The optimized color space is searched by using the wavelet scattering network in the KTH_TIPS_COL color image database for image texture classification. The effect of choosing the color space on the classification acc...The optimized color space is searched by using the wavelet scattering network in the KTH_TIPS_COL color image database for image texture classification. The effect of choosing the color space on the classification accuracy is investigated by converting red green blue （RGB） color space to various other color spaces. The results show that the classification performance generally changes to a large degree when performing color texture classification in various color spaces, and the opponent RGB-based wavelet scattering network outperforms other color spaces-based wavelet scattering networks. Considering that color spaces can be changed into each other, therefore, when dealing with the problem of color texture classification, converting other color spaces to the opponent RGB color space is recommended before performing the wavelet scattering network.展开更多
A newalgorithm, called Magnitude Cut, to recover a signal from its phase in the transform domain, is proposed.First, the recovery problem is converted to an equivalent convex optimization problem, and then it is solve...A newalgorithm, called Magnitude Cut, to recover a signal from its phase in the transform domain, is proposed.First, the recovery problem is converted to an equivalent convex optimization problem, and then it is solved by the block coordinate descent（ BCD） algorithm and the interior point algorithm. Finally, the one-dimensional and twodimensional signal reconstructions are implemented and the reconstruction results under the Fourier transform with a Gaussian random mask（ FTGM）, the Cauchy wavelets transform（ CWT）, the Fourier transform with a binary random mask（ FTBM） and the Gaussian random transform（ GRT） are also comparatively analyzed. The analysis results reveal that the M agnitude Cut method can reconstruct the original signal with the phase information of different transforms; and it needs less phase information to recover the signal from the phase of the FTGM or GRT than that of FTBM or CWT under the same reconstruction error.展开更多
基金The National Basic Research Program of China(No.2011CB707904)the National Natural Science Foundation of China(No.61201344,61271312,11301074)+1 种基金the Natural Science Foundation of Jiangsu Province(No.BK2012329)the Specialized Research Fund for the Doctoral Program of Higher Education(No.20110092110023,20120092120036)
文摘The optimized color space is searched by using the wavelet scattering network in the KTH_TIPS_COL color image database for image texture classification. The effect of choosing the color space on the classification accuracy is investigated by converting red green blue （RGB） color space to various other color spaces. The results show that the classification performance generally changes to a large degree when performing color texture classification in various color spaces, and the opponent RGB-based wavelet scattering network outperforms other color spaces-based wavelet scattering networks. Considering that color spaces can be changed into each other, therefore, when dealing with the problem of color texture classification, converting other color spaces to the opponent RGB color space is recommended before performing the wavelet scattering network.
基金The National Natural Science Foundation of China(No.6120134461271312+7 种基金11301074)the Specialized Research Fund for the Doctoral Program of Higher Education(No.2011009211002320120092120036)the Program for Special Talents in Six Fields of Jiangsu Province(No.DZXX-031)the Natural Science Foundation of Jiangsu Province(No.BK2012329BK2012743)the United Creative Foundation of Jiangsu Province(No.BY2014127-11)the"333"Project(No.BRA2015288)
文摘A newalgorithm, called Magnitude Cut, to recover a signal from its phase in the transform domain, is proposed.First, the recovery problem is converted to an equivalent convex optimization problem, and then it is solved by the block coordinate descent（ BCD） algorithm and the interior point algorithm. Finally, the one-dimensional and twodimensional signal reconstructions are implemented and the reconstruction results under the Fourier transform with a Gaussian random mask（ FTGM）, the Cauchy wavelets transform（ CWT）, the Fourier transform with a binary random mask（ FTBM） and the Gaussian random transform（ GRT） are also comparatively analyzed. The analysis results reveal that the M agnitude Cut method can reconstruct the original signal with the phase information of different transforms; and it needs less phase information to recover the signal from the phase of the FTGM or GRT than that of FTBM or CWT under the same reconstruction error.
