Color image analysis by quaternion-type moments. (English) Zbl 1331.68266

Summary: In this paper, by using the quaternion algebra, the conventional complex-type moments (CTMs) for gray-scale images are generalized to color images as quaternion-type moments (QTMs) in a holistic manner. We first provide a general formula of QTMs from which we derive a set of quaternion-valued QTM invariants (QTMIs) to image rotation, scale and translation transformations by eliminating the influence of transformation parameters. An efficient computation algorithm is also proposed so as to reduce computational complexity. The performance of the proposed QTMs and QTMIs are evaluated considering several application frameworks ranging from color image reconstruction, face recognition to image registration. We show they achieve better performance than CTMs and CTM invariants (CTMIs). We also discuss the choice of the unit pure quaternion influence with the help of experiments. \((i-j-k)/\sqrt 3\) appears to be an optimal choice.


68U10 Computing methodologies for image processing
68T10 Pattern recognition, speech recognition


Full Text: DOI HAL


[1] Subakan, ON; Vemuri, BC, A quaternion framework for color image smoothing and segmentation, Int. J. Comput. Vis., 91, 233-250, (2011) · Zbl 1235.68315
[2] Koschan, A., Abidi, M.: Digital Color Image Processing. Wiley, Hoboken (2008)
[3] Sangwine, SJ, Fourier transforms of colour images using quaternion or hypercomplex, numbers, Electron. Lett., 32, 1979-1980, (1996)
[4] Pei, S.C., Cheng, C.M.: A novel block truncation coding of color images by using quaternion-moment-preserving principle. In: Proc. IEEE Int. Symp. Circuits and Systems, vol. 2, pp. 684-687 (1996).
[5] Pei, SC; Cheng, CM, Color image processing by using binary quaternion-moment preserving thresholding technique, IEEE Trans. Image Process., 8, 22-35, (1999)
[6] Bihan, N.L., Sangwine, S.J.: Color image decomposition using quaternion singular value decomposition’. In: Proc. 2003 Int. Conf. Visual Information Engineering (VIE 2003), pp. 113-116 (2003).
[7] Pei, S.C., Cheng, C.M.: Quaternion matrix singular value decomposition and its applications for color image processing. In: Proc. 2003 Int. Conf. Image Processing (ICIP 2003), vol. 1, pp. 805-808 (2003)s.
[8] Bihan, N.L., Sangwine, S.J.: Quaternion principal component analysis of color images. In: Proc. 2003 10th IEEE Int. Conf. Image Processing (ICIP 2003), vol. 1, pp. 809-812 (2003). · Zbl 1372.94300
[9] Ell, TA; Sangwine, SJ, Hypercomplex Fourier transforms of color images, IEEE Trans. Image Process., 16, 22-35, (2007) · Zbl 1279.94014
[10] Alexiadis, DS; Sergiadis, GD, Estimation of motions in color image sequences using hypercomplex Fourier transforms, IEEE Trans. Image Process., 18, 168-187, (2009) · Zbl 1371.94021
[11] Assefa, D; Mansinha, L; Tiampo, KF; Rasmussen, H; Abdella, K, Local quaternion Fourier transform and color image texture analysis, Signal Process., 90, 1825-1835, (2010) · Zbl 1197.94021
[12] Chen, B.J., Shu, H.Z., Zhang, H., Chen, G., Luo, L.M.: Color image analysis by quaternion Zernike moments. In: Proc. 2010 20th Int. Conf. Pattern Recognition (ICPR2010), 2010, pp. 625-628 (2010)
[13] Guo, LQ; Zhu, M, Quaternion Fourier-Mellin moments for color image, Pattern Recognit., 44, 187-195, (2011) · Zbl 1211.68353
[14] Sun, YF; Chen, SY; Yin, BC, Color face recognition based on quaternion matrix representation, Pattern Recognit. Lett., 32, 597-605, (2011)
[15] Chen, BJ; Shu, HZ; Zhang, H; Chen, G; Toumoulin, C; Dillenseger, JL; Luo, LM, Quaternion Zernike moments and their invariants for color image analysis and object recognition, Signal Process., 92, 308-318, (2012)
[16] Rizo-Rodríguez, D; Méndez-Vázquez, H; García-Reyes, E, Illumination invariant face recognition using quaternion-based correlation filters, J. Math. Imaging Vis., 45, 164-175, (2013) · Zbl 1276.68138
[17] Ell, T.A.: Hypercomplex spectral transforms. Ph.D. dissertation, Minnesota Univ., Minneapolis, USA (1992)
[18] Bülow, T.: Hypercomplex spectral signal representations for image processing and analysis. Ph.D. dissertation, University of Kiel, Kiel, Germany (1999)
[19] Arena, P., Fortuna, L., Occhipinti, L.: Neural networks for quaternion valued function approximation. In: Proc. IEEE Int. Symp. Circuits and Systems, vol. 6, pp. 307-310 (1994) · Zbl 1279.94014
[20] Nitta, T.: A quaternary version of the back-propagation algorithm. In: Proc. IEEE Int. Conf. Neural Networks (ICNN’95), vol. 5, 2753-2756 (1995)
[21] Chan, W.L., Choi, H., Baraniuk, G.: Directional hypercomplex wavelets for multidimensional signal analysis and processing. In: Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2004), pp. 996-999 (2004)
[22] Bayro-Corrochano, E, The theory and use of the quaternion wavelet transform, J. Math. Imaging Vis., 24, 19-35, (2006)
[23] Bihan, N.L., Buchholz, S.: Quaternionic independent component analysis using hypercomplex nonlinearities. In: Proc. IMA 7th Conf. Mathematics in, Signal Processing, pp. 1-4 (2006). · Zbl 1369.94032
[24] Via, J; Palomar, DP; Vielva, L, Quaternion ica from second-order statistics, IEEE Trans. Signal Process., 59, 1586-1600, (2011)
[25] Hitzer, E.: Quaternionic Fourier-Mellin Transform. arXivpreprint arXiv:1306.1669 (2013)
[26] Li, YN, Quaternion polar harmonic transforms for color images, IEEE Signal Process. Lett., 20, 803-806, (2013)
[27] Batard, T., Berthier, M., Saint-Jean, C.: Clifford-Fourier transform for color image processing. In: Geometric Algebra Computing, pp. 135-162. Springer, London (2010) · Zbl 1214.68423
[28] Mennesson, J., Saint-Jean, C., Mascarilla, L.: Color object recognition based on a Clifford Fourier transform. Guide to Geometric Algebra in Practice, pp. 175-191. Springer, London (2011) · Zbl 1290.68110
[29] Hitzer, E., Sangwine, S.J. (eds.): Quaternion and Clifford Fourier transforms and wavelets. In: Trends in Mathematics (TIM), Birkhauser, Basel (2013) · Zbl 1273.42007
[30] Mennesson, J; Saint-Jean, C; Mascarilla, L, Color Fourier-Mellin descriptors for image recognition, Pattern Recogn. Lett., 40, 27-35, (2014)
[31] Pearson, J.K., Bisset, D.L.: Neural networks in the clifford domain. In: Proc. IEEE World Congress on Neural Networks, vol. 3, 1465-1469 (1994)
[32] Bayro-Corrochano, EJ; Arana-Daniel, N, Clifford support vector machines for classification, regression, and recurrence, IEEE Trans. Neural Netw., 21, 1731-1746, (2010)
[33] Bahri, M; Hitzer, E, Clifford algebra CI\(_{3, 0}\)-valued wavelet transformation, Clifford wavelet uncertainty inequality and Clifford Gabor wavelets, Int. J. Wavelets Multiresolution Inf. Process., 5, 997-1019, (2007) · Zbl 1197.42019
[34] Bujack, R; Scheuermann, G; Hitzer, E, Detection of outer rotations on 3D-vector fields with iterative geometric correlation and its efficiency, Adv. Appl. Clifford Alg., (2013) · Zbl 1263.15021
[35] Hitzer, E; Nitta, T; Kuroe, Y, Applications of clifford’s geometric algebra, Adv. Appl. Clifford Alg., 23, 377-404, (2013) · Zbl 1269.15022
[36] Flusser, J., Zitova, B., Suk, T.: Moments and moment invariants in pattern recognition. Wiley, Chichester (2009) · Zbl 1183.68530
[37] Shu, HZ; Luo, LM; Coatrieux, JL, Moment-based approaches in image part 1: basic features, IEEE Eng. Med. Biol. Mag., 26, 70-74, (2007)
[38] Khotanzad, A; Hong, YH, Invariant image recognition by Zernike moments, IEEE Trans. Pattern Anal. Machine Intell., 12, 489-497, (1990)
[39] Lin, YH; Chen, CH, Template matching using the parametric template vector with translation, rotation and scale invariance, Pattern Recognit., 41, 2413-2421, (2008) · Zbl 1138.68509
[40] Yang, CY; Chou, JJ, Classification of rotifers with machine vision by shape moment invariants, Aquac. Eng., 24, 33-57, (2000)
[41] Dai, XB; Shu, HZ; Luo, LM; Han, GN; Coatrieux, JL, Reconstruction of tomographic images from limited range projections using discrete Radon transform and tchebichef moments, Pattern Recognit., 43, 1152-1164, (2010) · Zbl 1187.68443
[42] Zhang, H; Shu, HZ; Coatrieux, G; Zhu, J; Wu, QMJ; Zhang, Y; Zhu, HQ; Luo, LM, Affine Legendre moment invariants for image watermarking robust to geometric distortions, IEEE Trans. Image Process., 20, 2189-2199, (2011) · Zbl 1372.94300
[43] Hamilton, W.R.: Elements of Quaternions. Longmans Green, London (1866)
[44] Chong, C.W., Raveendran, P., Mukundan, R.: Translation invariants of zernike moments. Pattern Recognit. 36(8), 1765-1773 (2003) · Zbl 1055.68135
[45] Liao, SX; Pawlak, M, On image analysis by moments, IEEE Trans. Pattern Anal. Machine Intell., 18, 254-266, (1996)
[46] Liao, SX; Pawlak, M, On the accuracy of Zernike moments for image analysis, IEEE Trans. Pattern Anal. Machine Intell., 20, 1358-1364, (1998)
[47] Suk, T., Flusser, J.: Affine moment invariants of color images. In: Proc. CAIP 2009, vol. LNCS5702, pp. 334-341 (2009)
[48] Shams, L; Malsburg, CVD, The role of complex cells in object recognition, Vis. Res., 42, 2547-2554, (2002)
[49] Shi, G; Shanechi, MM; Aarabi, P, On the importance of phase in human speech recognition, IEEE Trans. Audio Speech Lang. Process, 14, 1867-1874, (2006)
[50] Shu, HZ; Luo, LM; Han, GN; Coatrieux, JL, A general method to derive the relationship between two sets of Zernike coefficients corresponding to different aperture sizes, J. Opt. Soc. Am. A, 23, 1960-1966, (2006)
[51] Zhang, H; Shu, HZ; Haigron, P; Li, BS; Luo, LM, Construction of a complete set of orthogonal Fourier-Mellin moment invariants for pattern recognition applications, Image Vis. Comput., 28, 38-44, (2010)
[52] Walia, E; Singh, C; Goyal, A, On the fast computation of orthogonal Fourier-Mellin moments with improved numerical stability, J. Real-Time Image Process., 7, 247-256, (2012)
[53] Liu, C; Huang, XH; Wang, M, Fast computation of Zernike moments in polar coordinates, IET Image Process., 6, 996-1004, (2012)
[54] Singh, C., Walia, E., Pooja, S., Upneja, R.: Analysis of algorithms for fast computation of pseudo Zernike moments and their numerical stability. Digital Signal Process. 22(6), 1031-1043 (2012)
[55] Ell, T., Sangwine, S.J.: Decomposition of 2D hypercomplex Fourier transforms into pairs of complex Fourier transforms. In: Proc. Eusipco., vol. 2 (2000) · Zbl 1279.94014
[56] Qi, Q., Hu, Y.M., Zhang, C.Y.: A new color pattern recognition algorithm based on quaternion correlation. In: Proc. IEEE Int. Conf. Networking, Sensing and Control (CNSC 2008), pp. 462-466 (2008)
[57] Zuo, W., Wang, W.J.: Color watermarking algorithm based on modified qfft and dct. In: Proc. 2010 Int. Conf. Optoelectronics and Image Processing (ICOIP), vol. 1, pp. 328-331 (2010)
[58] Bas, P., Nihan, N.L., Chassery, J.M.: Color image watermarking using quaternion fourier transform. In: Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP 2003), vol. III, pp. 521-524 (2003)
[59] Moxey, CE; Sangwine, SJ; Ell, TA, Hypercomplex correlation techniques for vector images, IEEE Trans. Signal Process., 51, 1941-1953, (2003) · Zbl 1369.94032
[60] Nene, S.A., Nayar, S.K., Murase, H.: Columbia Object Image Library (COIL-100), Tech. Rep. CUCS-006-96 (1996)
[61] Teh, CH; Chin, RT, On image analysis by the method of moments, IEEE Trans. Pattern Anal. Machine Intell., 10, 496-513, (1988) · Zbl 0709.94543
[62] Chen, BJ; Shu, HZ; Chen, G; Ge, J; Luo, LM, Color face recognition based on quaternion Zernike moment invariants and quaternion bp neural network, Appl. Mech. Mater., 446-447, 1034-1039, (2014)
[63] Spacek, L.: (2008, June 20). Description of the Collection of Facial Images [Online]. Available: http://cswww.essex.ac.uk/mv/allfaces/index.html
[64] Chen, BJ; Shu, HZ; Zhang, H; Coatrieux, G; Luo, LM; Coatrieux, JL, Combined invariants to similarity transformation and to blur using orthogonal Zernike moments, IEEE Trans. Image Process., 20, 345-360, (2011) · Zbl 1372.94038
[65] Wang, WX; Luo, DJ; Li, WS, Algorithm for automatic image registration on harris-Laplace features, J. Appl. Remote Sens., 3, 1-13, (2009)
[66] Zhang, Z; Blum, RS, A hybrid image registration technique for a digital camera image fusion application, Inf. Fusion, 2, 135-149, (2001)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.