access icon free Natural image illuminant estimation via deep non-negative matrix factorisation

The influence of environmental light sources affects the colour cast in natural images. In computer vision, biased colours have a significant influence on object recognition and classification. Illuminant estimation aims to eliminate these effects and obtain the image in canonical white light. In this study, the authors propose a deep non-negative matrix factorisation (DeepNMF) method to estimate the illuminant of colour-biased images. DeepNMF deeply factorises the input matrix into multiple layers, separating the image into patches and reshaping each channel of the patch as an [R,G,B] matrix. Based on the diagonal model, they assume that the final layer is the estimated illuminant of each patch. Mean pooling is then used to estimate the illuminant of the overall image. The angular error is used as a metric to test the authors’ method on three commonly used colour constancy datasets. The results show that the proposed method is comparable to state-of-the-art methods, although it is simpler to implement. As the proposed method uses a single image as input, it does not require a learning process.

Inspec keywords: computer vision; matrix decomposition; image colour analysis; image classification

Other keywords: diagonal model; colour-biased images; computer vision; object classification; object recognition; environmental light sources; canonical white light; biased colours; colour constancy dataset; natural image illuminant estimation; colour cast; deepNMF method; deep nonnegative matrix factorisation; input matrix; mean pooling; angular error

Subjects: Algebra; Algebra; Image recognition; Computer vision and image processing techniques

References

    1. 1)
      • 14. Gao, S., Yang, K., Li, C., et al: ‘A color constancy model with double-opponency mechanisms’. Proc. of the IEEE Int. Conf. Computer Vision, 2013, pp. 929936.
    2. 2)
      • 25. Barnard, K., Ciurea, F., Funt, B.: ‘Sensor sharpening for computational color constancy’, J. Opt. Soc. Am., 2001, 18, (11), pp. 27282743.
    3. 3)
      • 39. Shi, L., Funt, B., Xiong, W.: ‘Illumination estimation via nonnegative matrix factorization’, J. Electron. Imaging, 2012, 21, (3), pp. 033022-1033022-13.
    4. 4)
      • 2. Hordley, S.D.: ‘Scene illuminant estimation: past, present, and future’, Color Res. Appl., 2006, 31, (4), pp. 303314.
    5. 5)
      • 11. Gijsenij, A., Gevers, T., Van De Weijer, J.: ‘Improving color constancy by photometric edge weighting’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (5), pp. 918929.
    6. 6)
      • 13. Ebner, M.: ‘Color constancy based on local space average color’, Mach. Vis. Appl., 2009, 20, (5), pp. 283301.
    7. 7)
      • 40. Shi, W., Loy, C.C., Tang, X.: ‘Deep specialized network for illuminant estimation’. European Conf. Computer Vision, 2016, pp. 371387.
    8. 8)
      • 19. Gehler, P.V., Rother, C., Blake, A., et al: ‘Bayesian color constancy revisited’. IEEE Conf. Computer Vision and Pattern Recognition, June 2009, pp. 18.
    9. 9)
      • 16. Finlayson, G.D., Hordley, S.D., Hubel, P.M.: ‘Color by correlation: a simple, unifying framework for color constancy’, IEEE Trans. Pattern Anal. Mach. Intell., 2001, 23, (11), pp. 12091221.
    10. 10)
      • 20. Joze, H.R.V., Drew, M.S.: ‘Exemplar-based color constancy and multiple illumination’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (5), pp. 860873.
    11. 11)
      • 6. Land, E.H.: ‘Recent advances in retinex theory’, in Ottoson, D., Zeki, S. (Eds.) ‘Central and peripheral mechanisms of colour vision’ (Palgrave Macmillan UK, 1985), pp. 517.
    12. 12)
      • 38. Funt, B., Xiong, W.: ‘Estimating illumination chromaticity via support vector regression’. Color and Imaging Conf., Society for Imaging Science and Technology, 2004, (1), pp. 4752.
    13. 13)
      • 26. Worthey, J.A., Brill, M.H.: ‘Heuristic analysis of von Kries color constancy’, J. Opt. Soc. Am., 1986, 3, (10), pp. 17081712.
    14. 14)
      • 24. Finlayson, G.D., Drew, M.S., Funt, B.V.: ‘Spectral sharpening: sensor transformations for improved color constancy’, J. Opt. Soc. Am., 1994, 11, (5), pp. 15531563.
    15. 15)
      • 31. Cheng, D., Prasad, D.K., Brown, M.S.: ‘Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution’, J. Opt. Soc. Am. A, 2014, 31, (5), pp. 10491058.
    16. 16)
      • 17. Cardei, V.C., Funt, B., Barnard, K.: ‘Estimating the scene illumination chromaticity by using a neural network’, J. Opt. Soc. Am, 2002, 19, (12), pp. 23742386.
    17. 17)
      • 21. Lee, D.D., Seung, H.S.: ‘Algorithms for non-negative matrix factorization’. Advances in Neural Information Processing Systems, 2001, pp. 556562.
    18. 18)
      • 1. Ebner, M.: ‘Color constancy’ (John Wiley & Sons, 2007).
    19. 19)
      • 27. Funt, B.V., Lewis, B.C.: ‘Diagonal versus affine transformations for color correction’, J. Opt. Soc. Am., 2000, 17, (11), pp. 21082112.
    20. 20)
      • 34. Gehler, P.V., Rother, C., Blake, A., et al: ‘Bayesian color constancy revisited’. IEEE Conf. Computer Vision and Pattern Recognition, June 2008, pp. 18.
    21. 21)
      • 41. Bianco, S., Cusano, C., Schettini, R.: ‘Single and multiple illuminant estimation using convolutional neural networks’, IEEE Trans. Image Process., 2017, 26, (9), pp. 43474362.
    22. 22)
      • 10. Van De Weijer, J., Gevers, T., Gijsenij, A.: ‘Edge-based color constancy’, IEEE Trans. Image Process., 2007, 16, (9), pp. 22072214.
    23. 23)
      • 23. Chong, H.Y., Gortler, S.J., Zickler, T.: ‘The von Kries hypothesis and a basis for color constancy’. IEEE 11th Int. Conf. Computer Vision, October 2007, pp. 18.
    24. 24)
      • 3. Gijsenij, A., Gevers, T., Van De Weijer, J.: ‘Computational color constancy: survey and experiments’, IEEE Trans. Image Process., 2011, 20, (9), pp. 24752489.
    25. 25)
      • 30. Boutsidis, C., Gallopoulos, E.: ‘SVD based initialization: a head start for nonnegative matrix factorization’, Pattern Recognit., 2008, 41, (4), pp. 13501362.
    26. 26)
      • 18. Gijsenij, A., Gevers, T.: ‘Color constancy using natural image statistics’. IEEE Conf. Computer Vision and Pattern Recognition, June 2007, pp. 18.
    27. 27)
      • 12. Finlayson, G.D., Schaefer, G.: ‘Convex and non-convex illuminant constraints for dichromatic colour constancy’. Proc. of the 2001 IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2001, vol. 1, pp. I598.
    28. 28)
      • 22. Funt, B., Jiang, H.: ‘Nondiagonal color correction’. Int. Conf. Image Processing Proc., September 2003, vol. 1, pp. I481.
    29. 29)
      • 7. Yang, M.T., Lo, K.H., Chiang, C.C., et al: ‘Moving cast shadow detection by exploiting multiple cues’, IET Image Process., 2008, 2, (2), pp. 95104.
    30. 30)
      • 28. West, G., Brill, M.H.: ‘Necessary and sufficient conditions for von Kries chromatic adaptation to give color constancy’, J. Math. Biol., 1982, 15, (2), pp. 249258.
    31. 31)
      • 35. Barnard, K., Martin, L., Funt, B., et al: ‘A dataset for color research’, Color Res. Appl., 2002, 27, (3), pp. 147151.
    32. 32)
      • 9. Finlayson, G.D., Trezzi, E.: ‘Shades of gray and colour constancy’. Color and Imaging Conf., Society for Imaging Science and Technology, January 2004, vol. 2004, (1), pp. 3741.
    33. 33)
      • 37. Yang, K.F., Gao, S.B., Li, Y.J.: ‘Efficient illuminant estimation for color constancy using grey pixels’. Proc. of the IEEE Conf. Computer Vision and Pattern Recognition, 2015, pp. 22542263.
    34. 34)
      • 43. Nvidia C. U. D. A.: ‘Programming guide’ (Nvidia, 2008).
    35. 35)
      • 15. Finlayson, G.D., Hordley, S.D., Tastl, I.: ‘Gamut constrained illuminant estimation’, Int. J. Comput. Vis., 2006, 67, (1), pp. 93109.
    36. 36)
      • 29. Brill, M.H.: ‘Minimal von Kries illuminant invariance’, Color Res. Appl., 2008, 33, (4), pp. 320323.
    37. 37)
      • 8. Rizzi, A., Gatta, C., Marini, D.: ‘Color correction between gray world and white patch’. Int. Society for Optics and Photonics Electronic Imaging 2002, June 2002, pp. 367375.
    38. 38)
      • 36. Tan, R.T., Nishino, K., Ikeuchi, K.: ‘Color constancy through inverse-intensity chromaticity space’, J. Opt. Soc. Am., 2004, 21, (3), pp. 321334.
    39. 39)
      • 42. Hordley, S.D., Finlayson, G.D.: ‘Re-evaluation of color constancy algorithm performance’, J. Opt. Soc. Am., 2006, 23, (5), pp. 10081020.
    40. 40)
      • 4. Jha, R.K., Biswas, P.K., Chatterji, B.N.: ‘Contrast enhancement of dark images using stochastic resonance’, IET Image Process., 2012, 6, (3), pp. 230237.
    41. 41)
      • 33. Shi, L., Funt, B.: ‘Re-processed version of the Gehler color constancy dataset of 568 images’. Simon Fraser University, 2010, 1, (2), p. 3.
    42. 42)
      • 5. Land, E.H.: ‘The retinex theory of color vision’, Sci. Am., 1977, 237, (6), pp. 108128.
    43. 43)
      • 32. Ciurea, F., Funt, B.: ‘A large image database for color constancy research’. Color and Imaging Conf., Society for Imaging Science and Technology, January 2003, (1), pp. 160164..
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-ipr.2016.1058
Loading

Related content

content/journals/10.1049/iet-ipr.2016.1058
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading