An edge-adaptive demosaicking method based on image correlation

Abstract

To reduce the cost, size and complexity, a consumer digital camera usually uses a single sensor overlaid with a color filter array (CFA) to sample one of the red-green-blue primary color values, and uses demosaicking algorithm to estimate the missing color values at each pixel. A novel image correlation and support vector machine (SVM) based edge-adaptive algorithm was proposed, which can reduce edge artifacts and false color artifacts, effectively. Firstly, image pixels were separated into edge region and smooth region with an edge detection algorithm. Then, a hybrid approach switching between a simple demosaicking algorithm on the smooth region and SVM based demosaicking algorithm on the edge region was performed. Image spatial and spectral correlations were employed to create middle planes for the interpolation. Experimental result shows that the proposed approach produced visually pleasing full-color result images and obtained higher CPSNR and smaller S-CIELAB ΔE*_ab than other conventional demosaicking algorithms.

Keywords

demosaicking / image correlation / support vector machine / edge-adaptability

References

[1] GunturkB K, GlotzbachJ, AltunbasakY, SchaferR W, MersereauR M. Demosaicking: Color filter array interpolation [J]. IEEE Signal Processing Magazine, 2005, 22(1): 44-54

[2] PeiS C, TamI K. Effective color interpolation in CCD color filter array using signal correlation [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2003, 13(6): 503-513

[3] ChangL L, TanY P. Effective use of spatial and spectral correlations for color filter array demosaicking [J]. IEEE Transactions on Consumer Electronics, 2004, 50(1): 355-365

[4] LukacR, PlataniotisK N. Data-adaptive filters for demosaicking: A framework [J]. IEEE Transactions on Consum Electron, 2005, 51(2): 560-570

[5] GwanggilJ, DuboisE. Demosaicking of noisy bayer-sampled color images with least-squares luma-chroma demultiplexing and noise level estimation [J]. IEEE Transactions on Image Processing, 2013, 22(1): 146-156

[6] ZhouD-w, Xiao-liuS, Wei-mingD. Colour demosaicking with directional filtering and weighting [J]. IET Image Processing, 2012, 6(8): 1084-1092

[7] FerradansS, BertalmioM, CasellesV. Geometry-based demosaicking [J]. IEEE Transactions on Image Processing, 2009, 18(3): 665-670

[8] ChungK L, YangW J, YanW M, WangC C. Demosaicing of color filter array captured images using gradient edge detection masks and adaptive heterogeneity-projection [J]. IEEE Transactions on Image Processing, 2008, 17(12): 2356-2367

[9] TsaiC Y, SongK T. Heterogeneity-projection hard-decision color interpolation using spectral-spatial correlation [J]. IEEE Transactions on Image Processing, 2007, 16(1): 78-91

[10] MenonD, CalvagnoG. Regularization approaches to demosaicking [J]. IEEE Transactions on Image Processing, 2009, 18(10): 2209-2220

[11] MairalJ, EladM, SapiroG. Sparse representation for color image restoration [J]. IEEE Transactions on Image Processing, 2008, 17(1): 53-69

[12] HaoP W, LiY, LinZ C, DuboisE. A geometric method for optimal design of color filter arrays [J]. IEEE Transactions on Image Processing, 2011, 20(3): 709-722

[13] JiaX-f, MaL-y, MaJ-chen. Support vector machines based color filter array interpolation scheme [J]. Journal of Sichuan University: Engineering Science Edition, 2010, 42(3): 145-150

[14] HuangX, ZhangL P. An SVM ensemble approach combining spectral, structural, and semantic features for the classification of high-resolution remotely sensed imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1): 257-272

[15] SahaI, MaulikU, BandyopadhyayS, PlewczynskiD. SVMeFC: SVM ensemble fuzzy clustering for satellite image segmentation [J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(1): 52-55

[16] WuJ X. Efficient HIK SVM learning for image classification [J]. IEEE Transactions on Image Processing, 2012, 21(10): 4442-4453

[17] WangT H, HuaJ L, LiX J, CaiC Y. Rough set-based feature weighting to improve SVM classification [J]. Journal of Computational Information Systems, 2012, 8(8): 3359-3367

[18] MoustakidisS, MallinisG, KoutsiasN, TheocharisJ B, PetridisV. SVM-based fuzzy decision trees for classification of high spatial resolution remote sensing images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2012, 50(1): 149-169

[19] ChenC H, ChenS J, HsiaoP Y. Edge detection on the bayer pattern [C]. IEEE Asia Pacific Conference on Circuits and Systems, 20061132-1135