Sparse representation based on vector extension of reduced quaternion matrix for multiscale image denoising

Gai, Shan; Wang, Long; Yang, Guowei; Yang, Peng

doi:10.1049/iet-ipr.2015.0611

Cited by 22 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantages of quaternion wavelet transform [1,17], quaternion principal component analysis [40] and other quaternion color image processing techniques [37] have been proven to extract more representative features for color images and achieved encouraging results in high-level vision tasks like color image classification. In low-level vision tasks like image denoising and super-resolution, the quaternion-based methods [8,38] preserve more interrelationship information across different channels, and thus, can restore images with higher quality. Recently, a quaternion-based neural network is also put forward and used for classification tasks [3,27,30].…”

Section: Quaternion-based Color Image Processingmentioning

confidence: 99%

See 1 more Smart Citation

Quaternion Convolutional Neural Networks

Zhu

et al. 2018

Lecture Notes in Computer Science

139

100

View full text Add to dashboard Cite

Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years. However, the extensions of the neural network models in other number fields and their potential applications are not fully-investigated yet. Focusing on color images, which can be naturally represented as quaternion matrices, we propose a quaternion convolutional neural network (QCNN) model to obtain more representative features. In particular, we re-design the basic modules like convolution layer and fullyconnected layer in the quaternion domain, which can be used to establish fully-quaternion convolutional neural networks. Moreover, these modules are compatible with almost all deep learning techniques and can be plugged into traditional CNNs easily. We test our QCNN models in both color image classification and denoising tasks. Experimental results show that they outperform the real-valued CNNs with same structures.

show abstract

Section: Quaternion-based Color Image Processingmentioning

confidence: 99%

“…where f i , i = 1, 2, 3, is defined as (8) does. The matrix of f i 's is exactly same as that in (7), but the operation switches from left multiplication to right multiplication.…”

Section: Backpropagationmentioning

confidence: 99%

Quaternion Convolutional Neural Networks

Zhu

et al. 2018

Lecture Notes in Computer Science

139

100

View full text Add to dashboard Cite

show abstract

“…Then, a reduced quaternion-based orthogonal matching pursuit algorithm is presented in the sparse coding stage. The proposed colour image sparse representation model is applied to colour image de-noising in order to demonstrate the superior performance [7]. The experimental results shows that the elapsed time for RQM-KSVD is less than the elapsed time for GSM, KSVD, I-KSVD, and QSVD.…”

Section: Literature Surveymentioning

confidence: 99%

A Survey of Various Image De-noising Techniques

Thakur

Singh

2018

IJERMT

View full text Add to dashboard Cite

show abstract

“…Their improvement in the sparse representation technique is the replacement of l 0 -norm to l 1 -norm. Gai et al (2016) proposed an extension to the KSVD algorithm, i.e., the quanternion matrix RQM-KSVD. Given the colour image they represent it by RQM and then SVD is applied to get the denoised image.…”

Section: Introductionmentioning

confidence: 99%

Enhancing proximity measure between residual and noise for image denoising

Baloch

Ahmed

2019

IJCVR

View full text Add to dashboard Cite

Sparse representation and dictionary learning-based image denoising algorithms approximate the clean image patch by linear combination of few dictionary atoms. Clearly, residue after completion of denoising must be similar to the contaminating noise. Ideally, clean image patch is perfectly recovered if residue is exactly contaminating noise. Hence, for better denoising, residue must be enforced to possess characteristics similar to the contaminating noise. In this paper, we model residue such that proximity between residue and contaminating noise is increased. The proposed mathematical model makes sure that the residue is as random in nature as contaminating noise. This is achieved by unique sparse coding and dictionary update stages developed based on modelling of randomness in residue. The proposed algorithm is tested on additive white Gaussian noise (AWGN), additive coloured Gaussian noise (ACGN) and Laplacian noise. Since performance of the image denoising algorithms also depend on image effective bandwidth, therefore, in this paper we have generated synthetic images with known effective image bandwidths. These images are generated using the discrete cosine transform (DCT). The proposed algorithm is also tested on these images. The proposed algorithm is compared with state-of-the-art algorithms. The comparison on the bases of peak signal-to-noise ratio (PSNR), structure similarity index measure (SSIM) and feature similarity index measure (FSIM) indicate that the proposed algorithm is able to produce often better and competitive results.

show abstract

Sparse representation based on vector extension of reduced quaternion matrix for multiscale image denoising

Cited by 22 publications

References 41 publications

Quaternion Convolutional Neural Networks

Quaternion Convolutional Neural Networks

A Survey of Various Image De-noising Techniques

Enhancing proximity measure between residual and noise for image denoising

Contact Info

Product

Resources

About