Medical image fusion algorithm based on multi-resolution analysis coupling approximate spare representation

Guan, Jian; Kang, Shaobo; Sun, Yung-Nien

doi:10.1016/j.future.2018.12.027

Cited by 13 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Discrete wavelet transform is a tool for multiscale analysis to convert signals from the time domain to the frequency domain. It provides the frequency and time-frequency information of the signal by splitting the signal into subband signals of different frequencies and breaking down the low frequency (approximate) [9] part of each subband and high frequency (detail) signal. So this method is used to extract the wavelet coefficient and calculate the eigenvalue.…”

Section: Fault Feature Extractionmentioning

confidence: 99%

Wind power gearbox fault diagnosis of BP neural network based on improved Sparrow algorithm

Li,

Fan

2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

It is difficult to identify the faults on the surface and root of the fan gearbox, resulting in low diagnostic accuracy. As an important part of the wind turbine, the abnormal vibration of the gear is easy to cause great losses, in order to improve the specific fault identification rate and reduce the fault. The following aspects are used to improve the sparrow algorithm. First, the homogeneous distribution Tent chaotic model is introduced to initialize the population distribution to improve the uniformity of the population distribution, then the Gaussian variation is used to add the random distribution to the newly generated individuals, and finally the adaptive weight is used to determine the value of the adjustment weight from the adaptation according to the population search state. The optimized sparrow algorithm can avoid falling into the local optimal solution and improve the convergence speed. By using the final conclusion of the improved sparrow algorithm, the accuracy of fault detection can be improved.

show abstract

Section: Fault Feature Extractionmentioning

confidence: 99%

Wind power gearbox fault diagnosis of BP neural network based on improved Sparrow algorithm

Li,

Fan

2024

Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023)

View full text Add to dashboard Cite

show abstract

“…The fused image preserved more of the original image's information with strong edge retention, according to a visual and quantitative examination of the experimental results. Guan et al proposed an image fusion algorithm based on multi-scale analysis coupled with approximate sparse representation to better deal with the singularity of high-dimensional features of images and to take into account the fusion of image target features and average intensity information [11]. The highfrequency and low-frequency information of the image was obtained by the scale analysis of the source image, and the specific target detail information was highlighted.…”

Section: Related Workmentioning

confidence: 99%

“…In Equation (10), the original image is recorded with I , the center of I is noted as  and   , ij is any point. which can be established in Equation (11). In Equation (11), q  represents the Euclidean distance of the similar parts between the shared blocks.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Application of Medical Brain CT/MRI Image Fusion Algorithm based on Neural Network

Yang¹

2023

IJACSA

View full text Add to dashboard Cite

In recent years, fused images have been developed for fast processing of medical images, which provide a more reliable basis for reducing the burden on physicians because they can contain multiple times the image information. In order to achieve fast and accurate recognition results in medical image recognition, avoid similar blocks and shadow fitting in CT/MR fusion images, and improve the entire medical system, in this study, CT/MRI image fusion of brain images is studied based on algorithms generated by Convolutional Neural Network (CNN). The study utilizes Rolling Guidance Filter (RGF) to divide medical CT/MRI images into two parts, one of which is used for model training and the other for image fusion. In the experiments, the results of all three experiments are compared with the Nonsub Sampled Contourlet Transform -Piecewise Convolutional Neural Network (NSCT -PCNN), and the CNN-RGF MI/ IE/SSIM/AG values of CNN-RGF are superior compared to the conventional algorithm of NSCT-RCNN with an average improvement of 10.0% and above, and the resulting CNN-RGF observed meningitis, hydrocephalus, and cerebral infarction with an average of 24.8% higher compared to NSCT-RCNN. The outcomes show that for brain image fusion and detection, the CNN-RGF approach put forward in the study performs better.

show abstract

“…Testing Images. In the experiments, nine pairs of medical images of the database[21,33] are used as the testing image sets, as shown in Figure4. These images have a resolution of 256 × 256 pixels and 256 levels, except for the ninth group of images that have a resolution of 464 × 464.4.1.2.…”

mentioning

confidence: 99%

Medical Image Fusion Based on Low-Level Features

Zhang

Guo

Zhao

2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Medical image fusion is an important technique to address the limited depth of the optical lens for a completely informative focused image. It can well improve the accuracy of diagnosis and assessment of medical problems. However, the difficulty of many traditional fusion methods in preserving all the significant features of the source images compromises the clinical accuracy of medical problems. Thus, we propose a novel medical image fusion method with a low-level feature to deal with the problem. We decompose the source images into base layers and detail layers with local binary pattern operators for obtaining low-level features. The low-level features of the base and detail layers are applied to construct weight maps by using saliency detection. The weight map optimized by fast guided filtering guides the fusion of base and detail layers to maintain the spatial consistency between the source images and their corresponding layers. The recombination of the fused base and detail layers constructs the final fused image. The experimental results demonstrated that the proposed method achieved a state-of-the-art performance for multifocus images.

show abstract

Medical image fusion algorithm based on multi-resolution analysis coupling approximate spare representation

Cited by 13 publications

References 9 publications

Wind power gearbox fault diagnosis of BP neural network based on improved Sparrow algorithm

Wind power gearbox fault diagnosis of BP neural network based on improved Sparrow algorithm

Application of Medical Brain CT/MRI Image Fusion Algorithm based on Neural Network

Medical Image Fusion Based on Low-Level Features

Contact Info

Product

Resources

About