Denoising of MRI Images Using Curvelet Transform

Biswas, R. K.; Purkayastha, Debraj Dhar; Roy, Sudipta

doi:10.1007/978-981-10-4762-6_55

Cited by 18 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the proposed denoising method for simulated noisy sonar image, and compare it with several methods. The denoising comparison algorithms used in this paper include Lee filter [36], Kuan filter [37], Frost filter [38], SRAD filter [39], Wavelet-based denoising method [14], Curvelet-based denoising method [15], DCT-based denoising method [12], and K-SVD denoising method [34]. Figure 4 shows the original image and simulated noisy image.…”

Section: Denoising Results Of Simulated Noisy Imagementioning

confidence: 99%

“…However, the another transform domain filtering method contains common Discrete Cosine Transform (DCT) [12], principal component analysis (PCA) [13], and Wavelet denoising algorithms [14]. Based on wavelet transform, a direction parameter was added and the Curvelet transform threshold filtering was used for noise removal [15]. Researchers used the Curvelet method for sonar image denoising as well in [16,17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speckle Noise Reduction in Sonar Image Based on Adaptive Redundant Dictionary

Huang

Yuan

2020

JMSE

View full text Add to dashboard Cite

As acoustic waves are affected by the channel characteristics, such as scattering and reverberation when propagating in water, sonar images often exhibit speckle noise which will cause visual quality of the image to decrease. Therefore, denoising is a crucial preprocessing technique in sonar image applications. However, speckle noise is mainly caused by the sediment echo signals which are related to the background of seafloor sediment and can be obtained by prior modeling. Although deep learning-based denoising algorithms represent a research hotspot now, they are not suitable for such applications due to the high calculation amount and the large requirement of original images considering that sonar is carried by Autonomous Underwater Vehicles (AUVs) for collecting sonar images and performing calculation. In contrast, dictionary learning-based denoising method is more suitable and easier to be modeled. Compared with deep learning, it can greatly reduce the calculation amount and is more easily integrated into AUV systems. In addition, dictionary learning method based on image sparse representation can effectively achieve image denoising similarly. In order to solve the above problems, we propose a new adaptive dictionary learning method based on multi-resolution characteristics, which combines K-SVD dictionary learning with wavelet transform. Our method has the characteristics of dictionary learning and inherits the features of wavelet analysis as well. Compared with several classical methods, the proposed method is better at speckle noise reduction and edge detail preservation. At the same time, the calculation time is greatly reduced and the efficiency is significantly improved.

show abstract

Section: Denoising Results Of Simulated Noisy Imagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Speckle Noise Reduction in Sonar Image Based on Adaptive Redundant Dictionary

Huang

Yuan

2020

JMSE

View full text Add to dashboard Cite

show abstract

“…Bacterial Foraging (BF) technique [36] with genetic algorithm and the algorithm has limitation over non optimal parameter. The frequency domain approaches like [37] wiener based CVT technique where the images are decomposed into disjoint scaling using ridgelet transform. CVT proves to be effective in Rician noise removal with suitable threshold value.…”

Section: Introductionmentioning

confidence: 99%

A New Performance Metric Algorithm in Image Filtering

Remya¹,

Nirmala²

2022

Preprint

View full text Add to dashboard Cite

Denoising play a vital role in image quality analysis and it is regarded as a challenging task. The quality of the image is analysed based on various performance metrics. This paper focuses on the quality metric for image filtered output and the testing is made on various general and medical images. Denoising is performed by various image filtering approaches and the outcome is good for other stages of image processing such as segmentation and image classification. An enhanced Discrete Wavelet Transform (Enhanced DWT) and a novel performance metrics based on logarithmic estimation are proposed for image denoising and analysing the quality of image. Along with the proposed similarity metrics other metrics like PSNR, NAE, and SSIM are consider for the work. The performance analysis is tested on different images like biomedical images, Barbara, cameraman, vegetables, and remote sensing images as well as a natural image. The experimental result shows that the proposed enhanced DWT yields a better result for all the similarity metrics.

show abstract