In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of ea...In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.展开更多
Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion a...Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion area.In order to reduce the effect of noise on feature extraction,the stacked automatic encoder with robustness was used.In order to improve the ability of gait classification,the sparse coding was used to express and classify the gait features.Experiments results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA-B and TUM-GAID for gait recognition.展开更多
This paper introduces a Gray map from （Fp ＋ vFp）n to F2pn, and describes the relationship between codes over Fp ＋ vFp and their Gray images. The authors prove that every cyclic code of arbitrary length n over Fp ...This paper introduces a Gray map from （Fp ＋ vFp）n to F2pn, and describes the relationship between codes over Fp ＋ vFp and their Gray images. The authors prove that every cyclic code of arbitrary length n over Fp ＋ vFp is principal, and determine its generator polynomial as well as the number of cyclic codes. Moreover, the authors obtain many best-known p-ary quasic-cyclic codes in terms of their parameters via the Gray map.展开更多
In this paper, the Hausdorff dimension of the intersection of self-similar fractals in Euclidean space R^n generated from an initial cube pattern with an(n-m)-dimensional hyperplane V in a fixed direction is discussed...In this paper, the Hausdorff dimension of the intersection of self-similar fractals in Euclidean space R^n generated from an initial cube pattern with an(n-m)-dimensional hyperplane V in a fixed direction is discussed. The authors give a sufficient condition which ensures that the Hausdorff dimensions of the slices of the fractal sets generated by "multirules" take the value in Marstrand's theorem, i.e., the dimension of the self-similar sets minus one. For the self-similar fractals generated with initial cube pattern, this sufficient condition also ensures that the projection measure μVis absolutely continuous with respect to the Lebesgue measure L^m. When μV《 L^m, the connection of the local dimension ofμVand the box dimension of slices is given.展开更多
文摘In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.
基金Project(51678075) supported by the National Natural Science Foundation of ChinaProject(2017GK2271) supported by Hunan Provincial Science and Technology Department,China
文摘Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion area.In order to reduce the effect of noise on feature extraction,the stacked automatic encoder with robustness was used.In order to improve the ability of gait classification,the sparse coding was used to express and classify the gait features.Experiments results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA-B and TUM-GAID for gait recognition.
基金supported by NNSF of China under Grant Nos.11126174,60973125,71071045 and 71001032Talents youth Fund of Anhui Province Universities under Grant No.2012SQRL020ZD+1 种基金Youth Science Research Fund of Anhui University under Grant No.2009QN026Bthe 211 Project of Anhui University Grant No. KJTD002B
文摘This paper introduces a Gray map from （Fp ＋ vFp）n to F2pn, and describes the relationship between codes over Fp ＋ vFp and their Gray images. The authors prove that every cyclic code of arbitrary length n over Fp ＋ vFp is principal, and determine its generator polynomial as well as the number of cyclic codes. Moreover, the authors obtain many best-known p-ary quasic-cyclic codes in terms of their parameters via the Gray map.
基金supported by the National Natural Science Foundation of China(Nos.11371329,11471124,11071090,11071224,11101159,11401188)K.C.Wong Magna Fund in Ningbo University,the Natural Science Foundation of Zhejiang Province(Nos.LR13A010001,LY12F02011)the Natural Science Foundation of Guangdong Province(No.S2011040005741)
文摘In this paper, the Hausdorff dimension of the intersection of self-similar fractals in Euclidean space R^n generated from an initial cube pattern with an(n-m)-dimensional hyperplane V in a fixed direction is discussed. The authors give a sufficient condition which ensures that the Hausdorff dimensions of the slices of the fractal sets generated by "multirules" take the value in Marstrand's theorem, i.e., the dimension of the self-similar sets minus one. For the self-similar fractals generated with initial cube pattern, this sufficient condition also ensures that the projection measure μVis absolutely continuous with respect to the Lebesgue measure L^m. When μV《 L^m, the connection of the local dimension ofμVand the box dimension of slices is given.
