.

show abstract

“…Researchers have divided the methods of merging images into two categories; the transform domain and the spatial domain [4]. For example, in the field of space, we can refer to the Fast Intensity Hue Saturation (FIHS method), and in the field of transformation, we can refer to the Discrete Wavelet Transform (DWT) method that in this article the Transform domain method is considered [5].…”

Section: Introductionmentioning

confidence: 99%

Image Fusion of Noisy Images Based on Simultaneous Empirical Wavelet Transform

Rahmani¹,

Almasi²,

Saleh³

et al. 2020

View full text Add to dashboard Cite

Fusion image is the method of extracting the relevant information from two or more identical input images into one scene and creating a new image. This method allows the new image to provide comprehensive information about the wand, leading to a visual understanding of the human being. Fusion image application in image processing is an important issue. Applications in many fields such as photography, microscopy, astronomy, medical imaging, satellite imagery, machine vision, biology are monitored. In this study first, an image fusion method, suggested recently based on transform empirical wavelet, was implemented in which coefficients were obtained by processing the input images. Then they were combined by applying the rules. The aim of this study is to investigate the noise effect and to remove the noise in the aforementioned suggested method. First, the noise was added to the images, and the images were decomposed into layers or coefficients. Second, by thresholding the coefficients, the noise was removed. Then the coefficients were combined based on the rules to obtain the final coefficients. In the end, the final coefficients were used to obtain the fused image. The results show that the noise removal of images during image fusion is much better and more effective than denoising before image fusion, and the demonstration of the method is proved by obtaining better results in comparison to some existing methods.

show abstract

Image Fusion Techniques: A Review

Cited by 43 publications

References 51 publications

Fusion of Multi Modal Lumber Spine Scans using Wavelet and Convolutional Neural Network

Fusion of Multi Modal Lumber Spine Scans using Wavelet and Convolutional Neural Network

Variational Osmosis for Non-Linear Image Fusion

Image Fusion of Noisy Images Based on Simultaneous Empirical Wavelet Transform

Contact Info

Product

Resources

About