Residual interpolation for color image demosaicking

Kiku, Daisuke; Monno, Yusuke; Tanaka, Masayuki; Okutomi, Masatoshi

doi:10.1109/icip.2013.6738475

Cited by 127 publications

(157 citation statements)

References 11 publications

Supporting

Mentioning

157

Contrasting

Order By: Relevance

“…RI [10] is applied to the interpolation of R/B pixels in MLRI [12] in which the guide filter is the key point. The guide filter is a linear variable process.…”

Section: The Guide Filter In Mlrimentioning

confidence: 99%

“…The rest of this paper is organized as follows: Section 2 starts with a brief review of color difference, RI [10], Laplacian energy, and the G interpolation in GBTF [8] and MDWI-GF [17]. Section 3 presents the process of the proposed interpolation method.…”

Section: Introductionmentioning

confidence: 99%

“…Finally, to generate the full R images, the interpolated G pixel images are added to the interpolated color difference images. [12] and (b) the process of residual interpolation (RI) [10]. Figure 2b shows the RI [10] process of the R plane.…”

Section: Introductionmentioning

confidence: 99%

“…[12] and (b) the process of residual interpolation (RI) [10]. Figure 2b shows the RI [10] process of the R plane. The part that is different from CDI [12] is the estimations of R pixel values.…”

Section: Introductionmentioning

confidence: 99%

“…Most spatial interpolation algorithms are proposed by assuming that color ratios and color differences are constant over small regions, while residual interpolation (RI) [10], a novel demosaicking algorithm, works over residual domain. The interpolation method, which defined the residual as the difference between the observed and the tentatively estimated pixel values, first generates an estimate image accurately enough over R/B channel by using the guide filter [11], a powerful edge-preserving filter, followed by using GBTF [8].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Bayer Image Demosaicking Using Eight-Directional Weights Based on the Gradient of Color Difference

et al. 2018

View full text Add to dashboard Cite

Abstract:In this paper, we propose a new demosaicking algorithm which uses eight-directional weights based on the gradient of color difference (EWGCD) for Bayer image demosaicking. To obtain the interpolation of green (G) pixels, the eight-directional G pixel values are first estimated in red (R)/blue (B) pixels. This estimate is used to calculate the color difference in R/B pixels of the Bayer image in diagonal directions. However, in horizontal and vertical directions, the new estimated G pixels are defined to obtain the color difference. The eight-directional weights of estimated G pixels can be obtained by considering the gradient of the color difference and the gradient of the RGB pixels of the Bayer image. Therefore, the eight-directional weighted values and the first estimated G pixel values are combined to obtain the full G image. Compared with six similar algorithms using the same eighteen McMaster images, the results of the experiment demonstrate that the proposed algorithm has a better performance not only in the subjective visual measurement but also in the assessments of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index measurement.

show abstract

“…RI [10] is applied to the interpolation of R/B pixels in MLRI [12] in which the guide filter is the key point. The guide filter is a linear variable process.…”

Section: The Guide Filter In Mlrimentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Bayer Image Demosaicking Using Eight-Directional Weights Based on the Gradient of Color Difference

et al. 2018

View full text Add to dashboard Cite

show abstract

Neural Network Evolution Using Expedited Genetic Algorithm for Medical Image Denoising

Liu

Basha

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning

Ulaş

Tetteh

Kaczmarz

et al. 2018

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

View full text Add to dashboard Cite

Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and benefits in quantification. However, ASL suffers from an inherently low-signal-to-noise ratio (SNR) requiring repeated measurements of control/spin-labeled (C/L) pairs to achieve a reasonable image quality, which in return increases motion sensitivity. This leads to clinically prolonged scanning times increasing the risk of motion artifacts. Thus, there is an immense need of advanced imaging and processing techniques in ASL. In this paper, we propose a novel deep learning based approach to improve the perfusion-weighted image quality obtained from a subset of all available pairwise C/L subtractions. Specifically, we train a deep fully convolutional network (FCN) to learn a mapping from noisy perfusion-weighted image and its subtraction (residual) from the clean image. Additionally, we incorporate the CBF estimation model in the loss function during training, which enables the network to produce high quality images while simultaneously enforcing the CBF estimates to be as close as reference CBF values. Extensive experiments on synthetic and clinical ASL datasets demonstrate the effectiveness of our method in terms of improved ASL image quality, accurate CBF parameter estimation and considerably small computation time during testing.

show abstract

Residual interpolation for color image demosaicking

Cited by 127 publications

References 11 publications

Bayer Image Demosaicking Using Eight-Directional Weights Based on the Gradient of Color Difference

Bayer Image Demosaicking Using Eight-Directional Weights Based on the Gradient of Color Difference

Neural Network Evolution Using Expedited Genetic Algorithm for Medical Image Denoising

DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning

Contact Info

Product

Resources

About