A sparse proximal Newton splitting method for constrained image deblurring

Pan, Han; Jing, Zhongliang; Lei, Ming; Liu, Rongli; Jin, Bo; Zhang, Canlong

doi:10.1016/j.neucom.2013.06.027

Cited by 14 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proximal methods are a type of forward-backward splitting approach, which alternates between computing a gradient step on the data fidelity term and a solution to a proximal problem involving the regularization (Parikh et al, 2014;Combettes and Pesquet, 2011;Beck and Teboulle, 2009b). Moreover, the proximal gradient methods can also be accelerated by utilizing momentum information from past gradients or by deploying second order information to solve the proximal problem (Becker and Fadili, 2012;Beck and Teboulle, 2009b;Beck and Teboulle, 2009a;Pan et al, 2013;Nesterov et al, 2007;Lee et al, 2012;Stella et al, 2017). Examples of PACT images of a live mouse reconstructed by use of two different reconstruction methods are displayed in Fig.…”

Section: Penalized Least Squares Methodsmentioning

confidence: 99%

“…Teboulle 2009b, Combettes and Pesquet 2011, Parikh et al 2014. Moreover, the proximal gradient methods can also be accelerated by utilizing momentum information from past gradients or by deploying second order information to solve the proximal problem(Nesterov et al 2013, Beck and Teboulle 2009a, 2009b, Becker and Fadili 2012, Lee et al 2012, Pan et al 2013, Stella et al 2017.Examples of PACT images of a live mouse reconstructed by use of two different reconstruction methods are displayed in figure…”

mentioning

confidence: 99%

See 1 more Smart Citation

A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography

2019

View full text Add to dashboard Cite

Photoacoustic computed tomography (PACT), also known as optoacoustic tomography, is an emerging imaging technique that holds great promise for biomedical imaging. PACT is a hybrid imaging method that can exploit the strong endogenous contrast of optical methods along with the high spatial resolution of ultrasound methods. In its canonical form that is addressed in this article, PACT seeks to estimate the photoacoustically-induced initial pressure distribution within the object. Image reconstruction methods are employed to solve the acoustic inverse problem associated with the image formation process. When an idealized imaging scenario is considered, analytic solutions to the PACT inverse problem are available; however, in practice, numerous challenges exist that are more readily addressed within an optimization-based, or iterative, image reconstruction framework. In this article, the PACT image reconstruction problem is reviewed within the context of modern optimization-based image reconstruction methodologies. Imaging models that relate the measured photoacoustic wavefields to the sought-after object function are described in their continuous and discrete forms. The basic principles of optimization-based image reconstruction from discrete PACT measurement data are presented, which includes a review of methods for modeling the PACT measurement system response and other important physical factors. Non-conventional formulations of the PACT image reconstruction problem, in which acoustic parameters of the medium are concurrently estimated along with the PACT image, are also introduced and reviewed.

show abstract

Section: Penalized Least Squares Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography

2019

View full text Add to dashboard Cite

show abstract

“…Its purpose is to restore potentially tidy image from blurry image, which is a morbid inverse problem. Many scholars have improved the image quality by regarding blur and potential sharp image as prior information (Liu et al, 2018; Wang et al, 2011), including regularization intensity prior (Dong et al, 2011; Tang et al, 2019), total variation (TV) (Jidesh and Banothu, 2017; Osher et al, 2005), mathematically driven discriminate prior (Li et al, 2018), sparse image prior (Pan et al, 2013), and so forth. Although these improve the image quality, estimated blur kernel may cause image visual artifacts.…”

Section: Related Workmentioning

confidence: 99%

RFID multi-tag dynamic detection measurement based on conditional generative adversarial nets and YOLOv3

Lin

Liu

et al. 2021

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

The quality of multi-tag imaging greatly affects the effective detection of multi-tag. When multi-tag moves rapidly, the image may have serious dynamic blur, and tags can not be detected efficiently. In previous work, it is generally assumed that blur kernel and noise stationary to improve image quality. However, the dynamic deblurring of Radio Frequency Identification (RFID) multi-tag imaging is an ill-posed inverse problem. In this paper, firstly, blur-sharp multi-tag image pairs are made by superimposing and averaging the adjoin random frames. Then, we propose blind deblurring for dynamic RFID multi-tag imaging based on conditional generative adversarial nets (CGANs), which adds perceptual loss and content loss to generator to make image sharper. Finally, tags are detected by YOLOv3 in real time in end-to-end manner. Experimental results demonstrate that PSNR is at least 0.56dB higher and speed is at least 31.25 % faster than that of the current improved convolution neural networks (CNN). CGANs can remove image blur better, which has great superiority in the field of dynamic multi-tag imaging. In addition, YOLOv3 detects multi-tag quickly, thereby improving the detection accuracy.

show abstract

“…The motivation of the proposed method is to handle the practical limitations in [19] [27] [35] e.g., the inaccuracy estimate of the sub-problem and the dimension limitation. Accordingly, the framework of the generalized proximal conjugate gradient(GPCG) is proposed.…”

Section: B the Contributionsmentioning

confidence: 99%

Generalized proximal conjugate gradient method for image deblurring

Pan

Jing

Huang

et al. 2014

11th IEEE International Conference on Control &Amp; Automation (ICCA)

Self Cite

View full text Add to dashboard Cite

It is very difficult to restore natural geometry of the actual image from degraded observation. In this paper, to deal with approximation error and the turbulence casued by proximal splitting scheme, a generalized proximal conjugate gradient framework is proposed. To trade off approximate accuracy and computational complexity, an approximate solution is presented, which characterized by maintaining the sparse pattern of second-derivate information and considered a correcting stage with conjugate gradient. Some theoretical properties of the proposed method are discussed and presented. The numerical experiments of the proposed algorithm, in compassion to the favorable state-of-the-art methods, demonstrate the advantages of the proposed method and its great potential.

show abstract

A sparse proximal Newton splitting method for constrained image deblurring

Cited by 14 publications

References 28 publications

A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography

A survey of computational frameworks for solving the acoustic inverse problem in three-dimensional photoacoustic computed tomography

RFID multi-tag dynamic detection measurement based on conditional generative adversarial nets and YOLOv3

Generalized proximal conjugate gradient method for image deblurring

Contact Info

Product

Resources

About