Fractional-order differentiation based sparse representation for multi-focus image fusion

Yu, Lei; Zhang, Zhi; Wang, Huiqi; Pedrycz, Witold

doi:10.1007/s11042-021-11758-3

Cited by 7 publications

(6 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. [𝑆 𝑗 (𝑠, 𝑡)] 𝑦 𝑗 (8) Where 𝐶 𝑗 (𝑠, 𝑡), 𝑆 𝑗 (𝑠, 𝑡), 𝑙 𝑚 (𝑠, 𝑡) denotes the contrast, structure and luminance comparison with m scale respectively.…”

Section: 𝑀𝑆_𝑆𝑆𝐼𝑀(𝑠 𝑡) = [𝑙 𝑚 (𝑠 𝑡)] 𝛼 𝑀 ∏ [𝐶 𝑗 (𝑠 𝑡)]mentioning

confidence: 99%

“…Yang Bin [7] proposed approximate sparse representationbased image fusion, using a multi-selection strategy in orthogonal matching pursuit to guide the fusion of image patches. A novel approach termed fractional-order differentiation based sparse representation (FD-SR) is proposed by Lei Yu [8]. To acquire the feature maps, the source images are first convoluted with fractional-order differentiation masks, after which the HOG are generated to extract the salient information.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Infrared and visible image fusion using LatLRR and ResNet

Prema,

Arivazhagan,

Aishwarya

et al. 2024

AIP Conference Proceedings

View full text Add to dashboard Cite

Image fusion is a notable concern in the image processing field which helps to produce a resultant image by amalgamating all the features from one or more source images. We envisioned an infrared (IR) and visible (VIS) image fusion technique combining (Latent Low Rank Representation) LatLRR and ResNet to mitigate the loss of contrast, texture, spectral, and spatial details in the resultant image. The fused image seems to be more appropriate and obvious for human and machine vision perception. Using LatLRR, the source images are initially broken down into saliency and latent low rank parts. Then, using weighted-average method, the Latent Low Rank components are integrated. Fusion approach based on deep features is used to overcome the problem of information lost by using RESNET to extract multilayer features for the saliency part as this network has a skip connection which helps to gather information from every layer. After that, the deep features are normalized by nuclear norm, and preliminary weight maps are generated. Combining the original weight maps with a Soft-Max operation yields the final-weight maps. At last, by summing the fused Latent Low Rank component and the Saliency content, the fused image will be reconstructed. Both visual and quantitative performance evaluation is done for the proposed method with five existing methods and it is inferred from the results that the proposed method can well reconstruct the fused image without haloes and artifacts.

show abstract

Section: 𝑀𝑆_𝑆𝑆𝐼𝑀(𝑠 𝑡) = [𝑙 𝑚 (𝑠 𝑡)] 𝛼 𝑀 ∏ [𝐶 𝑗 (𝑠 𝑡)]mentioning

confidence: 99%

mentioning

confidence: 99%

Infrared and visible image fusion using LatLRR and ResNet

Prema,

Arivazhagan,

Aishwarya

et al. 2024

AIP Conference Proceedings

View full text Add to dashboard Cite

show abstract

“…That is, fractional differentiation can enhance the edge and contour information and weak textural areas of an image. Thus, fractional differentiation is a valuable tool in image processing [16][17][18][19][20].…”

Section: Fractional-differential-based Depth Image Enhancementmentioning

confidence: 99%

Depth Image Enhancement Algorithm Based on Fractional Differentiation

et al. 2023

View full text Add to dashboard Cite

Depth image enhancement techniques can help to improve image quality and facilitate computer vision tasks. Traditional image−enhancement methods, which are typically based on integer−order calculus, cannot exploit the textural information of an image, and their enhancement effect is limited. To solve this problem, fractional differentiation has been introduced as an innovative image−processing tool. It enables the flexible use of local and non−local information by taking into account the continuous changes between orders, thereby improving the enhancement effect. In this study, a fractional differential is applied in depth image enhancement and used to establish a novel algorithm, named the fractional differential–inverse−distance−weighted depth image enhancement method. Experiments are performed to verify the effectiveness and universality of the algorithm, revealing that it can effectively solve edge and hole interference and significantly enhance textural details. The effects of the order of fractional differentiation and number of iterations on the enhancement performance are examined, and the optimal parameters are obtained. The process data of depth image enhancement associated with the optimal number of iterations and fractional order are expected to facilitate depth image enhancement in actual scenarios.

show abstract

“…However, this approach did not necessarily result in a highly structured dictionary (Nejati et al 2015). Later, to construct a representative dictionary for SR, Yu proposed a histogram of oriented gradient (HOG)-based image fusion scheme that divided a pre-trained dictionary into several categories through clustering (Yu et al 2022). Therefore, existing SR-based fusion schemes either utilize a pre-constructed dictionary that requires less processing time or employ a learning dictionary that necessitates prior knowledge of externally pre-collected data.…”

Section: Introductionmentioning

confidence: 99%

“…In addition to the effects of the acquisition approaches for pre-trained dictionaries on fusion performance of the SR-based schemes, unreasonable strategies for measuring the activity level may inevitably reduce the fusion weight accuracy. The use of the activity level measure aids in identifying the unique characteristics of the source images during the fusion process, and the max L1-norm mode is the conventional approach to capturing the detailed information present in sparse vectors (Zhu et al 2016, Yu et al 2022, while the mode is more suitable for single-target salient feature expression, since multi-target features are not all salient features. Therefore, the mode will inevitably result in information loss.…”

Section: Introductionmentioning

confidence: 99%

Adaptive convolutional sparsity with sub-band correlation in the NSCT domain for MRI image fusion

Hu,

Cai,

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

ObjectiveMultimodal medical image fusion (MMIF) technologies merges diverse medical images with rich information, boosting diagnostic efficiency and accuracy. Due to global optimization and single-valued nature, convolutional sparse representation (CSR) outshines the standard sparse representation (SR) in significance. By addressing the challenges of sensitivity to highly redundant dictionaries and robustness to misregistration, an adaptive convolutional sparsity scheme with measurement of the sub-band correlation in the non-subsampled contourlet transform (NSCT) domain is proposed for MMIF.ApproachThe fusion scheme incorporates four main components: image decomposition into two scales, fusion of detail layers, fusion of base layers, and reconstruction of the two scales. We solved a Tikhonov regularization optimization problem with source images to obtain the base and detail layers. Then, after CSR processing, detail layers were sparsely decomposed using pre-trained dictionary filters for initial coefficient maps. NSCT domain's sub-band correlation was used to refine fusion coefficient maps, and sparse reconstruction produced the fused detail layer. Meanwhile, base layers were fused using averaging. The final fused image was obtained via two-scale reconstruction.Main resultsExperimental validation of clinical image sets revealed that the proposed fusion scheme can not only effectively eliminate the interference of partial misregistration, but also outperform the representative state-of-the-art fusion schemes in the preservation of structural and textural details according to subjective visual evaluations and objective quality evaluations.SignificanceThe proposed fusion scheme is competitive due to its low-redundancy dictionary, robustness to misregistration, and better fusion performance. This is achieved by training the dictionary with minimal samples through CSR to adaptively preserve overcompleteness for detail layers, and constructing fusion activity level with sub-band correlation in the NSCT domain to maintain CSR attributes. Additionally, ordering the NSCT for reverse sparse representation further enhances sub-band correlation to promote the preservation of structural and textural details.

show abstract

Fractional-order differentiation based sparse representation for multi-focus image fusion

Cited by 7 publications

References 60 publications

Infrared and visible image fusion using LatLRR and ResNet

Infrared and visible image fusion using LatLRR and ResNet

Depth Image Enhancement Algorithm Based on Fractional Differentiation

Adaptive convolutional sparsity with sub-band correlation in the NSCT domain for MRI image fusion

Contact Info

Product

Resources

About