改进SSIM图像评价系统的开发与应用
|
摘要
为了实现图像内容相关评价中的自动化,体现出一幅图像中不同内容的难易度,实现图像评价的智能化,开发了图像自动评价系统。将分水岭算法(Watershed Algorithm)和结构相似度(SSIM)理论相结合,提出了一种针对难易程度进行评价的算法WSSIM。通过随机选取5场实际考试进行检验,共计3 173个样本。计算了人工评价与系统评价绝对误差,结果表明:所有的实验组中均有超过63.75%的样本绝对误差数值小于1.5,最大值达到74.26%,有超过84.41%的样本绝对误差数值小于2.5,最大值达到92.68%。统计结果表明:图像的自动评价结果与人工评价有比较好的一致性,标准差值小于人工评价,改进后的方法能使绝对误差数值小于1.5的样本数量平均提高2.77%。实验结果表明:该系统是有效的,经编译完成后,可在Windows7操作系统中直接运行。它能够为相关院校和等级考试中图像的自动评价提供帮助。
In order to realize the automation of image evaluation in all kinds of course and examination, and reflect the degree of difficulty of different content in one image, the image automatic evaluation program is designed. By combining the watershed algorithm with the Structural Similarity(SSIM)theory, a WSSIM algorithm for evaluating the degree of difficulty is proposed. A total of 3,173 samples are tested by randomly selecting from 5 actual experiments, which already have artificial evaluation results. By calculating the absolute error between the artificial evaluation and the system evaluation,the results show that:more than 63.75% of samples error is less than 1.5, while the maximum value can reach 74.26%.More than 84.41% of samples error value is less than 2.5, while the maximum value can reach 92.68%. The statistical results show that the results of system evaluation are in good agreement with manual evaluation, and the standard difference is less than manual evaluation. The average accuracy of WSSIM is 12.91% higher than that of SSIM. The experimental results show that the system is effective and can be run directly in the Windows 7 after compilation. It can help relevant institutions and grade examination to carry out automatic image marking.
In order to realize the automation of image evaluation in all kinds of course and examination, and reflect the degree of difficulty of different content in one image, the image automatic evaluation program is designed. By combining the watershed algorithm with the Structural Similarity(SSIM)theory, a WSSIM algorithm for evaluating the degree of difficulty is proposed. A total of 3,173 samples are tested by randomly selecting from 5 actual experiments, which already have artificial evaluation results. By calculating the absolute error between the artificial evaluation and the system evaluation,the results show that:more than 63.75% of samples error is less than 1.5, while the maximum value can reach 74.26%.More than 84.41% of samples error value is less than 2.5, while the maximum value can reach 92.68%. The statistical results show that the results of system evaluation are in good agreement with manual evaluation, and the standard difference is less than manual evaluation. The average accuracy of WSSIM is 12.91% higher than that of SSIM. The experimental results show that the system is effective and can be run directly in the Windows 7 after compilation. It can help relevant institutions and grade examination to carry out automatic image marking.
引文
[1]Wang Zhou,Bovik A C.Modern image quality assessment[M].New York:Morgan and Claypool Publishing Company,2006:20-30.
[2]Zhang Lin,Zhang Lei,Mou Xuanqin,et al.A comprehensive evaluation of full reference image quality assessment algorithms[C]//2012 19th IEEE International Conference on Image Processing,2012:1477-1480.
[3]Wang Zhou,Bovik A C.A universal image quality index[J].IEEE Transactions on Signal Processing,2002,9(3):91-94.
[4]Kishorebabu V,Packyanathan G,Kamatham H,et al.An adaptive decision based interpolation scheme for the removal of high density salt and pepper noise in images[J].EURASIP Journal on Image&Video Processing,2017(1):67.
[5]Zhang Xuande,Feng Xiangchu,Wang Weiwei,et al.Twodirection nonlocal model for image interpolation[J].Science China(Technological Sciences),2013,56(4):930-939.
[6]Wang Zhou,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[7]Premaratne P,Premaratne M.Image matching using moment invariants[J].Neuro Computing,2014,137(11):65-70.
[8]Wang X Y,Chen Z F,Yun J J.An effective method for color image retrieval based on texture[J].Computer Standards&Interfaces,2012,34(1):31-35.
[9]Wang Zhengyou,Li Liying,Wu Shuang,et al.A new image quality assessment algorithm based on SSIM and multiple regressions[J].International Journal of Signal Processing,Image Processing and Pattern Recognition,2015,8(11):221-230.
[10]于康龙,秦卫城,杨进,等.超分辨重建图像质量评价算法[J].计算机工程与应用,2017,53(2):201-205.
[11]Wang X,Wang Z.The method for image retrieval based on multi-factors correlation utilizing block truncation coding[J].Pattern Recognition,2014,47(10):3293-3303.
[12]Wang X Y,Chen Z F,Yun J J.An effective method for color image retrieval based on texture[J].Computer Standards&Interfaces,2012,34(1):31-35.
[13]Wang X,Wang Z.The method for image retrieval based on multi-factors correlation utilizing block truncation coding[J].Pattern Recognition,2014,47(10):3293-3303.
[14]Wang X,Wang Z.A novel method for image retrieval based on structure elements’descriptor[J].Journal of Visual Communication&Image Representation,2013,24(1):63-74.
[15]Zhao X,Wang X.Fractal dimension estimation of RGBcolor images using maximum color distance[J].FractalsComplex Geometry Patterns&Scaling in Nature&Society,2016,24(4):1650040.
[16]Zhao X,Wang X Y.An approach to compute fractal dimension of color images[J].Fractals-Complex Geometry Patterns&Scaling in Nature&Society,2017,25(1):149-163.
[17]Bieniek A,Moga A.An efficient watershed algorithm based on connected components[J].Pattern Recognition,2000,33(6):907-916.
[18]Yu Y,Li B,Zhang X,et al.Marked watershed segmentation algorithm for RGBD images[J].Journal of Image&Graphics,2016.
[19]Gong M,Lan J,Yang C,et al.Adaptive image segmentation algorithm under the constraint of edge posterior probability[J].IET Computer Vision,2017,11(8):702-709.
[20]Yang C N,Hsu S C,Kim C.Improving stego image quality in image interpolation based data hiding[J].Computer Standards&Interfaces,2017,50:209-215.
[21]汪启伟.图像直方图特征及其应用研究[D].合肥:中国科学技术大学,2014.
[22]Roth V.Kernel fisher discriminants for outlier detection[J].Neural Computation,2014,18(4):942-960.
[23]张德丰.数字图像处理:MATLAB版[M].北京:人民邮电出版社,2015.
[24]Peleg T,Elad M.A statistical prediction model based on sparse representations for single image superresolution[J].IEEE Transactions on Image Processing,2014,23(6):2569-2582.
[2]Zhang Lin,Zhang Lei,Mou Xuanqin,et al.A comprehensive evaluation of full reference image quality assessment algorithms[C]//2012 19th IEEE International Conference on Image Processing,2012:1477-1480.
[3]Wang Zhou,Bovik A C.A universal image quality index[J].IEEE Transactions on Signal Processing,2002,9(3):91-94.
[4]Kishorebabu V,Packyanathan G,Kamatham H,et al.An adaptive decision based interpolation scheme for the removal of high density salt and pepper noise in images[J].EURASIP Journal on Image&Video Processing,2017(1):67.
[5]Zhang Xuande,Feng Xiangchu,Wang Weiwei,et al.Twodirection nonlocal model for image interpolation[J].Science China(Technological Sciences),2013,56(4):930-939.
[6]Wang Zhou,Bovik A C,Sheikh H R,et al.Image quality assessment:from error visibility to structural similarity[J].IEEE Transactions on Image Processing,2004,13(4):600-612.
[7]Premaratne P,Premaratne M.Image matching using moment invariants[J].Neuro Computing,2014,137(11):65-70.
[8]Wang X Y,Chen Z F,Yun J J.An effective method for color image retrieval based on texture[J].Computer Standards&Interfaces,2012,34(1):31-35.
[9]Wang Zhengyou,Li Liying,Wu Shuang,et al.A new image quality assessment algorithm based on SSIM and multiple regressions[J].International Journal of Signal Processing,Image Processing and Pattern Recognition,2015,8(11):221-230.
[10]于康龙,秦卫城,杨进,等.超分辨重建图像质量评价算法[J].计算机工程与应用,2017,53(2):201-205.
[11]Wang X,Wang Z.The method for image retrieval based on multi-factors correlation utilizing block truncation coding[J].Pattern Recognition,2014,47(10):3293-3303.
[12]Wang X Y,Chen Z F,Yun J J.An effective method for color image retrieval based on texture[J].Computer Standards&Interfaces,2012,34(1):31-35.
[13]Wang X,Wang Z.The method for image retrieval based on multi-factors correlation utilizing block truncation coding[J].Pattern Recognition,2014,47(10):3293-3303.
[14]Wang X,Wang Z.A novel method for image retrieval based on structure elements’descriptor[J].Journal of Visual Communication&Image Representation,2013,24(1):63-74.
[15]Zhao X,Wang X.Fractal dimension estimation of RGBcolor images using maximum color distance[J].FractalsComplex Geometry Patterns&Scaling in Nature&Society,2016,24(4):1650040.
[16]Zhao X,Wang X Y.An approach to compute fractal dimension of color images[J].Fractals-Complex Geometry Patterns&Scaling in Nature&Society,2017,25(1):149-163.
[17]Bieniek A,Moga A.An efficient watershed algorithm based on connected components[J].Pattern Recognition,2000,33(6):907-916.
[18]Yu Y,Li B,Zhang X,et al.Marked watershed segmentation algorithm for RGBD images[J].Journal of Image&Graphics,2016.
[19]Gong M,Lan J,Yang C,et al.Adaptive image segmentation algorithm under the constraint of edge posterior probability[J].IET Computer Vision,2017,11(8):702-709.
[20]Yang C N,Hsu S C,Kim C.Improving stego image quality in image interpolation based data hiding[J].Computer Standards&Interfaces,2017,50:209-215.
[21]汪启伟.图像直方图特征及其应用研究[D].合肥:中国科学技术大学,2014.
[22]Roth V.Kernel fisher discriminants for outlier detection[J].Neural Computation,2014,18(4):942-960.
[23]张德丰.数字图像处理:MATLAB版[M].北京:人民邮电出版社,2015.
[24]Peleg T,Elad M.A statistical prediction model based on sparse representations for single image superresolution[J].IEEE Transactions on Image Processing,2014,23(6):2569-2582.