Midfrequency-based real-time blind image restoration via independent component analysis and genetic algorithms

Luo, Yufei; Fu, Chengyu

doi:10.1117/1.3567072

Cited by 8 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This section describes our experiments using Matlab on a desktop PC (Intel Core(TM) i5‐3337 at 1.8 GHz × 2 CPU; 4 GB memory). For comparison, we consider Luo's algorithm (mid‐frequency based algorithm) [11], Goldstein's algorithm [19], and Perrone's algorithm (TVBD) [7]. Luo's algorithm is non‐iterative, and the other two are iterative.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Non‐iterative blind deconvolution algorithm based on power‐law distribution

Gao

Yang

et al. 2020

IET image process

View full text Add to dashboard Cite

The spectral amplitude of most natural images is approximately isotropic and follows the power law. In this study, the authors propose a new non‐iterative blind image deconvolution algorithm that builds an isosceles curve model to approximate the spectrum amplitude of the real image. In the authors’ proposed algorithm, the optical transfer function (OTF) is obtained by comparing the reconstructed and degraded spectra. Then they employ the integrated multidirectional comprehensive estimation to reduce the OTF estimation error. The restored image is then obtained by applying the estimated OTF and the Wiener filter. Experiments on image deconvolution tasks indicate that the proposed algorithm provides a significant performance gain by obtaining an accurate OTF, reducing ringing artefacts compared with existing algorithms, and realising real‐time image restoration.

show abstract

Section: Methodsmentioning

confidence: 99%

“…This method also based on trial and error which leads to a time‐consuming parameter selection process. Although APEX algorithm has been later significantly considerably improved in [10–12], the above issues remained unsolved.…”

Section: Introductionmentioning

confidence: 99%

Non‐iterative blind deconvolution algorithm based on power‐law distribution

Gao

Yang

et al. 2020

IET image process

View full text Add to dashboard Cite

show abstract

“…附近的"低频"区域，卷积核的信息被完全淹没在瞬态图像的信息中，而频谱的"高频"区域幅度小且易被噪声污染。由于"低频"和"高 6 域，即不含太多的瞬态图像能量又没有被噪声淹没，我们将之称为"中频域" ，可以用于估计 K 值从而进行维纳滤波反卷积 [22] 。非视域成像系统中捕获的瞬态图像中大多数信号变化缓慢，只有少数信号变化大，频谱往往为全局单减，因此瞬态图像存在中频域并且数值特征大都相似。图 2 50 w  时瞬态图像的频谱图 ( , , ) G u v w…”

Section: 引言unclassified

Non-line-of-sight imaging algorithm based on Wiener filtering of mid-frequency

Tang¹,

Luo²,

Xie³

et al. 2023

Acta Phys. Sin.

View full text Add to dashboard Cite

Non-line-of-sight (NLOS) imaging is an emerging technology for optical imaging of objects blocked out of the detector's line of sight. Non-line-of-sight imaging based on light-cone transform and inverted method can be regarded as a deconvolution process. The traditional wiener filtering deconvolution method uses empirical values or repeated attempts to obtain the power spectral density noise-to-signal ratio (PSDNSR) of the transient image which is different in various hidden scenes of NLOS imaging, so the prior estimation is not appropriate and repeated attempts make it difficult to quickly find the optimal value. Therefore, this paper proposes a method which estimate PSDNSR using the mid-frequency information of captured transient images for wiener filtering to achieve NLOS imaging. In this method, the turning points between the mid-frequency domain and the high-frequency domain of the transient image amplitude spectrum are determined, and then the PSDNSR value is solved by analyzing the characteristics and relationship of the noise power spectrum in the low, middle and high frequency. Experiments show that PSDNSR estimated by NLOS imaging algorithm based on wiener filtering of mid-frequency domain is of the order of magnitude with better reconstruction effect. Compared with other methods, the algorithm in this paper can directly estimate PSDNSR in one step, without iterative operation, and the computational complexity is low, which simplifies the parameter adjustment steps of the Wiener filtering deconvolution Non-line-of-sight imaging algorithm based on light-cone transform, so that the reconstruction efficiency can be improved on the premise of ensuring the reconstruction effect.

show abstract

“…After obtaining the blur kernel, the final latent image will be restored from the full-scale blurred image, which contains more noise and the process is time consuming. In order to achieve high robustness and processing speed, we adopt the MR-based Wiener filter [ 26 ] to restore the final latent sharp image in frequency domain, whose transfer function is formulated as follow:

where

is defined as:

…”

Section: Single Image Blind Deconvolution Using Reliable Structurementioning

confidence: 99%

Robust Image Restoration for Motion Blur of Image Sensors

Yang

Huang

Luo

et al. 2016

Sensors

Self Cite

View full text Add to dashboard Cite

Blind image restoration algorithms for motion blur have been deeply researched in the past years. Although great progress has been made, blurred images containing large blur and rich, small details still cannot be restored perfectly. To deal with these problems, we present a robust image restoration algorithm for motion blur of general image sensors in this paper. Firstly, we propose a self-adaptive structure extraction method based on the total variation (TV) to separate the reliable structures from textures and small details of a blurred image which may damage the kernel estimation and interim latent image restoration. Secondly, we combine the reliable structures with priors of the blur kernel, such as sparsity and continuity, by a two-step method with which noise can be removed during iterations of the estimation to improve the precision of the estimated blur kernel. Finally, we use a MR-based Wiener filter as the non-blind deconvolution algorithm to restore the final latent image. Experimental results demonstrate that our algorithm can restore large blur images with rich, small details effectively.

show abstract

Midfrequency-based real-time blind image restoration via independent component analysis and genetic algorithms

Cited by 8 publications

References 24 publications

Non‐iterative blind deconvolution algorithm based on power‐law distribution

Non‐iterative blind deconvolution algorithm based on power‐law distribution

Non-line-of-sight imaging algorithm based on Wiener filtering of mid-frequency

Robust Image Restoration for Motion Blur of Image Sensors

Contact Info

Product

Resources

About