Automatic prior selection for image deconvolution: Statistical modeling on natural images

Lee, Haegeun; Han, Jeong Hye; Hong, Soonyoung; Kang, Moon Gi

doi:10.1016/j.sigpro.2021.108307

Cited by 4 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed non-blind thermal image deconvolution algorithm was experimentally validated and compared with those of conventional studies on visible-band images [ 6 , 8 , 10 , 11 ]. To construct the simulation set, clean infrared images were blurred by real image blurs [ 30 ] and subsequently degraded by the column FPN and random noise.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…Jon et al [ 11 ] focused on the distributions of overlapping patches and combined overlapping group sparsity with a natural image prior to penalize grouped sparsity. Lee et al [ 10 ] proposed an automatic prior selection algorithm that automatically determines the most-effective prior term for visible-band images. The thermal images restored by these well-established algorithms for visible-band images were compared with those of the proposed algorithm.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…Zoran et al [ 26 ] employed the Gaussian mixture model (GMM) and derived the expected patch log likelihood (EPLL) framework to consider patch statistics more deliberately. Lee et al [ 10 ] proposed an automated prior selection algorithm that precisely estimates the inherent gradient statistics from the observations. However, few studies have been conducted on infrared images in this field.…”

Section: Related Workmentioning

confidence: 99%

“…We employed statistical modeling in our previous study [ 10 ], which numerically estimated the two parameters that most closely describe the reference distributions. As shown in Figure 5 , the comparatively higher peaks and shorter tails of the thermal images are represented by smaller values of p and

.…”

Section: Proposed Algorithmmentioning

confidence: 99%

“…Image deconvolution removes the observed blurs by solving the inverse problem of linear degradation models, and various approaches have been studied for visible-band images [ 6 , 7 , 8 ]. In particular, non-blind deconvolution algorithms can restore the observed degradations when the point spread function is given and have been extensively studied for the deep consideration of imaging systems considering restored image characteristics [ 9 , 10 , 11 ]. Several studies have been conducted to overcome blurs and random noise for infrared images [ 12 , 13 ]; however, they did not consider FPN in the modeling, which dominates the quality of the observed infrared images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Infrared Image Deconvolution Considering Fixed Pattern Noise

Lee

Kang

2023

Sensors

Self Cite

View full text Add to dashboard Cite

As the demand for thermal information increases in industrial fields, numerous studies have focused on enhancing the quality of infrared images. Previous studies have attempted to independently overcome one of the two main degradations of infrared images, fixed pattern noise (FPN) and blurring artifacts, neglecting the other problems, to reduce the complexity of the problems. However, this is infeasible for real-world infrared images, where two degradations coexist and influence each other. Herein, we propose an infrared image deconvolution algorithm that jointly considers FPN and blurring artifacts in a single framework. First, an infrared linear degradation model that incorporates a series of degradations of the thermal information acquisition system is derived. Subsequently, based on the investigation of the visual characteristics of the column FPN, a strategy to precisely estimate FPN components is developed, even in the presence of random noise. Finally, a non-blind image deconvolution scheme is proposed by analyzing the distinctive gradient statistics of infrared images compared with those of visible-band images. The superiority of the proposed algorithm is experimentally verified by removing both artifacts. Based on the results, the derived infrared image deconvolution framework successfully reflects a real infrared imaging system.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Experiments Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

.…”

Section: Proposed Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Infrared Image Deconvolution Considering Fixed Pattern Noise

Lee

Kang

2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

Overlapping group prior for image deconvolution using patch-wise gradient statistics

et al. 2023

View full text Add to dashboard Cite

Enhancing time‐frequency resolution via deep‐learning framework

Wang

Chen

Xiao

et al. 2023

IET Signal Processing

View full text Add to dashboard Cite

The fixed window function used in the short‐time Fourier transform (STFT) does not guarantee both time and frequency resolution, exerting a negative impact on the subsequent study of time‐frequency analysis (TFA). To avoid these limitations, a post‐processing method that enhances the time‐frequency resolution using a deep‐learning (DL) framework is proposed. Initially, the deconvolution theoretical formula is derived and a post‐processing operation is performed on the time‐frequency representation (TFR) of the STFT via deconvolution, a theoretical calculation to obtain the ideal time‐frequency representation (ITFR). Then, aiming at the adverse influence of the window function, a novel fully‐convolutional encoder‐decoder network is trained to preserve effective features and acquire the optimal time‐frequency kernel. In essence, the generation of the optimal time‐frequency kernel can be regarded as a deconvolution process. The authors conducted the qualitative and quantitative analyses of numerical simulations, with experimental results demonstrate that the proposed method achieves satisfactory TFR, possesses strong anti‐noise capabilities, and exhibits high steady‐state generalisation capability. Furthermore, results of a comparative experiment with several TFA methods indicate that the proposed method yields significantly improved performance in terms of time‐frequency resolution, energy concentration, and computational load.

show abstract

Automatic prior selection for image deconvolution: Statistical modeling on natural images

Cited by 4 publications

References 20 publications

Infrared Image Deconvolution Considering Fixed Pattern Noise

Infrared Image Deconvolution Considering Fixed Pattern Noise

Overlapping group prior for image deconvolution using patch-wise gradient statistics

Enhancing time‐frequency resolution via deep‐learning framework

Contact Info

Product

Resources

About