基于HOG特征与子区域模糊融合的人耳识别研究

作为一种新兴的生物特征识别技术,人耳识别具有其自身独特优势.利用局部特征信息,研究一类新型的基于梯度方向直方图的人耳身份识别方法,提出一种基于梯度方向直方图与子区域模糊融合相结合的人耳识别方案.将人耳图像划分为不同子区域,分别提取各子区域梯度方向直方图特征,引入模糊隶属度匹配融合策略,获取最终的分类结果.与多种方法的对比实验表明,基于梯度方向直方图的特征提取方法具有高识别性能,针对USTB人耳图像库3的测试实验,可达到99.75％的识别率.     

基于指导滤波与二值图像组互相关匹配的3D掌纹识别

提出了一种鲁棒的掌纹识别方法。在特征提取阶段,使用指导图像滤波去除噪声,然后基于Gabor变换提取鲁棒的掌纹方向特征,并使用一组二值图像表示每幅3D掌纹图像;在匹配阶段,采用了基于二值图像组互相关运算的匹配算法。该方法能够充分利用图像组中的特征配准图像来得到准确的匹配分数。HK-PolyU 2D+3Dpalmprint database数据库上的实验表明,该方法能够有效提高掌纹识别算法的识别率。     

语义级深度迁移的2D转3D算法

海量视频数据推动了基于数据驱动的单目图像深度估计研究.针对现有方法存在不同对象深度分配层次感不够的问题,在相似场景具有相似深度的假设前提下,提出一种基于语义级分割和深度迁移的单目图像2D转3D的方法.首先使用分割迁移模型将输入图像的像素进行语义级分类;然后通过语义级分类结果对场景匹配进行约束;再次利用SIFT流建立输入图像和匹配图像间像素级对应关系,并由此将匹配图像的深度迁移到输入图像上;最后通过语义级分割约束的最优化深度融合模型为不同对象区域分配深度值.Make3D测试数据的实验结果表明,该方法估计的深度质量比现有深度迁移方法更高,与最优化融合深度迁移算法相比,平均对数误差和平均相对误差分别降低0.03和0.02个点.     

基于多列深度3D卷积神经网络的手势识别

传统2D卷积神经网络对于视频连续帧图像的特征提取容易丢失目标时间轴上的运动信息,导致识别准确度较低。为此,提出一种基于多列深度3D卷积神经网络(3D CNN)的手势识别方法。采用3D卷积核对连续帧图像进行卷积操作,提取目标的时间和空间特征捕捉运动信息。为避免因单组3D CNN特征提取不充分而导致的误分类,训练多组具有较强分类能力的3D CNN结构组成多列深度3D CNN,该结构通过对多组3D CNN的输出结果进行权衡,将权重最大的类别判定为最终的输出结果。实验结果表明,将多列深度3D CNN应用于CHGDs数据集上进行手势识别,识别率达到95.09%,与单组3D CNN及传统2D CNN相比分别提高近7%,20%,对连续图像目标识别具有较好的识别能力。     

基于人耳生物特征的身份识别

人耳识别技术的研究与应用在个体生物特征识别范围属于一种新的尝试.本文首先讨论了人耳识别技术的可行性及其特点,介绍了基于二维灰度图像、3D深度图像和耳纹图像的人耳自动识别方法,并重点对静态人耳图像识别方法进行了总结.最后针对人耳识别技术中的一些关键性问题,如人耳特征信息的提取、人耳图像的遮挡与缺损处理、人耳识别方法以及人耳图像库的构建进行了探讨,提出一些解决问题的思路.     

基于融合哈希粗匹配的快速手指静脉识别方法

针对基于模板匹配的手指静脉识别过程中存在大量异源匹配导致匹配时间长的问题,提出一种融合哈希粗匹配和加权LTS-HD精确匹配相结合的二次匹配特征识别方法.首先,在特征提取过程自适应设置检测算子的移动步长,减少宽线检测算法中的冗余计算;然后,使用均值哈希算法和差值哈希算法计算静脉图像相似度进行加权融合,利用遗传算法进行权重...     

基于灰度曲面匹配的人耳识别方法

本文提出了一种基于灰度曲面匹配的人耳识别方法。该方法摒弃特征提取和编码等传统操作，依据整体特征分析的思想直接利用耳朵的灰度曲面进行匹配。首先，对耳图像的大小和灰度进行调整。其次，对两幅耳图像的灰度值做差，得到灰度差曲面。最后，求出该灰度差曲面的方差，并将方差作为衡量两幅耳图像是否匹配的依据。     

多尺度特征融合的残缺卷烟编码识别

针对背景紊乱、字符残缺的卷烟图像,提出多尺度特征融合的残缺卷烟编码识别方法,以进行端到端的训练与应用.首先使用特征提取网络从图像中提取多尺度融合特征;然后提出区域优化模块,对提取到的融合特征进一步优化,识别与定位网络学习这些优化后的特征能更加鲁棒地完成识别与定位任务;最后使用匹配算法对识别与定位结果进行匹配,得到最终结...     

一种基于D-S证据理论的融合RGB特征和Depth特征的3D目标识别方法

针对利用单一特征进行3D目标识别导致识别率低的问题,结合RGB图像和Depth图像的优势,提出一种结合支持向量机(SVM)和D-S证据理论的融合RGB特征和Depth特征的3D目标识别方法。该方法提取目标物体的RGB特征以及Depth特征,分别以这两类单特征的SVM的概率输出作为独立的证据,构造出基于每个证据的基本概率分配函数(BPA),利用D-S证据融合规则进行证据融合,并根据决策准则得到最终的3D目标识别结果。在Kinect相机得到的RGB-D数据集上进行实验验证,结果表明,该方法能够有效地实现对RGB特征和Depth特征的融合,提高了3D目标识别的识别准确性和可靠性。     

基于独立分量分析的人耳图像识别方法

人耳识别是一种新的生物特征识别技术.本文将独立分量分析应用于人耳图像的特征提取,并分别与最近邻分类器、RBF神经网络分类器和支持向量机相结合进行分类识别.实验结果表明基于独立分量分析的人耳识别方法优于传统的主分量分析方法.     

基于色彩空间分块匹配的三维动画融合技术

为了提高影视动画制作的三维图像成像质量,需要进行动画图像的动态信息融合处理,提出一种基于二维色彩空间分块匹配的三维动画图像的动态信息融合处理技术,采用虚拟视景重构技术进行三维动画图像采集和特征投影处理,对三维动画图像进行二值拟合和边缘轮廓检测,采用RGB分解技术进行三维动画图像的颜色分量提取,采用颜色模板空间投影算法进行三维动画图像的分块融合处理,提高三维动画图像的边缘像素点的特征配对性能,结合三维动画图像的色彩空间分块融合结果进行像素特征优化配置,计算匹配窗口相关系数,实现三维动画图像的动态信息融合处理。仿真结果表明,采用该方法进行三维动画图像的动态信息融合处理,能提高图像输出峰值信噪比,提高动态成像质量。     

Efficient Detection and Recognition of 3D Ears

The use of ear shape as a biometric trait is a recent trend in research. However, fast and accurate detection and recognition of the ear are very challenging because of its complex geometry. In this work, a very fast 2D AdaBoost detector is combined with fast 3D local feature matching and fine matching via an Iterative Closest Point (ICP) algorithm to obtain a complete, robust and fully automatic system with a good balance between speed and accuracy. Ear images are detected from 2D profile images using the proposed Cascaded AdaBoost detector. The corresponding 3D ear data is then extracted from the co-registered range image and represented with local 3D features. Unlike previous approaches, local features are used to construct a rejection classifier, to extract a minimal region with feature-rich data points and finally, to compute the initial transformation for matching with the ICP algorithm. The proposed system provides a detection rate of 99.9% and an identification rate of 95.4% on Collection F of the UND database. On a Core 2 Quad 9550, 2.83 GHz machine, it takes around 7.7 ms to detect an ear from a 640×480 image. Extracting features from an ear takes 22.2 sec and matching it with a gallery using only the local features takes 0.06 sec while using the full matching including ICP requires 2.28 sec on average.     

2D/3D information fusion for building extraction from high-resolution satellite stereo images using kernel graph cuts

This study presents a building extraction strategy from High-resolution satellite stereo images (HRSSI) using 2D and 3D information fusion. In the 2D processing strategy, a visible vegetation index (VVI) is generated. In the 3D processing, a disparity map is generated using semi-global matching (SGM). To remove defects from the disparity map, an object-based approach is proposed by using mean-shift image segmentation and extracting rectangles. By removing terrain effects, a normalized disparity map (nDM) is produced. In the next step, vegetation pixels are removed from nDM and an initial building mask is generated. As nDM does not have precise building boundaries, hybrid segmentation by the kernel graph cut (KGC) is applied to the feature space including the RGB, nDM, and VVI and the results are used in a decision level fusion step. By this methodology, segments that are highly intersected with initial building mask are classified as buildings. Finally, a building boundary refinement (BBR) algorithm is applied to buildings for removing the remaining defects. The proposed method is applied to two pairs of GeoEye-1 stereo images including residential and industrial test areas. Evaluation results show the completeness and correctness level of higher than 90% for the two test areas. Further evaluations show that the quality metric has significantly changed after decision level fusion using the KGC.     

An ear biometric system based on artificial bees and the scale invariant feature transform

Ear recognition is a new biometric technology that competes with well-known biometric modalities such as fingerprint, face and iris. However, this modality suffers from common image acquisition problems, such as change in illumination, poor contrast, noise and pose variation. Using a 3D ear models reduce rotation, scale variation and translation-related problems, but they are computationally expensive. This paper presents a new architecture of ear biometrics that aims at solving the acquisition problems of 2D ear images. The proposed system uses a new ear image contrast enhancement approach based on the gray-level mapping technique, and uses an artificial bee colony (ABC) algorithm as an optimizer. This technique permits getting better-contrasted 2D ear images. In the feature extraction stage, the scale invariant feature transform (SIFT) is used. For the matching phase, the Euclidean distance is adopted. The proposed approach was tested on three reference ear image databases: IIT Delhi, USTB 1 and USTB 2, and compared with traditional ear image contrast enhancement approaches, histogram equalization (HE) and contrast limited adaptive histogram equalization (CLAHE). The obtained results show that the proposed approach outperforms traditional ear image contrast enhancement techniques, and increases the amount of detail in the ear image, and consequently improves the recognition rate.     

结合三维几何形状信息和二维纹理的3D目标匹配

为了实现场景中三维目标与模型之间的匹配,提出了一种结合三维几何形状信息和二维纹理的三维目标匹配方法。首先提取场景中深度图像的尺度不变特征变换(SIFT)特征,用SIFT算法与三维模型重建时所用到的一系列2.5维深度图像进行一一匹配,找到与场景中目标姿态最为相似的深度图像,提取此深度图像的三维几何形状特征与模型进行匹配,实现模型的初始化,即将模型重置到与场景目标相接近的姿态。最后用融合二维纹理信息的迭代就近点（ICP）算法实现场景中目标与模型之间的匹配,从而得到场景中三维目标的准确姿态。实验结果验证了方法的可行性与精确性。     

基于稀疏图像序列的雕塑点自动云三维重构方法

为了提高对雕塑点稀疏图像的点云三维重建的分析能力,提出一种基于稀疏图像序列的雕塑点自动云三维重构方法,基于稀疏散乱点三维重建和锐化模板特征匹配方法进行图像三维重建。采用三维角点检测和边缘轮廓特征提取方法,进行雕塑点稀疏图像三维点云特征检测,对检测的雕塑点稀疏图像点云数据进行信息融合处理,采用梯度运算方法进行特征分解,实现对雕塑点稀疏图像的信息增强和融合滤波。结合局部均值降噪方法进行图像的提纯处理,提高雕塑点稀疏图像轮廓重建能力,采用锐化模板特征匹配和块分割技术,实现雕塑点自动云三维重构。仿真结果表明,采用该方法进行雕塑点自动云三维重构的准确性较高,图像匹配能力较好,且重构输出信噪比较高。     

Ear recognition based on local information fusion

Ears have rich structural features that are almost invariant with increasing age and facial expression variations. Therefore ear recognition has become an effective and appealing approach to non-contact biometric recognition. This paper gives an up-to date review of research works on ear recognition. Current 2D ear recognition approaches achieve good performance in constrained environments. However the recognition performance degrades severely under pose, lighting and occlusion. This paper proposes a 2D ear recognition approach based on local information fusion to deal with ear recognition under partial occlusion. Firstly, the whole 2D image is separated to sub-windows. Then, Neighborhood Preserving Embedding is used for feature extraction on each sub-window, and we select the most discriminative sub-windows according to the recognition rate. Each sub-window corresponds to a sub-classifier. Thirdly, a sub-classifier fusion approach is used for recognition with partially occluded images. Experimental results on the USTB ear dataset and UND dataset have illustrated that using only few sub-windows we can represent the most meaningful region of the ear, and the multi-classifier model gets higher recognition rate than using the whole image for recognition.     

一种快速的三维扫描数据自动配准方法

研究了两幅和多幅深度图像的自动配准问题.在配准两幅深度图像时,结合二维纹理图像配准深度图像,具体过程是:首先,从扫描数据中提取纹理图像,特别地,针对不包含纹理图像的扫描数据提出了一种根据深度图像直接生成纹理图像的方法;然后,基于SIFT(scale-invariant feature transform)特征提取纹理图像中的兴趣像素,并通过预过滤和交叉检验兴趣像素等方法从中找出匹配像素对的候选集;之后,使用RANSAC(random sample consensus)算法,根据三维几何信息的约束找出候选集中正确的匹配像素对和相对应的匹配顶点对,并根据这些匹配顶点对计算出两幅深度图像间的刚体置换矩阵;最后,使用改进的ICP(iterative closest point)算法优化这一结果.在配准多幅深度图像时,提出了一种快速构建模型图的方法,可以避免对任意两幅深度图像作配准,提高了配准速度.该方法已成功应用于多种文物的三维逼真建模.