Multi-resolution feature fusion for face recognition

For face recognition, image features are first extracted and then matched to those features in a gallery set. The amount of information and the effectiveness of the features used will determine the recognition performance. In this paper, we propose a novel face recognition approach using information about face images at higher and lower resolutions so as to enhance the information content of the features that are extracted and combined at different resolutions. As the features from different resolutions should closely correlate with each other, we employ the cascaded generalized canonical correlation analysis (GCCA) to fuse the information to form a single feature vector for face recognition. To improve the performance and efficiency, we also employ “Gabor-feature hallucination”, which predicts the high-resolution (HR) Gabor features from the Gabor features of a face image directly by local linear regression. We also extend the algorithm to low-resolution (LR) face recognition, in which the medium-resolution (MR) and HR Gabor features of a LR input image are estimated directly. The LR Gabor features and the predicted MR and HR Gabor features are then fused using GCCA for LR face recognition. Our algorithm can avoid having to perform the interpolation/super-resolution of face images and having to extract HR Gabor features. Experimental results show that the proposed methods have a superior recognition rate and are more efficient than traditional methods.     

Towards adaptive learning with improved convergence of deep belief networks on graphics processing units

In this paper we focus on two complementary approaches to significantly decrease pre-training time of a deep belief network (DBN). First, we propose an adaptive step size technique to enhance the convergence of the contrastive divergence (CD) algorithm, thereby reducing the number of epochs to train the restricted Boltzmann machine (RBM) that supports the DBN infrastructure. Second, we present a highly scalable graphics processing unit (GPU) parallel implementation of the CD-k algorithm, which boosts notably the training speed. Additionally, extensive experiments are conducted on the MNIST and the HHreco databases. The results suggest that the maximum useful depth of a DBN is related to the number and quality of the training samples. Moreover, it was found that the lower-level layer plays a fundamental role for building successful DBN models. Furthermore, the results contradict the pre-conceived idea that all the layers should be pre-trained. Finally, it is shown that by incorporating multiple back-propagation (MBP) layers, the DBNs generalization capability is remarkably improved.     

大冶硫酸四系列干吸塔结构特点

以干燥塔为例，介绍大冶公司硫酸四系列干吸塔的结构特点。除捕沫层简体及出气管为316L不锈钢外，其余塔体均为碳钢内衬瓷砖结构。塔底为球形底，中心排酸。采用槽管式分酸器，分酸点密度为43个/m^2，设可调闸板以保证各槽酸量均匀；闸板外设置带孔板的分布板，以消除进口酸的冲击，保证槽内酸液面平稳。比较了该塔与常规塔的不同之处，强调了设备节点的优化设计。     

Skeleton-enhanced line drawings for 3D models

We present a novel line drawing approach for 3D models by introducing their skeleton information into the rendering process. Based on the silhouettes of the input 3D models, we first extract feature lines in geometric regions by utilizing their curvature, torsion and view-dependent information. Then, the skeletons of the models are extracted by our newly developed skeleton extraction algorithm. After that, we draw the skeleton-guided lines from non-geometric regions through the skeleton information. These lines are combined with the feature lines to render the final line drawing result using the line optimization. Experimental results show that our algorithm can render line drawings more effectively with enhanced skeletons. The resulting artistic effects can capture the local geometries as well as the global skeletons of the input 3D models.     

一种道路车辆监控视频中的关键帧提取方法

针对道路监控视频中特定车辆图像序列的关键帧提取问题,在运动对象检测的基础上,提出一种关键帧提取方法。将积分通道特征和面积特征作为图像特征描述子,结合Ada Boost训练分类器,实现道路监控视频车辆序列图像中关键帧的提取。通过运动对象前景检测技术获得出现在监控区域的运动车辆最小外接矩形图像序列,选择满足监控分析需求(车牌清晰度高,能判断车型)的若干帧作为正样本,其他不满足监控分析需求的作为负样本,提取样本图像的面积特征和积分通道特征,利用Ada Boost方法训练得到一个分类器,使用Ada Boost分类器对测试样本进行分类,根据打分规则提取关键帧。实验结果表明,该方法能提取运动车辆从进入到离开监控区域的序列图像帧中最清晰的图像,实现道路车辆监控视频分析数据的有效压缩。     

基于NSST和RI-LPQ的纹理图像检索

针对采用单一方法提取图像特征时检索率不高的问题,结合非下采样剪切波变换(NSST)统计特征和旋转不变的局部相位量化(RI-LPQ)原理,提出一种纹理图像检索方法。非下采样剪切波不仅具有方向选择性及平移不变性,而且可以对图像进行有效的稀疏表示,与传统小波相比,可有效捕捉图像的边缘轮廓等纹理信息,与非下采样轮廓波相比,具有更高的计算效率。利用广义高斯分布函数对图像NSST高频子带系数的统计特征进行分析,RI-LPQ描述算子直接提取图像特征,采用具有权重系数的相似性测度公式对Brodatz图像库进行纹理图像检索。实验结果表明,与传统小波和轮廓波的方法相比,NSST统计特征方法的平均检索率分别提高4.77%和1.44%,纹理图像检索方法的平均检索率分别提高7.36%和1.98%。     

基于动态特性的D-LTSV语音端点检测方法

端点检测是语音信号处理的一个关键环节。为提高语音在低性噪比以及非平稳噪声环境下的端点检测性能,在长时信号变化特征(LTSV)的基础上提出一种新的D-LTSV语音端点检测方法。采用Bartlett-Welch方法估计语音谱,分析语音谱在长时域上的熵,利用倒谱的动态特性分析方法提取连续帧熵值的动态变化特征。实验结果表明,D-LTSV综合考虑了语音的非平稳性和帧间非平稳性的动态变化情况,具有比LTSV更好的分辨能力,特别是在低性噪比和非平稳噪声的环境下,D-LTSV的分辨能力提升了50.77%,能够准确地进行端点检测,具有更强的鲁棒性。     

快速鲁棒特征算法的CUDA加速优化

提出一种基于统一计算设备架构(Compute Unified Device Architecture,CUDA)的快速鲁棒特征(Speed-up Robust Feature,SURF)图像匹配算法。分析了SURF算法的并行性,在图像处理单元(Graphics Processing Unit,GPU)的线程映射和内存模型方面对算法的构建尺度空间、特征点提取、特征点主方向的确定、特征描述子的生成及特征匹配5个步骤进行CUDA加速优化。实验表明,相比适用于CPU的SURF算法,文中提出的适用于GPU的SURF算法在处理30MB的图片时性能提高了33倍。适用于GPU的SURF算法拓展了SURF算法在遥感等领域的快速应用,尤其是大影像的快速配准。     

一种应用于复杂组合软件的可靠性测试模型

当前复杂的组合型软件可靠性测试一直是一个难点,主要原因是无法多多种差异性较大的软件特征建立可约束的检测分析模型,一旦软件数量过多,模型会迅速陷入不收敛。为了解决这一问题,提出一种复杂组合差异性软件的可靠性分析模型。对组合软件以一种分解的思想对其进行建模。对分解后的软件特征进行重新分区建模。形成多个可测试的子服务特征。运用一种稳定概率统计的观点,对模型进行分析,分析不同区域组合后的稳定概率,进而代表组合后的可靠性结果。仿真实验结果表明,该种模型能改对较多软件组成的、差异性较大的大型软件可靠性进行更为合理的分析,模型鲁棒性较好,能较好完成可靠性分析的工作。