欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为了更有效地利用彩色人脸的色彩信息进行识别，提出了一种新的基于彩色图像四元数表示的算法．首先基于彩色图像四元数表示和四元数代数理论定义了四元数伪Zernike矩（Quaternion pseudo．Zernike moments，QPZMs），将传统的主要处理灰度图像的伪Zernike矩（Pseudo-Zernikemoments，PZMs）推广应用于彩色图像，然后基于QPZMs构造了彩色人脸图像针对旋转、缩放和平移（Rotation，scaling，andtranslation，RST）变换的四无数值不变量，最后结合这些鲁棒的不变量特征和四元数BP神经网络（Quaternion back propagation neural network，QBPNN）分类器进行彩色人脸识别．实验结果表明，与现有基于四元数的算法比较，本文算法在表情、光照、位置等变化方面具有更强的鲁棒性．
英文摘要：
In order to make better use of color information for color face recognition, a new algorithm based on quaternion representation has been proposed. First of aU, quaternion pseudo-Zernike moments （QPZMs） are defined to generalize the conventional pseudo-Zernike moments （PZMs） for grayscale images to the case of color images using the quaternion representation and the algebra of quaternions. Secondly, we derive a set of quaternion-valued invariants with respect to rotation, scaling and translation （RST） transformations for color face images based on the generalized QPZMs. Finally, color face recognition is carried out by combining these robust invariants with quaternion back propagation neural network （QBPNN）. Experimental results demonstrate that the proposed algorithm performs better than the existing quaternion- based algorithms in terms of robustness to the facial expression, illumination and position changes.
同期刊论文项目
同项目期刊论文
Quaternion Bessel–Fourier moments and their invariant descriptors for object reconstruction and reco
Removing Gaussian noise for colour images by quaternion representation and optimisation of weights i
A new deconvolution approach to robust fluence for intensity modulation under geometrical uncertaint
Quaternion Bessel-Fourier moments and their invariant descriptors for object reconstruction and reco
A New Strategy for Model Order Identification and Its Application to Transfer Entropy for EEG Signal
期刊信息
位置：