No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain

doi:10.21629/JSEE.2019.02.01

Journal of Systems Engineering and Electronics ›› 2019, Vol. 30 ›› Issue (2): 223-237.doi: 10.21629/JSEE.2019.02.01

• • 下一篇

收稿日期:2017-12-19 出版日期:2019-04-01 发布日期:2019-04-26

No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain

Junhua YAN^1,^2,*(), Xuehan BAI¹(), Wanyi ZHANG¹(), Yongqi XIAO¹(), Chris CHATWIN²(), Rupert YOUNG²(), Phil BIRCH²()

¹ College of Astronautics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
² School of Engineering and Informatics, University of Sussex, Brighton BN1 9QT, UK

Received:2017-12-19 Online:2019-04-01 Published:2019-04-26
Contact: Junhua YAN E-mail:yjh9758@126.com;1595720931@qq.com;daisyzwy917@126.com;couragexyq@163.com;C.R.Chatwin@sussex.ac.uk;R.C.D.Young@sussex.ac.uk;p.m.birch@sussex.ac.uk
About author:YAN Junhua was born in 1972. She received her B.S. degree, M.S. degree and Ph.D. degree from Nanjing University of Aeronautics and Astronautics in 1993, 2001 and 2004, respectively. She is a professor at Nanjing University of Aeronautics and Astronautics. Her research interests include image quality assessment, multi-source information fusion, target detection, tracking and recognition. E-mail:yjh9758@126.com|BAI Xuehan was born in 1993. She received her B.S. degree from Harbin Institute of Technology in 2016. She is a graduate student at Nanjing University of Aeronautics and Astronautics. Her research interest is image quality assessment. E-mail:1595720931@qq.com|ZHANG Wanyi was born in 1992. She received her B.S. degree and M.S. degree from Nanjing University of Aeronautics and Astronautics in 2014 and 2017. Her research interest is image quality assessment. E-mail:daisyzwy917@126.com|XIAO Yongqi was born in 1994. He received his B.S. degree and M.S. degree from Nanjing University of Aeronautics and Astronautics in 2015 and 2018. His research interest is image quality assessment. E-mail:couragexyq@163.com|CHATWIN Chris was born in 1950. He received his B.S. degree from University of Aston in 1973, his M.S. and Ph.D. degrees from University of Birmingham in 1977, and 1980, respectively. He is a professor in Engineering at University of Sussex. His research interests are smart cameras and algorithms, UAV surveillance systems, multi camera tracking systems, image processing for cancer diagnostics. E-mail:C.R.Chatwin@sussex.ac.uk|YOUNG Rupert was born in 1959. He received his B.S. and Ph.D. degrees from University of Glasgow in 1986, and 1994, respectively. He is a reader at University of Sussex. His current research interests are machine vision, image processing, neural networks, and quantum computing. E-mail:R.C.D.Young@sussex.ac.uk|BIRCH Phil was born in 1973. He received his B.S., M.S. degree and Ph.D. degrees from University of Durham in 1994, and 1999, respectively. He is a senior lecturer at University of Sussex. His current research interests are optical signal processing, target detection and computer vision. E-mail:p.m.birch@sussex.ac.uk
Supported by:
the National Natural Science Foundation of China(61471194);the National Natural Science Foundation of China(61705104);the Science and Technology on Avionics Integration Laboratory and Aeronautical Science Foundation of China(20155552050);the Natural Science Foundation of Jiangsu Province(BK20170804);This work was supported by the National Natural Science Foundation of China (61471194; 61705104), the Science and Technology on Avionics Integration Laboratory and Aeronautical Science Foundation of China (20155552050), and the Natural Science Foundation of Jiangsu Province (BK20170804)

摘要/Abstract

Abstract:

Considering the relatively poor robustness of quality scores for different types of distortion and the lack of mechanism for determining distortion types, a no-reference image quality assessment (NR-IQA) method based on the AdaBoost BP neural network in the wavelet domain (WABNN) is proposed. A 36-dimensional image feature vector is constructed by extracting natural scene statistics (NSS) features and local information entropy features of the distorted image wavelet sub-band coefficients in three scales. The ABNN classifier is obtained by learning the relationship between image features and distortion types. The ABNN scorer is obtained by learning the relationship between image features and image quality scores. A series of contrast experiments are carried out in the laboratory of image and video engineering (LIVE) database and TID2013 database. Experimental results show the high accuracy of the distinguishing distortion type, the high consistency with subjective scores and the high robustness of the method for distorted images. Experiment results also show the independence of the database and the relatively high operation efficiency of this method.

Key words: image quality assessment (IQA), AdaBoost BP neural network (ABNN), wavelet transform, natural scene statistics (NSS), local information entropy

. [J]. Journal of Systems Engineering and Electronics, 2019, 30(2): 223-237.

Junhua YAN, Xuehan BAI, Wanyi ZHANG, Yongqi XIAO, Chris CHATWIN, Rupert YOUNG, Phil BIRCH. No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain[J]. Journal of Systems Engineering and Electronics, 2019, 30(2): 223-237.

图/表 23

Distortion type	Method	RMSE	LPCC	SROCC	KROCC
WN	BIQI	6.721 4	0.953 8	0.951 0	0.821 9
	DIIVINE	5.481 5	0.988 0	$\textbf{0.984 0}$	0.878 2
	BLIINDS-II	6.011 2	0.979 9	0.978 3	0.851 1
	NIQE	6.254 6	0.977 3	0.966 2	0.849 5
	BRISQUE	$\textbf{5.327 1}$	$\textbf{0.985 1}$	0.978 6	$\textbf{0.876 3}$
	SSEQ	5.928 9	0.980 6	0.978 4	0.859 7
	BHOD	6.554 4	0.980 1	0.972 8	0.864 5
	NRSL	$\textbf{5.384 6}$	$\textbf{0.986 8}$	$\textbf{0.980 1}$	$\textbf{0.891 6}$
	WABNN	$\textbf{5.439 4}$	$\textbf{0.985 5}$	$\textbf{0.981 6}$	$\textbf{0.870 8}$
BLUR	BIQI	8.964 8	0.829 3	0.846 3	0.779 5
	DIIVINE	7.996 1	0.923 0	0.921 0	0.796 1
	BLIINDS-II	7.6863	0.9381	0.9432	0.832 8
	NIQE	7.056 7	0.952 5	0.934 1	0.828 6
	BRISQUE	7.239 5	0.950 6	0.943 5	0.837 9
	SSEQ	$\textbf{6.864 9}$	$\textbf{0.960 7}$	$\textbf{0.948 3}$	$\textbf{0.846 1}$
	BHOD	$\textbf{6.166 9}$	$\textbf{0.966 0}$	$\textbf{0.964 9}$	$\textbf{0.854 7}$
	NRSL	7.850 4	0.944 7	0.942 0	0.808 1
	WABNN	$\textbf{6.633 9}$	$\textbf{0.957 2}$	$\textbf{0.9442 }$	$\textbf{0.840 7}$
JPEG	BIQI	10.144 0	0.901 1	0.891 4	0.783 9
	DIIVINE	9.5101	0.9210	0.910 0	0.808 5
	BLIINDS-II	8.654 1	0.937 6	0.931 1	0.825 7
	NIQE	8.298 2	0.941 4	0.938 2	0.821 8
	BRISQUE	$\textbf{7.204 2}$	$\textbf{0.973 4}$	$\textbf{0.964 7}$	$\textbf{0.846 6}$
	SSEQ	7.570 5	0.970 2	$\textbf{0.951 0}$	$\textbf{0.841 5}$
	BHOD	8.173 5	$\textbf{0.972 6}$	0.946 1	0.820 6
	NRSL	$\textbf{7.568 4}$	$\textbf{0.976 4}$	$\textbf{0.950 8}$	0.829 4
	WABNN	$\textbf{7.483 8}$	0.942 3	0.934 8	$\textbf{0.838 1}$
JP2K	BIQI	12.013 3	0.808 6	0.799 5	0.736 8
	DIIVINE	9.610 9	0.922 0	0.913 0	0.765 6
	BLIINDS-II	9.505 5	0.934 8	$\textbf{0.950 6}$	$\textbf{0.816 8}$
	NIQE	9.502 4	0.937 0	0.917 2	0.781 8
	BRISQUE	9.875 2	0.922 9	0.913 9	0.769 3
	SSEQ	$\textbf{8.165 3}$	$\textbf{0.946 4}$	0.942 0	0.801 1
	BHOD	$\textbf{7.482 1}$	$\textbf{0.966 2}$	$\textbf{0.946 2}$	$\textbf{0.818 0}$
	NRSL	$\textbf{7.311 1}$	$\textbf{0.967 1}$	$\textbf{0.951 4}$	$\textbf{0.824 3}$
	WABNN	8.916 5	0.941 2	0.931 0	0.795 1
FF	BIQI	18.103 2	0.732 8	0.706 7	0.606 4
	DIIVINE	14.429 5	0.888 0	0.863 0	0.668 6
	BLIINDS-II	13.505 5	0.895 5	0.865 7	0.684 1
	NIQE	12.605 8	0.912 8	0.859 4	0.665 3
	BRISQUE	$\textbf{11.799 6}$	0.914 8	0.886 1	0.721 6
	SSEQ	12.685 8	0.916 2	$\textbf{0.903 5}$	0.749 3
	BHOD	$\textbf{10.181 3}$	$\textbf{0.944 5}$	$\textbf{0.919 8}$	$\textbf{0.776 0}$
	NRSL	11.934 8	$\textbf{0.923 8}$	0.902 9	$\textbf{0.753 5}$
	WABNN	$\textbf{11.591 3}$	$\textbf{0.918 9}$	$\textbf{0.911 0}$	$\textbf{0.766 2}$

Distortion type	Method	RMSE	LPCC	SROCC	KROCC
WN	BIQI	$\textbf{0.292 2}$	$\textbf{0.910 6}$	$\textbf{0.901 5}$	$\textbf{0.737 7}$
	DIIVINE	0.338 3	0.877 3	0.810 4	0.708 9
	BLIINDS-II	0.385 7	0.839 5	0.821 5	0.626 7
	NIQE	0.399 4	0.842 8	0.815 5	0.605 0
	BRISQUE	0.330 5	0.884 1	0.868 8	0.683 3
	SSEQ	$\textbf{0.310 8}$	$\textbf{0.900 2}$	$\textbf{0.894 6}$	$\textbf{0.726 7}$
	BHOD	0.485 8	0.729 5	0.710 6	0.522 1
	NRSL	0.312 7	0.896 7	0.889 1	0.713 3
	WABNN	$\textbf{0.280 4}$	$\textbf{0.916 3}$	$\textbf{0.916 6}$	$\textbf{0.728 9}$
BLUR	BIQI	0.635 6	0.855 2	0.836 2	0.663 3
	DIIVINE	0.479 9	0.921 1	0.916 5	0.760 0
	BLIINDS-II	$\textbf{0.380 3}$	$\textbf{0.951 0}$	$\textbf{0.946 2}$	$\textbf{0.811 4}$
	NIQE	0.670 2	0.825 4	0.815 5	0.589 0
	BRISQUE	0.483 7	0.919 4	0.911 5	0.749 0
	SSEQ	0.531 2	0.901 2	0.893 1	0.720 0
	BHOD	0.668 2	0.919 3	0.910 7	0.746 7
	NRSL	$\textbf{0.396 5}$	$\textbf{0.945 6}$	$\textbf{0.934 6}$	$\textbf{0.793 3}$
	WABNN	$\textbf{0.430 3}$	$\textbf{0.934 5}$	$\textbf{0.928 7}$	$\textbf{0.779 6}$
JPEG	BIQI	1.022 0	0.728 8	0.670 3	0.493 3
	DIIVINE	0.684 5	0.884 4	0.810 4	0.620 0
	BLIINDS-II	$\textbf{0.461 5}$	$\textbf{0.950 7}$	$\textbf{0.905 4}$	$\textbf{0.733 0}$
	NIQE	0.559 5	0.926 8	0.866 5	0.649 8
	BRISQUE	0.521 2	0.936 1	0.870 8	0.700 0
	SSEQ	0.462 2	$\textbf{0.948 7}$	$\textbf{0.900 9}$	$\textbf{0.737 9}$
	BHOD	0.475 3	0.948 3	0.871 2	0.686 7
	NRSL	$\textbf{0.413 4}$	$\textbf{0.958 7}$	0.900 5	0.732 3
	WABNN	$\textbf{0.413 9}$	0.944 6	$\textbf{0.919 8}$	$\textbf{0.766 3}$
JP2K	BIQI	0.761 2	0.893 4	0.822 0	0.631 1
	DIIVINE	$\textbf{0.636 7}$	0.924 9	0.877 3	0.700 0
	BLIINDS-II	$\textbf{0.546 6}$	$\textbf{0.944 9}$	$\textbf{0.926 9}$	$\textbf{0.780 0}$
	NIQE	0.715 5	0.907 2	0.898 1	0.706 2
	BRISQUE	0.672 3	0.912 8	$\textbf{0.907 3}$	$\textbf{0.752 3}$
	SSEQ	0.601 1	$\textbf{0.932 8}$	0.899 9	0.737 9
	BHOD	$\textbf{0.609 3}$	$\textbf{0.933 2}$	0.890 7	0.720 0
	NRSL	0.656 2	0.920 4	0.883 1	0.713 3
	WABNN	0.699 6	0.913 6	$\textbf{0.906 6}$	$\textbf{0.749 3}$

参考文献 34

1	MANAP R A, SHAO L. Non-distortion-specific no-reference image quality assessment:a survey. Information Sciences, 2015, 301 (C): 141- 160.
2	ZHU X, MILANFAR P. A no-reference sharpness metric sensitive to blur and noise. Proc. of International Workshop on Quality of Multimedia Experience, 2009, 64- 69.
3	CHEN M J, BOVIK A C. No-reference image blur assessment using multiscale gradient. Proc. of International Workshop on Quality of Multimedia Experience, 2009, 1- 11.
4	MARICHAL X, MA W Y, ZHANG H J. Blur determination in the compressed domain using DCT information. Proc. of the IEEE International Conference on Image Processing, 2002, 12, 386- 390.
5	SHAO Y, SUN F, LI H. No-reference remote sensing image quality assessment method using visual properties. Journal of Tsinghua University, 2013, 53 (4): 550- 555.
6	WANG Z, BOVIK A C, EVAN B L. Blind measurement of blocking artifacts in images. Proc. of the IEEE International Conference on Image Processing, 2000, 981- 984.
7	SAZZAD Z M P, KAWAYOKE Y, HORITA Y. No reference image quality assessment for JP2K based on spatial features. Signal Processing Image Communication, 2008, 23 (4): 257- 268. doi: 10.1016/j.image.2008.03.005
8	HORITA Y, ARATA S, MURAI T. No-reference image quality assessment for JPEG/JP2K coding. Proc. of the IEEE Signal Processing Conference, 2004, 1301- 1304.
9	XIE F, PAN X, JIANG Z, et al. No-reference haze effects assessment for remote sensing images. Chinese Journal of Stereology & Image Analysis, 2015, 20 (1): 22- 27.
10	WANG Z, BOVIK A C. Modern image quality assessment. New York: Morgan and Claypool Publishing Company, 2006.
11	MOORTHY A K, BOVIK A C. A two-step framework for constructing blind image quality indices. IEEE Signal Processing Letters, 2010, 17 (5): 513- 516. doi: 10.1109/LSP.2010.2043888
12	LI C, BOVIK A C, WU X. Blind image quality assessment using a general regression neural network. IEEE Trans. on Neural Networks, 2011, 22 (5): 793- 799. doi: 10.1109/TNN.2011.2120620
13	MOORTHY A K, BOVIK A C. Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans. on Image Processing: A Publication of the IEEE Signal Processing Society, 2011, 20(12): 3350-3364.
14	SAAD M A, BOVIK A C, CHARRIER C. DCT statistics model-based blind image quality assessment. Proc. of the IEEE 18th International Conference on Image Processing, 2011, 9, 3154- 3157.
15	SAAD M A, BOVIK A C, CHARRIER C. Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans. on Image Processing: A Publication of the IEEE Signal Processing Society, 2012, 21(8): 3339-3352.
16	MITTAL A, SOUNDARARAJAN R, BOVIK A C. Making a "completely blind" image quality analyzer. IEEE Signal Processing Letters, 2013, 20 (3): 209- 212. doi: 10.1109/LSP.2012.2227726
17	MITTAL A, MOORTHY A K, BOVIK A C. No-reference image quality assessment in the spatial domain. IEEE Trans. on Image Processing: A Publication of the IEEE Signal Processing Society, 2012, 21(12): 4695-4708.
18	MITTAL A, MOORTHY A K, BOVIK A C. Blind/referenceless image spatial quality evaluator. Proc. of the IEEE 45th Asilornar Conference on Signals, Systems and Computers, 2011: 723-727.
19	LIU L, LIU B, HUANG H, et al. No-reference image quality assessment based on spatial and spectral entropies. Signal Processing Image Communication, 2014, 29 (8): 856- 863. doi: 10.1016/j.image.2014.06.006
20	LI Q, LIN W, FANG Y. No-reference image quality assessment based on high order derivatives. Proc. of the IEEE International Conference on Multimedia and Expo, 2016: 1-6.
21	LI Q, LIN W, XU J, et al. Blind image quality assessment using statistical structural and luminance features. IEEE Trans. on Multimedia, 2016, 18(12): 2457-2469.
22	LIU L, HUA Y, ZHAO Q, et al. Blind image quality assessment by relative gradient statistics and adaboosting neural network. Signal Processing Image Communication, 2016, 40 (C): 1- 15.
23	RUDERMAN D L. The statistics of natural images. Network Computation in Neural Systems, 2009, 5 (4): 517- 548.
24	WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment. Proc. of the 37th IEEE Asilomar Conference on Signals, Systems & Computers, 2003, 2: 1398-1402.
25	SRIVASTAVA A, LEE A B, SIMONCELLI E P, et al. On advances in statistical modeling of natural images. Journal of Mathematical Imaging & Vision, 2003, 18 (1): 17- 33.
26	SHEIKH H R, WANG Z, BOVIK A C, et al. Image and video quality assessment research at LIVE 2004. http://live.ece.utexas.edu/research/quality.
27	SHEIKH H R, SABIR M F, BOVIK A C. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans. on Image Processing, 2006, 15(11): 3440-3451.
28	SHARIFI K, LEON-GARCIA A. Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video. IEEE Trans. on Circuits & Systems for Video Technology, 1995, 5(1): 52-56.
29	ZHOU Y L, CHEN F, SUN B. Identification method of gas-liquid two-phase flow pattern based on image wavelet packet information entropy and genetic neural network. Nuclear Power Engineering, 2008, 29 (1): 115- 120.
30	ZHANG Z. Digital image processing and machine vision. Beijing: The Posts and Telecommunications Press, 2010.
31	CAO Y, MIAO Q G, LIU J C, et al. Advance and prospects of adaboost algorithm. Acta Automatica Sinica, 2013, 39 (6): 745- 758. doi: 10.1016/S1874-1029(13)60052-X
32	WU J L, ZHANG B H, WANG K. Application of Adaboostbased BP neural network for short-term wind speed forecast. Power System Technology, 2012, 36 (9): 221- 225.
33	LI S, XIE Y L, WANG W X. Application of AdaBoost BP neural network in prediction of railway freight volumes. Computer Engineering and Applications, 2012, 48 (6): 233- 234.
34	PONOMA N, PONOMARENKO N, JIN L, et al. Image database TID2013:peculiarities, results and perspectives. Signal Processing:Image Communication, 2015, 30, 57- 77. doi: 10.1016/j.image.2014.10.009

Vector elements	Meaning
$f_1$-$f_3 $	Variance $\sigma ^2$ of the three sub-bands in the horizontal orientations and the first, second and third scales
$f_4$-$f_6 $	Variance $\sigma ^2$ of the three sub-bands in the vertical orientations and the first, second and third scales
$f_7$-$f_9 $	Variance $\sigma ^2$ of the three sub-bands in the diagonal orientations and the first, second and third scales
$f_{10}$-$f_{12} $	Shape parameter $\gamma $ of the three sub-bands in the horizontal orientations and the first, second and third scales
$f_{13}$-$f_{15} $	Shape parameter $\gamma $ of the three sub-bands in the vertical orientations and the first, second and third scales
$f_{16}$-$f_{18} $	Shape parameter $\gamma $ of the three sub-bands in the diagonal orientations and the first, second and third scales

Vector elements	Meaning
$f_{19}$-$f_{21}$	Mean $\mu_w$ of sub-band local information entropy in the first scale and the horizontal, vertical and diagonal orientations
$f_{22}$-$f_{24}$	Mean $\mu_w$ of sub-band local information entropy in the second scale and the horizontal, vertical and diagonal orientations
$f_{25}$-$f_{27}$	Mean $\mu_w$ of sub-band local information entropy in the third scale and the horizontal, vertical and diagonal orientations
$f_{28}$-$f_{30}$	Skewness $S_w$ of sub-band local information entropy in the first scale and the horizontal, vertical and diagonal orientations
$f_{31}$-$f_{33}$	Skewness $S_w$ of sub-band local information entropy in the second scale and the horizontal, vertical and diagonal orientations
$f_{34}$-$f_{36}$	Skewness $S_w$ of sub-band local information entropy in the third scale and the horizontal, vertical and diagonal orientations

Dataset	RMSE	LPCC	SROCC	KROCC
Dataset 1	8.674 1	0.948 4	0.940 8	0.780 1
Dataset 2	9.135 9	0.922 7	0.917 3	0.763 5
Dataset 3	9.948 6	0.915 9	0.908 8	0.756 2
Dataset 4	8.825 4	0.935 5	0.926 5	0.768 7
Dataset 5	8.936 6	0.949 1	0.935 2	0.778 1
All	9.110 7	0.936 4	0.924 9	0.766 4

Dataset	WN	BLUR	JPEG	JPEG2000	FF	All
Dataset 1	96.67	90.00	97.37	85.29	86.67	91.36
Dataset 2	96.67	93.33	94.44	89.19	86.67	92.02
Dataset 3	100.00	90.00	91.89	88.24	90.00	91.93
Dataset 4	100.00	93.33	88.24	88.57	86.67	91.19
Dataset 5	96.00	92.00	96.30	89.66	88.00	93.13
All	97.87	91.73	93.65	88.19	87.60	91.93

Method	WN	Blur	JPEG	JP2K	ALL
BIQI	0.876 8	0.876 6	0.666 5	0.855 9	0.819 0
DIIVINE	0.883 9	0.893 9	0.852 4	0.789 5	0.854 9
BLIINDS-II	0.723 1	0.583 3	0.566 2	0.611 2	0.621 0
NIQE	0.815 5	0.815 5	0.866 5	0.898 1	0.848 9
BRISQUE	0.906 7	0.904 5	0.891 7	0.888 8	$\textbf{0.897 9 }$
SSEQ	0.861 6	0.898 6	0.918 3	0.902 3	$\textbf{0.895 2 }$
BHOD	0.748 9	0.914 8	0.881 5	0.915 5	0.865 2
NRSL	0.842 2	0.909 4	0.909 2	0.777 9	0.859 7
WABNN	0.901 0	0.897 1	0.922 1	0.841 2	$\textbf{0.890 4 }$

No-reference image quality assessment based on AdaBoost BP neural network in wavelet domain

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 23

参考文献 34

相关文章 0

编辑推荐

Metrics

本文评价

Dataset	Categories of distorted images	Types and numbers of distorted image
Dataset	Categories of distorted images	WN	BLUR	JPEG	JP2K	FF	All
1	Bikes, building2, buildings, caps, carnivaldolls, cemetry	30	30	38	34	30	162
2	Churchandcapitol, lighthouse, dancers, coinsinfountain, house, loweronih35	30	30	36	37	30	163
3	Lighthouse2, manfishing, monarch, ocean, parrots, paintedhouse	30	30	37	34	30	161
4	Plane, rapids, sailing1, sailing2, sailing3, sailing4	30	30	34	35	30	159
5	Statue, stream, womanhat, studentsculpture, woman	25	25	30	29	25	134
All distorted images in LIVE database		145	145	175	169	145	779

	DIIVINE	BLIINDS-II	SSEQ	BRISQUE	BHOD	NRSL	WABNN
Mean time/s	19.645 0	62.372 0	2.135 7	0.171 8	0.827 3	0.296 4	0.251 3

	DIIVINE	BLIINDS-II	SSEQ	BRISQUE	BHOD	NRSL	WABNN
Mean time/s	14.733 8	62.372 0	1.414 6	0.111 7	0.549 8	0.170 3	0.238 6