Image fusion via feature residual and statistical matching

Lijuan, Wang; Han, Jing; Zhang, Yi; Bai, Lianfa

doi:10.1049/iet-cvi.2015.0280

Cited by 19 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the feature maps are also constructed by the combined statistical, saliency and structural approaches to improve the fusion performance. The combination of mean, standard deviation, entropy and gradient were used in [72], entropy, visibility and local contrast measures in [73], local mean and local energy for the fusion of low and high frequency coefficients in Discrete wavelet packet transform domain in [74], PC and FD combination is used to define the fusion rule for multi-sensor fusion for night vision applications by [75] and energy, variance combination in [76] in DCT domain for multi-sensor fusion. Geometric structural features such as attribute angle, length, distance etc.…”

Section: E Structural Approach For Feature Extractionmentioning

confidence: 99%

A Compendious Analysis of Feature-Extraction Algorithms to Frame Fusion Rules

Kumari¹

2022

IJCDS

View full text Add to dashboard Cite

Advancement in sensor technology provides the complete information captured by multiple sensors. To reduce the eye strain and workload from analyzing the scene with multiple images, the information is combined into a single image by the process called image fusion. In this paper, a compendious analysis of feature-extraction based fusion algorithms that define an appropriate fusion rule is reviewed. A state-of-art classification of feature-based fusion schemes is carried out and the extracted feature maps are presented. The qualitative analysis for different fusion methods are illustrated and compared. The quantitative fusion metrics are grouped as contrast, information, edge and visual based metrics and are evaluated. Finally, the conclusion and future directions are briefed out.

show abstract

Section: E Structural Approach For Feature Extractionmentioning

confidence: 99%

A Compendious Analysis of Feature-Extraction Algorithms to Frame Fusion Rules

Kumari¹

2022

IJCDS

View full text Add to dashboard Cite

show abstract

“…The fusion rule for combining the information decides the clarity of the final fused image. The local residual features (FR) (Wang et al, 2016) of the two source images are used for computing weights. The method suffers from high computational time as the features are extracted at each pixel considering the features about the centered region and the surrounding region.…”

Section: Combining the Enhanced Dark And Bright Regionsmentioning

confidence: 99%

A two-stage processing approach for contrast intensified image fusion

Teku

Rao

Inty

2020

WJE

View full text Add to dashboard Cite

Purpose Integrating complementary information with high-quality visual perception is essential in infrared and visible image fusion. Contrast-enhanced fusion required for target detection in military, navigation and surveillance applications, where visible images are captured at low-light conditions, is a challenging task. This paper aims to focus on the enhancement of poorly illuminated low-light images through decomposition prior to fusion, to provide high visual quality. Design/methodology/approach In this paper, a two-step process is implemented to improve the visual quality. First, the low-light visible image is decomposed to dark and bright image components. The decomposition is accomplished based on the selection of a threshold using Renyi’s entropy maximization. The decomposed dark and bright images are intensified with the stochastic resonance (SR) model. Second, texture information-based weighted average scheme for low-frequency coefficients and select maximum precept for high-frequency coefficients are used in the discrete wavelet transform (DWT) domain. Findings Simulations in MATLAB were carried out on various test images. The qualitative and quantitative evaluations of the proposed method show improvement in edge-based and information-based metrics compared to several existing fusion techniques. Originality/value In this work, a high-contrast, edge-preserved and brightness-improved image is obtained by the processing steps considered in this work to get good visual quality.

show abstract

“…Wavelet transform : Wavelet transform has been widely used in image editing, such as image denoising [ZY11] and image fusion [WHZB16]. Image fusion techniques based on multi‐scale wavelet transform also have been proposed, which improve the fusion performance, for example, Li et al [LLYZ16] proposed two multifocus image fusion techniques based on multi‐scale and multi‐direction neighbor distance.…”

Section: Related Workmentioning

confidence: 99%

Wavelet Flow: Optical Flow Guided Wavelet Facial Image Fusion

Ding

Yan²,

et al. 2019

Computer Graphics Forum

View full text Add to dashboard Cite

Estimating the correspondence between the images using optical flow is the key component for image fusion, however, computing optical flow between a pair of facial images including backgrounds is challenging due to large differences in illumination, texture, color and background in the images. To improve optical flow results for image fusion, we propose a novel flow estimation method, wavelet flow, which can handle both the face and background in the input images. The key idea is that instead of computing flow directly between the input image pair, we estimate the image flow by incorporating multi‐scale image transfer and optical flow guided wavelet fusion. Multi‐scale image transfer helps to preserve the background and lighting detail of input, while optical flow guided wavelet fusion produces a series of intermediate images for further fusion quality optimizing. Our approach can significantly improve the performance of the optical flow algorithm and provide more natural fusion results for both faces and backgrounds in the images. We evaluate our method on a variety of datasets to show its high outperformance.

show abstract

Image fusion via feature residual and statistical matching

Cited by 19 publications

References 21 publications

A Compendious Analysis of Feature-Extraction Algorithms to Frame Fusion Rules

A Compendious Analysis of Feature-Extraction Algorithms to Frame Fusion Rules

A two-stage processing approach for contrast intensified image fusion

Wavelet Flow: Optical Flow Guided Wavelet Facial Image Fusion

Contact Info

Product

Resources

About