Abstract
In this paper a colourizing technique based on some tensor properties is proposed. Toward this goal, it is clarified that tensor decomposition possesses the ability of extracting and gathering overall colour information. The methodology considers a grayscale pixel as a balanced vector in RGB colour space. Any deviation to unbalance the colour coordinates means adding colour information to the initial pixel. For finding the appropriate direction of deviation, the proposed technique uses tensor decomposition to extract colour information from a block divided exemplar colour image called reference. Then apply this direction to the best matched block of the grayscale image based on a similarity criterion while its basic structure is preserved. Finally by retrieving from tensor space into spatial domain the conversion is fulfilled. The similarity criteria for block matching and the plausibility of the system output are the most challenging problems. Both images blocks are considered as 3D tensors and Tucker3 with its unique properties is utilized for transferring the colour information. The novelty, simplicity, accuracy, and the conversion speed are some parameters which are introduced and developed by the proposed algorithm. This approach proves that in comparison with spatial or frequency domain, transforming the colour information into tensor space make it more clear and give us better ability of rendering. The results show that the proposed algorithm is able to present the average structural similarity up to 94%.
Similar content being viewed by others
References
Bader BW, Kolda TG et al (2016) MATLAB Tensor Toolbox Version 2.6, Available online. URL: http://www.sandia.gov/~tgkolda/TensorToolbox/
Bugeau A, Ta V-T, Papadakis N (2014) Variational exemplar-based image colorization. IEEE Trans Image Process 23(1):298–307
Burger W, Burge MJ (2009) Principal of Digital Signal Processing. British Library Cataloguing in Publication Data, Springer-Verlag London Limited
Casaca W, Gomez-Nieto E, Ferreira COL, Tavares G, Pagliosa P, Paulovich F, Nonato LG, Paiva A (2012) Colorization by multidimensional projection. In: XXV SIBGRAPI Conference on Graphics, Patterns and Images
Charpiat G, Hofmann M, Schölkopf B (2008) Automatic image colorization via multimodal predictions. In: ECCV 2008: 10th European Conference on Computer Vision–ECCV, Marseille, france, 2008 procedding, Part III - Springer, pp 126-139
Chatzichristofis SA, Boutalis YS (2008) Fcth: Fuzzy color and texture histogram-a low level feature for accurate image retrieval. Image Analysis for Multimedia Interactive Services. WIAMIS'08. Ninth International Workshop on. IEEE
Cheng Z, Cheng Z, Sheng B (2015) Deep Colorization. In:The IEEE International Conference on Computer Vision (ICCV), 2015 I.E. International Conference on, pp. 415-423
Chia AY-S, Zhuo S, Gupta RK, Tai Y-W, Cho S-Y, Tan P, Lin S (2011) Semantic colorization with internet images. In: Proceedings of the 2011 SIGGRAPH Asia Conference Volume 30 Issue 6, December 2011
Cichocki A, Mandic D, Phan A-H, Caiafa C, Zhou G, Zhao Q, De Lathauwer L (2014) Tensor Decompositions for Signal Processing Applications. In: IEEE Singnal Processing Magazine, pp 1053–5888
Dang-Nguyen D-T, Pasquini C, Conotter V, Boato G (2015) RAISE–A raw images dataset for digital image forensics. In: ACM Multimedia Systems, Portland, Oregon
De Lathauwer L, De Moor B, Vandewalle J (2000) A multilinear singular value decomposition. SIAM J Matrix Anal Appl 21(4):1253–1278
Deshpande A, Rock J, Forsyth D (2015) Learning large-scale automatic image colorization. In Proceedings of the IEEE International Conference on Computer Vision, pp 567–575
Doulamis AD, Doulamis ND, Kollias SD (2000) A fuzzy video content representation for video summarization and content-based retrieval. Signal Process 80(6):1049–1067
Drew MS, Finlayson GD (2008) Realistic colorization via the structure tensor. In: ICIP, 978–1–4244-1764-3/08, IEEE
Dunlavy DM, Kolda TG, Kegelmeyer WP (2006) Multilinear algebra for analyzing data with multiple linkages. Tech. Rep. SAND2006–2079, Sandia National Laboratories, Albuquerque, NM and Livermore, CA
Gupta RK, Chia AY-S, Rajan D, Ng ES, Zhiyong H (2012) Image colorization using similar images. In: Proceedings of the 20th ACM international conference on Multimedia, pp 369–378
Hu M, Ou B, Xiao Y (2016) Efficient Image Colorization Based on Seed Pixel Selection. In: Multimed Tools Appl (2017) 76:23567. https://doi.org/10.1007/s11042-016-4112-9, Springer
Huang H, Li X, Zhao H, Nie G, Hu Z, Xiao L (2014) Manifold-preserving image colorization with nonlocalestimation. In: Mult imed Tools Appl. Springer(2015) 74: 7555. https://doi.org/10.1007/s11042-014-1991-5
Irony R, Cohen-Or D, Lischinski D (2005) Colorization by example. In: Proceeding of the 16th Eurographics conference on rendering techniques (EGSR 2005) Switzerland (2005)
Kolda T, Bader B (2009) Tensor decompositions and applications. SIAM Rev 51(3):455–500
Larsson G, Maire M, Shakhnarovich G (2016) Learning Representations for Automatic Colorization. In: Leibe B et al (eds) ECCV 2016, Part IV, LNCS 9908. Springer International Publishing AG 2016, pp 577–593
Levin A, Lischinski D, Weiss Y (2004) Colorization using optimization. ACM Trans Graphics 23:689–694
Li B, Zhao F, Su Z, Liang X, Lai Y-K, Rosin PL (2017) Example-based image colorization using locality consistent sparse representation. IEEE Trans Image Process 26(11):5188–5202
Lu H, Plataniotis KN, Venetsanopoulos AN (2011) A survey of mul-tilinear subspace learning for tensor data. Pattern Recognit 44(7):1540–1551
Lu H, Plataniotis KN, Venetsanopoulos AN (2014) Multilinear Subspace Learning. In: Machine Learning & Pattern Recognition Series, 1th ed. CRC Press Taylor & Francis, Boca Raton
Morten Morup (2011) Applications of tensor (multiway array) factorizations and decompositions in data mining, vol 1. Wiley, New York
Peter P, Kaufhold L, Weickert J (2016) Turning diffusion-based image colorization into efficient color compression. IEEE Trans Image Process. 2016 Nov 10. Published in: IEEE Transactions on Image Processing (Volume: 26, Issue: 2, Feb. 2017) pp 860-869
Pierre F, Aujol J-F, Bugeau A, Papadakis N, Ta V-T (2014) Exemplar-based colorization in RGB color space. In: Internationnal Conference on Image Processing, Oct, Paris, France. pp 1–5. <hal-01019627>
Pierre F, Aujol JF, Bugeau A, Papadakis N, Ta VT (2015) Luminance-chrominance model for image colorization. SIAM Journal on Imaging Sciences 8(1):536–563
Saravanan C (2010) Color Image to Grayscale Image Conversion. In: Computer Engineering and Applications (ICCEA), 2010 Second International Conference on
Sivalingam R, Sivalingam R, Boley D, Morellas V, Papanikolopoulos N (2014) Tensor sparse coding for positive definite matrices. IEEE Trans Pattern Anal Mach Intell 36(3):592–605
Vertan C, Boujemaa N (2000). Using fuzzy histograms and distances for color image retrieval. Challenge of image retrieval, Brighton
Vervliet N, Debals O, Sorber L, Van Barel M, De Lathauwer L (2017) Tensorlab 3.0, Available online. URL: http://www.tensorlab.net
Wan Y, Xie Q (2016) A Novel Framework for Optimal RGB to Grayscale Image Conversion. In: Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2016 8th International Conference on
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. In: IEEE Transactions on Image Processing (Volume: 13, Issue: 4, April 2004) pp 600-612
Welsh T, Ashikhmin M, Mueller K (2002) Transferring color to greyscale images. ACM Trans Graph 21(3):277–280
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rahmanian Koushkaki, H., Salehi, M.R. & Abiri, E. Automatic colourization of grayscale images based on tensor decomposition. Multimed Tools Appl 77, 20043–20063 (2018). https://doi.org/10.1007/s11042-017-5419-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-5419-x