Author: |
黃智瑋 Jhih-Wei Huang |
---|---|
Thesis Title: |
基於胡伯損失函數的殘量內插解馬賽克演算法 Huber-Loss Based Residual Interpolation for Image Demosaicking |
Advisor: |
鍾國亮
Kuo-Liang Chung |
Committee: |
貝蘇章
Soo-Chang Pei 范國清 Kuo-Chin Fan 廖弘源 Hong-Yuan Liao 陳建中 Jiann-Jone Chen |
Degree: |
碩士 Master |
Department: |
電資學院 - 資訊工程系 Department of Computer Science and Information Engineering |
Thesis Publication Year: | 2016 |
Graduation Academic Year: | 104 |
Language: | 中文 |
Pages: | 30 |
Keywords (in Chinese): | Bayer色彩濾波陣列 、影像解馬賽克 、殘量 、內插 、Huber損失函數 、CPSNR 、S-CIELAB 、SSIM |
Keywords (in other languages): | Bayer color filter array (CFA), Image demosaicking, residual, interpolation, Huber-loss function, CPSNR, S-CIELAB, SSIM |
Reference times: | Clicks: 452 Downloads: 3 |
Share: |
School Collection Retrieve National Library Collection Retrieve Error Report |
為了節省硬體的成本,現在的數位相機大多採用單一感光元件並配合RGB色彩濾波陣列來捕捉真實世界的場景。由於拍攝到的影像中,每一個像素只包含紅、綠、藍其中一種主色,因此這類的影像我們稱之為馬賽克影像。由於全彩影像是人們較為接受的,將馬賽克影像轉換成全彩影像是必要的。本論文提出一套結合Huber損失函數的殘量內插解馬賽克演算法。所提方法中,利用Huber損失函數來壓抑離群值對線性回歸的結果。同時也提出利用兩種遮罩的結合方法,來取得較好的影像品質。我們實作三種代表性的測試影像,實驗結果顯示本論文所提出的方法有較好的影像品質。
To save hardware cost, most modern digital cameras employ the single-sensor
technology together with the red-green-blue (RGB) color filter array (CFA) structure to capture real-world scenes. Since each pixel in the captured image is only composed of one primary color, such an image is usually referred to as the mosaic image. For the purpose of visual display, it is necessary to convert the captured mosaic image into the full-color RGB image. In this thesis, we propose a novel residual interpolation for image demosaicking associated with Huber-loss function. In the proposed method, we use Huber-loss function to decrease the effect of outliers which affect the result of linear regression. Besides, we also use two different sizes of mask to fuse the result of tentative demosaicked image. Based on 3 image datasets, experimental results show that the demosaicked image generated by the proposed demosaicking method has better quality in terms of visual signal-to-noise ratio (CPSNR) and demonstrates less
color artifact when compared with Tanaka et al.’s methods.
[1] R. Lukac, Single-sensor imaging: methods and applications for digital cameras, CRC Press, 2008.
[2] B. E. Bayer, “Color imaging array,” U.S. Patent 3 971 065, Jul. 1976.
[3] B. K. Gunturk, J. Glotzbach, Y. Altunbasak, R. W. Schafer, and R. M. Mersereau, “Demosaicking: Color filter array interpolation,” IEEE Signal Processing Magazine, vol. 22, no. 1, pp. 44–54, Jan. 2005.
[4] X. Li, B. Gunturk, and L. Zhang, “Image demosaicing: A systematic survey,” Processing SPIE, vol. 6822, pp. 68221J-1–68221J-15, Jan. 2008.
[5] D. Menon and G. Calvagno, “Color image demosaicking: An overview,” Signal Processing: Image Communication, vol. 26, nos. 8–9, pp. 518–533, Oct. 2011.
[6] T. Sakamoto, C. Nakanishi, and T. Hase, “Software pixel interpolation for digital still cameras suitable for a 32-bit MCU,” IEEE Transactions on Consumer Electronics, vol. 44, no. 4, pp. 1342-1352, 1988.
[7] D. R. Cok, “Signal processing method and apparatus for producing interpolated chrominance values in a sampled color image signal,” U.S. Patent 4642678, Feb. 10, 1987.
[8] R. H. Hibbard, “Apparatus and method for adaptively interpolating a full color image utilizing luminance gradients,” U.S. Patent 5382976, Jan. 17, 1995.
[9] J. F. Hamilton, Jr., and J. E. Adams, Jr., “Adaptive color plan interpolation in single sensor color electronic camera,” U.S. Patent 5629734, May 13, 1997.
[10] D. Kiku, Y. Monno, M. Tanaka, and M. Okutomi, “Residual interpolation for color image demosaicking,” Proceedings of IEEE International Conference on Image Processing (ICIP), Sep. 2013, pp. 2304–2308.
[11] D. Kiku, Y. Monno, M. Tanaka, and M. Okutomi, “Minimized-Laplacian residual interpolation for color image demosaicking,” Processing SPIE, vol. 9023, pp. 90230L-1–90230L-8, Mar. 2014.
[12] D. Kiku, Y. Monno, M. Tanaka, and M. Okutomi, “Beyond Color Difference: Residual Interpolation for Color Image Demosaicking,” IEEE Transactions on Image Processing, vol. 25, no. 3, pp. 1288-1300, Mar. 20162r.
[13] W. Ye and K.K. Ma, “Color Image Demosaicking Using Iterative Residual Interpolation,” IEEE Transactions on Image Processing, vol. 24, no.12, pp. 5879-5891, 2015.
[14] Peter J. Huber, “Robust Estimation of a Location Parameter,” Annals of Statistics, vol. 35, no.1, pp.73-101, 1964.
[15] I. Pekkucuksen and Y. Altunbasak, “Gradient based threshold free color filter array interpolation,” Proceedings of IEEE International Conference on Image Processing (ICIP), pp. 137–140, Sep. 2010.
[16] K. He, J. Sun, and X. Tang, “Guided image filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1397–1409, Jun. 2013.
[17] L. Zhang, X. Wu, A. Buades, and X. Li, “Color demosaicking by local directional interpolation and nonlocal adaptive thresholding,” Journal of Electronic Imaging, vol. 20, no. 2, pp. 023016-1–023016-16, Jun. 2011.
[18] True Color Kodak Images. [Online]. Available: http://r0k.us/graphics/kodak/
[19] Bradley J. Lucier’s Page. [Online]. Available: http://www.math.purdue.edu/~lucier/
[20] Kodak Image Dataset (High-Resolution Version). [Online]. Available: http://www.math.purdue.edu./~lucier/PHOTO_CD/BMP_IMAGES/
[21] R. W. G. Hunt, Measuring Colour, 2nd ed. Chichester, U.K.: Ellis Horwood,1995.
[22] W. Lu and Y. P. Tan, “Color filter array demosaicking: New method and performance measures,” IEEE Transactions on Image Processing, vol. 12, no. 10, pp.1194-1210, 2003.
[23] Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, “Image Quality Assessment: From Error Visibility to Structural Similarity,” IEEE Transactions on Image Processing, vol. 13, no. 4, pp.1-14, Apr. 2004.