Beyond Color Difference: Residual Interpolation for Color Image Demosaicking

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

doi:10.1109/tip.2016.2518082

Cited by 138 publications

(104 citation statements)

References 32 publications

Supporting

Mentioning

104

Contrasting

Order By: Relevance

“…Kiku and Y. Monno et al [34] showed that accuracy of interpolation has improved via reducing the image Laplacian energy. From the observation, the proposed MLRI performs an interpolation under a residual domain, with minimal Laplacian Energy (LE).…”

Section: Related Workmentioning

confidence: 99%

“…From the observation, the proposed MLRI performs an interpolation under a residual domain, with minimal Laplacian Energy (LE). For better optimization, D. Kiku [34] also proposed an algorithm that is Novel demosaicing algorithm. Through incorporating the MLRI approach [35] into GBTF algorithm [36], is one of a modern Bayer demosaicing algorithm.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning Approach for Image Denoising and Image Demosaicing

Prakash¹,

Prasad²,

Prasad³

2017

IJCA

View full text Add to dashboard Cite

Color image normally contain of three main colors at the each pixel, but the digital cameras capture only one color at each pixel using color filter array (CFA). While through capturing in color image, some noise/artifacts is added. So, the both demosaicing and de-noising are the first essential task in digital camera. Here, both the technique can be solve sequentially and independently. A conventional neural network based de-noising technique has applied for the removal of noise/artifacts. Afterwards, frequency based demosaicing with the convolutional neural network based image reconstruction algorithm is apply to acquire another two missing color component. The result analysis presented in this paper demonstrate that our proposed de-nosing and demosaicing exhibits the better performance and it is applicable for a large variety of images.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Deep Learning Approach for Image Denoising and Image Demosaicing

Prakash¹,

Prasad²,

Prasad³

2017

IJCA

View full text Add to dashboard Cite

show abstract

“…The residual interpolation (RI) method has been widely used recently [19][20][21][22][23][24][25]. The RI algorithm exploited the characteristics of the guided filter [26] and showed outstanding performance [19].…”

Section: Introductionmentioning

confidence: 99%

An Effective Directional Residual Interpolation Algorithm for Color Image Demosaicking

Yu¹,

Wang²,

Yang³

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

Abstract:In this paper, we propose an effective directional Bayer color filter array (CFA) demosaicking algorithm based on residual interpolation (RI). The proposed directional interpolation algorithm aims to reduce computational complexity and get more accurate interpolated pixel values in the complex edge areas. We use the horizontal and vertical weights to combine and smooth color difference estimations. Compared with four directional weights in minimized Laplacian residual interpolation, the proposed algorithm not only guarantees the quality of color images but also reduces the computational complexity. Generally, the directional estimations may be inaccurately calculated because of the false edge information in irregular edges. We alleviate it by using a new method to calculate the directional color difference estimations. Experimental results show that the proposed algorithm provides outstanding performance compared with some previous algorithms, especially in the complex edge areas. In addition, it has lower computational complexity and better visual effect.

show abstract

“…This method has proven to be effective. Due to the prominent impact of a precise tentative estimate on the performance of the algorithm, KiKu et al proposed minimized-Laplacian residual interpolation (MLRI) [12] to tentatively generate a more accurate estimate and introduced a weighted average in the guide filter [13]. Valuable information can be obtained from these two articles.…”

Section: Introductionmentioning

confidence: 99%

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

Beyond Color Difference: Residual Interpolation for Color Image Demosaicking

Cited by 138 publications

References 32 publications

Deep Learning Approach for Image Denoising and Image Demosaicing

Deep Learning Approach for Image Denoising and Image Demosaicing

An Effective Directional Residual Interpolation Algorithm for Color Image Demosaicking

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

Contact Info

Product

Resources

About