Gradient-based multi-focus image fusion method using convolution neural network

Zhou, Yang; Yang, Xiaobo; Zhang, Rongzhu; Li, Kai; Anisetti, Marco; Jeon, Gwanggil

doi:10.1016/j.compeleceng.2021.107174

Cited by 8 publications

(5 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, fused images are obtained by applying inverse transform on the modified coefficients [6]. The crucial aspect is deciding the fusion rule, which can be the average, weighted average, or maximum rule.…”

Section: Satellite Panchromatic (Pan) Images Obtained From Landsat En...mentioning

confidence: 99%

See 1 more Smart Citation

Estimation of spectral similarities utilizing segmented regions' probability distribution in the block‐optimized pan‐sharpened image for material classification

V. Karki,

et al. 2024

Luminescence

View full text Add to dashboard Cite

Pan‐sharpening is an image fusion approach that combines the spectral information in multispectral (MS) images with the spatial properties of PAN (Panchromatic) images. This vital technique is used in categorization, detection, and other remote sensing applications. In the first step, the article focuses on increasing the finer spatial details in the MS image with PAN images using two levels of fusion without causing spectral deterioration. The suggested fusion method efficiently utilizes image transformation techniques and spatial domain image fusion methods. The luminance component of MS images typically contains spatial features that are not as detailed as the PAN images. A multiscale transform is applied to the intensity/luminance component and PAN image to introduce features into the intensity component. In the first level of processing, coefficients obtained from the non‐subsampled contourlet transform are subjected to particle swarm optimization weighted block‐based fusion. The second level of fusion is carried out using the concept of spatial frequency to reduce spectral distortion. Numerous reference and non‐reference parameters are used to evaluate the sharpened image's quality. In the next step, the article focuses on designing an evaluation metric for analysing spectral distortion based on the Bhattacharyya coefficient and distance. The Bhattacharyya coefficient and distance are calculated for each segmented region to assess the sharpened images' quality. Spectral degradation analysis using proposed techniques can also be useful for analysing materials in the segmented regions. The research findings demonstrate that the spatial features of fused images obtained from the proposed technique increased with the least spectral degradation.

show abstract

Section: Satellite Panchromatic (Pan) Images Obtained From Landsat En...mentioning

confidence: 99%

“…In transform‐based fusion methods, the decomposed coefficients are combined based on certain fusion rules. Finally, fused images are obtained by applying inverse transform on the modified coefficients [6]. The crucial aspect is deciding the fusion rule, which can be the average, weighted average, or maximum rule.…”

Section: Introductionmentioning

confidence: 99%

Estimation of spectral similarities utilizing segmented regions' probability distribution in the block‐optimized pan‐sharpened image for material classification

V. Karki,

et al. 2024

Luminescence

View full text Add to dashboard Cite

show abstract

“…(Zhou, Yang. 2021) [35]A gradient-based approach is introduced to generate an all-in-focus image using a convolution neural network (CNN). The method inputs original images and gradient images into five models, generates initial focus score maps, and merges them to form a fused image.…”

Section: Gradient Domainmentioning

confidence: 99%

Exploring Types of Multi-Focus Image Fusion

Ghazal,

Majjed Dahl

2023

IRJIET

View full text Add to dashboard Cite

This paper explains methods. Fusion of multiplefocus images can actually take care of the profundity of field issue in optical focal point regions, the blurred picture appears strange due to the high frequency degradation Information. Most often, the camera is to blame for this. The absence of a deep field is caused by optics in the cameras. The picture becomes sharper as a result. Only in particular locations for a comprehensive focal length image, Fusion of multiple-focus images primary objective is to solve a problem with depth of field cameras. By blending at least two to some degree centred pictures into a solitary totally centred picture, Combination of various centre pictures can tackle the optical focal point's profundity of field issue.

show abstract

“…Gradient-based fusion techniques concentrate more on edges than on texture with the given inputs in which sparse inputs are not accepted directly [41]. Additionally, edge efficiency is not more accurate with more interruption at all levels of methodology [42,43]. The shortcomings of contourlet transformation are time-consuming, shift-invariant, and cannot be applied to complex structures.…”

Section: Comparison Of Cnn-based Image Fusion With Traditional and Co...mentioning

confidence: 99%

Fusion of SAR and optical images using pixel-based CNN

Bandi¹,

Anbarasan²,

Sheela³

2022

NNW

View full text Add to dashboard Cite

Sensors of different wavelengths in remote sensing field capture data. Each and every sensor has its own capabilities and limitations. Synthetic aperture radar (SAR) collects data that has a high spatial and radiometric resolution. The optical remote sensors capture images with good spectral information. Fused images from these sensors will have high information when implemented with a better algorithm resulting in the proper collection of data to predict weather forecasting, soil exploration, and crop classification. This work encompasses a fusion of optical and radar data of Sentinel series satellites using a deep learning-based convolutional neural network (CNN). The three-fold work of the image fusion approach is performed in CNN as layered architecture covering the image transform in the convolutional layer, followed by the activity level measurement in the max pooling layer. Finally, the decision-making is performed in the fully connected layer. The objective of the work is to show that the proposed deep learning-based CNN fusion approach overcomes some of the difficulties in the traditional image fusion approaches. To show the performance of the CNN-based image fusion, a good number of image quality assessment metrics are analyzed. The consequences demonstrate that the integration of spatial and spectral information is numerically evident in the output image and has high robustness. Finally, the objective assessment results outperform the state-of-the-art fusion methodologies.

show abstract

Gradient-based multi-focus image fusion method using convolution neural network

Cited by 8 publications

References 23 publications

Estimation of spectral similarities utilizing segmented regions' probability distribution in the block‐optimized pan‐sharpened image for material classification

Estimation of spectral similarities utilizing segmented regions' probability distribution in the block‐optimized pan‐sharpened image for material classification

Exploring Types of Multi-Focus Image Fusion

Fusion of SAR and optical images using pixel-based CNN

Contact Info

Product

Resources

About