DOI: 10.3724/SP.J.1004.2011.00150
Acta Automatica Sinica (自动化学报) 2011/37:2 PP.150-159
Abstract：
In this paper, according to the developed fractional differentiation and its applications in modern signal processing, we extend it to the quaternion body and put forward a novel concept: quaternion fractional directional differentiation, for image enhancement. We first use a quaternion function to color image and give the definition and calculation method of the quaternion fractional directional derivative. Then, we deduce their numerical calculation templates along eight directions. According to the fractional directional differentiation along the eight directions, the maximum of the norm of quaternion fractional directional differentiation for every point in the image plane is found, then this maximum as the pixel value of this point is viewed, and the enhanced image is obtained. Experimental results show that our method can greatly increase high frequency, reinforce medium frequency, and non-linearly preserve low frequency of signals, hence it is superior to those based on the traditional methods of differentiation in visual effects.
ReleaseDate：2014-07-21 15:48:46
Funds：Supported by National Natural Science Foundation of China (60773168) and Natural Science Foundation of Sichuan Education Office (07ZA207)
1 Ji T L, Sundarehan M K, Roehrig H. Adaptive image contrast enhancement based on human visual properties. IEEE Transaction Medical Imaging, 1994, 13(4): 573-586
2 Chang D C, Wu W R. Image contrast enhancement based on a histogram transformation of local standard deviation. IEEE Transaction Medical Imaging, 1998, 17(4): 518-531
3 Yuan Xiao-Song, Wang Xiu-Tan, Wang Xi-Qin. An adaptive image enhancement algorithm based on human visual properties. Acta Electronica Sinica, 1999, 27(4): 63-65 (袁晓松, 王秀坛, 王希勤. 基于人眼视觉特性的自适应的图像增强算法的研究. 电子学报, 1999, 27(4): 63-65)
4 Jain A K. Fundamentals of Digital Image Processing. New Jersey: Prentice-Hall, 1989
5 Chen Rui, Lin Xi-Rong, Ding Tian-Huai. Assessment of iris image quality based on wavelet-based contourlet transform. Acta Automatica Sinica, 2009, 35(5): 618-621 (陈瑞, 林喜荣, 丁天怀. 基于WBCT的虹膜图像质量评价方法. 自动化学报, 2009, 35(5): 618-621)
6 Leo D S, Ducati G. Quaternionic differential operators. Journal of Mathematical Physics, 2001, 42(5): 2236-2265
7 Deavours C A. The quaternion calculus. The American Mathematical Monthly, 1973, 80(9): 995-1008
8 Bihan L N, Mars J. Singular value decomposition of quaternion matrices: a new tool for vector-sensor signal processing. Signal Processing, 2004, 84(7): 1177-1199
9 Lang Fang-Nian, Zhou Ji-Liu, Yan Bin, Song En-Bin, Zhong Fan. Obtain method of quaternion matrix orthogonal eigenvector set and its application in color face recognition. Acta Automatica Sinica, 2008, 34(2): 121-129 (郎方年, 周激流, 闫斌, 宋恩彬, 钟钒. 四元数矩阵正交特征向量系的求解方法及其在彩色人脸识别中的应用. 自动化学报, 2008, 34(2): 121-129)
10 Oldham K B, Spanier J. The Fractional Calculus: Theory and Applications of Differentiation and Integration to Arbitrary Order. New York: Academic Press, 1974
11 Fisher Y. Fractal Image Compression: Theory and Application. London: Springer-Verlag, 1995
12 Pu Y F, Wang W X, Zhou J L, Wang Y Y, Jia H D. Fractional differential approach to detecting textural features of digital image and its fractional differential filter implementation. Science in China Series F: Information Sciences, 2008, 51(9): 1319-1339
13 Pu Yi-Fei, Wang Wei-Xing. Fractional differential masks of digital image and their numerical implementation algorithms. Acta Automatica Sinica, 2007, 33(11): 1128-1135 (蒲亦非, 王卫星. 数字图像的分数阶微分掩模及其数值运算规则. 自动化学报, 2007, 33(11): 1128-1135)
14 Berger M, Gostiaux B. Differential Geometry: Mannifolds, Curves and Surfaces. New York: Springer-Verlag, 1988
15 Boothby W M. An Introduction to Differentiable Manifolds and Riemannian Geometry. New York: Academic Press, 1975
16 Min W L, Lu K, He X F. Locality pursuit embedding. Pattern Recognition, 2004, 37(4): 781-788
17 Cheng Yun-Peng. Matrix Theory. Xi'an: Northwestern Polytechnical University Press, 1999 (程云鹏. 矩阵论. 西安: 西北工业大学出版社, 1999)