针对2维超声心动图像噪声大且难于分割的特点,提出基于Centripetal Catmull-Rom曲线的多尺度活动形状模型的左心室分割方法。该算法在金字塔上层提取2维轮廓法线向量特征并采用马氏距离寻找新的特征点位置;在图像金字塔底层快速提取特...针对2维超声心动图像噪声大且难于分割的特点,提出基于Centripetal Catmull-Rom曲线的多尺度活动形状模型的左心室分割方法。该算法在金字塔上层提取2维轮廓法线向量特征并采用马氏距离寻找新的特征点位置;在图像金字塔底层快速提取特征点周围的Log-Gabor特征并使用Gentle Ada Boost训练分类器,选择置信度水平最高的点作为新的特征点位置。实验证明,这种方法较之传统活动形状模型分割更为精确且分割结果交互方便,有利于对结果的再编辑。展开更多
In this paper, we propose a sparse overcomplete image approximation method based on the ideas of overcomplete log-Gabor wavelet, mean shift and energy concentration. The proposed approximation method selects the neces...In this paper, we propose a sparse overcomplete image approximation method based on the ideas of overcomplete log-Gabor wavelet, mean shift and energy concentration. The proposed approximation method selects the necessary wavelet coefficients with a mean shift based algorithm, and concentrates energy on the selected coefficients. It can sparsely approximate the original image, and converges faster than the existing local competition based method. Then, we propose a new compression scheme based on the above approximation method. The scheme has compression performance similar to JPEG 2000. The images decoded with the proposed compression scheme appear more pleasant to the human eyes than those with JPEG 2000.展开更多
为进一步提升人脸识别系统的识别率,加强其对光照、表情、姿态变化的鲁棒性,针对人脸识别中的特征提取问题,提出一种基于Log-Gabor与均匀局部二值模式(Uniform Local Binary Pattern,ULBP)改进算法的人脸识别方法。该算法采用多尺度、...为进一步提升人脸识别系统的识别率,加强其对光照、表情、姿态变化的鲁棒性,针对人脸识别中的特征提取问题,提出一种基于Log-Gabor与均匀局部二值模式(Uniform Local Binary Pattern,ULBP)改进算法的人脸识别方法。该算法采用多尺度、多方向Log-Gabor滤波器对图像进行滤波来提取Log-Gabor特征,再通过旋转不变均匀模式的LBP进行运算编码,并利用局部空间直方图来描述人脸,最后通过加权的卡方距离对直方图匹配完成人脸识别。在Yale、GT人脸数据库上的测试结果表明,该方法具有更好识别性能,且对环境鲁棒性较好。展开更多
Recognition of the human actions by computer vision has become an active research area in recent years. Due to the speed and the high similarity of the actions, the current algorithms cannot get high recognition rate....Recognition of the human actions by computer vision has become an active research area in recent years. Due to the speed and the high similarity of the actions, the current algorithms cannot get high recognition rate. A new recognition method of the human action is proposed with the multi-scale directed depth motion maps(MsdDMMs) and Log-Gabor filters. According to the difference between the speed and time order of an action, MsdDMMs is proposed under the energy framework. Meanwhile, Log-Gabor is utilized to describe the texture details of MsdDMMs for the motion characteristics. It can easily satisfy both the texture characterization and the visual features of human eye. Furthermore, the collaborative representation is employed as action recognition by the classification. Experimental results show that the proposed algorithm, which is applied in the MSRAction3 D dataset and MSRGesture3 D dataset, can achieve the accuracy of 95.79% and 96.43% respectively. It also has higher accuracy than the existing algorithms, such as super normal vector(SNV), hierarchical recurrent neural network(Hierarchical RNN).展开更多
文摘针对2维超声心动图像噪声大且难于分割的特点,提出基于Centripetal Catmull-Rom曲线的多尺度活动形状模型的左心室分割方法。该算法在金字塔上层提取2维轮廓法线向量特征并采用马氏距离寻找新的特征点位置;在图像金字塔底层快速提取特征点周围的Log-Gabor特征并使用Gentle Ada Boost训练分类器,选择置信度水平最高的点作为新的特征点位置。实验证明,这种方法较之传统活动形状模型分割更为精确且分割结果交互方便,有利于对结果的再编辑。
文摘In this paper, we propose a sparse overcomplete image approximation method based on the ideas of overcomplete log-Gabor wavelet, mean shift and energy concentration. The proposed approximation method selects the necessary wavelet coefficients with a mean shift based algorithm, and concentrates energy on the selected coefficients. It can sparsely approximate the original image, and converges faster than the existing local competition based method. Then, we propose a new compression scheme based on the above approximation method. The scheme has compression performance similar to JPEG 2000. The images decoded with the proposed compression scheme appear more pleasant to the human eyes than those with JPEG 2000.
文摘为进一步提升人脸识别系统的识别率,加强其对光照、表情、姿态变化的鲁棒性,针对人脸识别中的特征提取问题,提出一种基于Log-Gabor与均匀局部二值模式(Uniform Local Binary Pattern,ULBP)改进算法的人脸识别方法。该算法采用多尺度、多方向Log-Gabor滤波器对图像进行滤波来提取Log-Gabor特征,再通过旋转不变均匀模式的LBP进行运算编码,并利用局部空间直方图来描述人脸,最后通过加权的卡方距离对直方图匹配完成人脸识别。在Yale、GT人脸数据库上的测试结果表明,该方法具有更好识别性能,且对环境鲁棒性较好。
基金Sponsored by the Jiangsu Prospective Joint Research Project(Grant No.BY2016022-28)
文摘Recognition of the human actions by computer vision has become an active research area in recent years. Due to the speed and the high similarity of the actions, the current algorithms cannot get high recognition rate. A new recognition method of the human action is proposed with the multi-scale directed depth motion maps(MsdDMMs) and Log-Gabor filters. According to the difference between the speed and time order of an action, MsdDMMs is proposed under the energy framework. Meanwhile, Log-Gabor is utilized to describe the texture details of MsdDMMs for the motion characteristics. It can easily satisfy both the texture characterization and the visual features of human eye. Furthermore, the collaborative representation is employed as action recognition by the classification. Experimental results show that the proposed algorithm, which is applied in the MSRAction3 D dataset and MSRGesture3 D dataset, can achieve the accuracy of 95.79% and 96.43% respectively. It also has higher accuracy than the existing algorithms, such as super normal vector(SNV), hierarchical recurrent neural network(Hierarchical RNN).
