Face presentation attack detection using guided scale texture

Multimedia Tools and Applications - Aiming to counter presentation attack (also known as spoofing attack) in face recognition system, a face presentation attack detection (also known as spoofing...     

Face detection in color images

Human face detection plays an important role in applications such as video surveillance, human computer interface, face recognition, and face image database management. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex backgrounds. Based on a novel lighting compensation technique and a nonlinear color transformation, our method detects skin regions over the entire image and then generates face candidates based on the spatial arrangement of these skin patches. The algorithm constructs eye, mouth, and boundary maps for verifying each face candidate. Experimental results demonstrate successful face detection over a wide range of facial variations in color, position, scale, orientation, 3D pose, and expression in images from several photo collections (both indoors and outdoors)     

Face detection from color images using a fuzzy pattern matchingmethod

This paper describes a new method to detect faces in color images based on the fuzzy theory. We make two fuzzy models to describe the skin color and hair color, respectively. In these models, we use a perceptually uniform color space to describe the color information to increase the accuracy and stableness. We use the two models to extract the skin color regions and the hair color regions, and then comparing them with the prebuilt head-shape models by using a fuzzy theory based pattern-matching method to detect face candidates     

SOM Segmentation of gray scale images for optical recognition

This paper describes a clustering technique using Self Organizing Maps and a two-dimensional histogram of the image. The two-dimensional histogram is found using the pixel value and the mean in the neighborhood. This histogram is fed to a self organizing map that divides the histogram into regions. Carefully selecting the number of regions, a scheme that allows an optimum optical recognition of texts can be found.

The algorithm is specially suited for optical recognition application where a very high degree of confidence is needed. As an example application, the algorithm has been tested in a voting application, where a high degree of precision is required. Furthermore, the algorithm can be extended to any other thresholding or clustering applications.     

Adaptive gray scale mapping to reduce registration noise in difference images

Difference images are used in various image processing applications such as change detection, radar imaging, remote sensing, and biomedical image analysis. The difference image, or difference picture, is found by subtracting one image from another. One practical problem with difference images is that, if the images are not in perfect spatial registration before subtraction, their difference image will contain artifacts caused by incomplete cancellation of the unchanged background objects. These artifacts (registration noise) show up as extraneous light and dark regions on either side of the background objects. Usually, this noise is reduced by either smoothing (blurring), or thresholding the difference image. This paper describes a new method to reduce registration noise using adaptive gray scale mapping. This simple digital filter reduces registration noise as well as, or better than, previous methods, with less degradation of the actual differences between the images.     

基于Gabor小波和局部线性嵌入的人脸识别

提出了一种新的人脸识别算法。该算法采用Gabor小波和一种新颖的方式来提取人脸特征,利用局部线性嵌入（Locally Linear Embedding,LLE）算法来实现数据的非线性降维处理,最后训练基于欧式距离的最近邻分类器进行分类判决。在ORL人脸库中与PCA方法、Gabor小波+PCA方法和直接的LLE算法进行了实验比较,实验结果表明,提出的Gabor小波+LLE的方法具有更优的性能。     

Application of Baddeley''s distance to dissimilarity measurement between gray scale images

In this paper, we introduce a dissimilarity measure between two gray-scale images based on Baddeley's distance. To some extent, it can be regarded as a modification of that proposed by Wilson et al. [Internat. J. Comput. Vision 24 (1) (1997) 5–18]. Images are represented by surfaces in a 3D space, instead of their subgraphs. Distance calculations are performed by means of a 3D local distance operator adapted to parallelepipedic grids. No truncation effect is introduced. Properties of the new dissimilarity operator are compared to those of the Wilson–Baddeley–Owen operator in terms of sensitivity to gray level variations, spatial shifts and shape distortions. Compared with the Wilson–Baddeley–Owen operator, a more linear behavior is observed. A simplified phenomenological model is proposed in order to explain this behavior.     

基于局部线性嵌入的视频镜头变换检测

介绍了一种新的视频镜头变换类型检测方法,利用局部线性嵌入算法提取镜头变换的一维流形特征,用K近邻分类器确定渐变镜头变换的类型.实验表明,本算法镜头变换类型的识别率为97.5%以上.     

Nonlinear fault detection based on locally linear embedding

In this paper, a new nonlinear fault detection technique based on locally linear embedding （LLE） is developed. LLE can efficiently compute the low-dimensional embedding of the data with the local neighborhood structure information preserved. In this method, a data-dependent kernel matrix which can reflect the nonlinear data structure is defined. Based on the kernel matrix, the Nystrrm formula makes the mapping extended to the testing data possible. With the kernel view of the LLE, two monitoring statistics are constructed. Together with the out of sample extensions, LLE is used for nonlinear fault detection. Simulation cases were studied to demonstrate the performance of the proposed method.     

MGSI-8CA标记算法

针对已有连通域标记算法不能适用于遥感数据等海量灰度图像八连通域快速标记的问题,设计并实现了一种MGSI-8CA标记算法。该算法对传统的八连通域标记算法进行八向变四向优化,采用列表机制解决连通域标记冲突问题,并引入了筛选机制和分块处理机制,实现了对海量灰度图像八连通域标记的快速处理,同时也得到了灰度图像连通域的正确划分及精确的连通域数目。实验结果证明,MGSI-8CA标记算法运行效率高,更能适应海量灰度图像处理的要求。     

新的噪声污染灰度图像边缘检测方法

传统的图像边缘检测方法由于引入了各种微分运算,因此用于噪声图像边缘检测时对噪声极度敏感。针对这一问题,提出了一种基于独立分量分析技术的噪声图像边缘检测方法,该算法通过计算数据之间的高阶统计信息,提取特征模板,然后将被高斯噪声污染的灰度图像与这些模板逐个匹配,提取出边缘成分。实验结果表明,基于独立分量分析技术的模板匹配方法自适应强,复杂度低,是一种有效的高斯噪声污染灰度图像边缘检测方法。     

Optimal one-page tree embeddings in linear time

In the minimum linear arrangement problem one wishes to assign distinct integers to the vertices of a given graph so that the sum of the differences (in absolute value) across the edges of the graph is minimized. This problem is known to be NP-complete for the class of all graphs, but polynomial for trees—algorithms of time complexity O(n^2.2) and O(n^1.6) were given by Shiloach [SIAM J. Comput. 8 (1979) 15-32] and Chung [Comput. Math. Appl. 10 (1984) 43-60], respectively. We present a linear-time algorithm for finding the optimal embedding (arrangement) in a restricted but important class of embeddings called one-page embeddings.¹     

Face recognition in low-quality images using adaptive sparse representations

Although unconstrained face recognition has been widely studied over the recent years, state-of-the-art algorithms still result in an unsatisfactory performance for low-quality images. In this paper, we make two contributions to this field: the first one is the release of a new dataset called ‘AR-LQ’ that can be used in conjunction with the well-known ‘AR’ dataset to evaluate face recognition algorithms on blurred and low-resolution face images. The proposed dataset contains five new blurred faces (at five different levels, from low to severe blurriness) and five new low-resolution images (at five different levels, from 66 × 48 to 7 × 5 pixels) for each of the hundred subjects of the ‘AR’ dataset. The new blurred images were acquired by using a DLSR camera with manual focus that takes an out-of-focus photograph of a monitor that displays a sharp face image. In the same way, the low-resolution images were acquired from the monitor by a DLSR at different distances. Thus, an attempt is made to acquire low-quality images that have been degraded by a real degradation process. Our second contribution is an extension of a known face recognition technique based on sparse representations (ASR) that takes into account low-resolution face images. The proposed method, called blur-ASR or bASR, was designed to recognize faces using dictionaries with different levels of blurriness. These were obtained by digitally blurring the training images, and a sharpness metric for matching blurriness between the query image and the dictionaries. These two main adjustments made the algorithm more robust with respect to low-quality images. In our experiments, bASR consistently outperforms other state-of-the-art methods including hand-crafted features, sparse representations, and seven well-known deep learning face recognition techniques with and without super resolution techniques. On average, bASR obtained 88.8% of accuracy, whereas the rest obtained less than 78.4%.     

新的噪声污染灰度图像边缘检测统计方法*

针对传统算子进行边缘检测时易丢失边缘信息和在非边缘处增强噪声的缺陷,提出一种基于非参数变点统计分析的噪声图像边缘检测方法,该统计方法不但不需要图像数字特征的任何先验信息,而且对噪声污染的图像不作任何滤波处理.实验结果表明,提出的算法优于Sobel算子,并能抑制信噪较低的高斯噪声和密度较高的椒盐噪声对分割结果的影响,是一种有效的噪声污染灰度图像边缘检测方法.     

基于细胞神经网络的灰度图像边缘提取

针对细胞神经网络(cellular neural network,CNN),研究了图像边缘提取的过程,给出算法流程,阐述了算法实现过程中的几个关键步骤.对二值图像和灰度图像,分别采用基于CNN的算法和传统算子(prewitt、sobel、canny)进行边缘提取,定性分析比较了两类算法在性能上的优劣.实验结果表明,基于CNN的算法在硬件实现上能够高速并行计算,而且处理速度与图像大小无关,能够实现图像实时处理.     

Parameterized real-time moment computation on gray images using block techniques

Moments constitute a well-known tool in the field of image analysis and pattern recognition, but they suffer from the drawback of high computational cost. Efforts for the reduction of the required computational complexity have been reported, mainly focused on binary images, but recently some approaches for gray images have been also presented. In this study, we propose a simple but effective approach for the computation of gray image moments. The gray image is decomposed in a set of binary images. Some of these binary images are substituted by an ideal image, which is called “half-intensity” image. The remaining binary images are represented using the image block representation concept and their moments are computed fast using block techniques. The proposed method computes approximated moment values with an error of 2–3% from the exact values and operates in real time (i.e., video rate). The procedure is parameterized by the number m of “half-intensity” images used, which controls the approximation error and the speed gain of the method. The computational complexity is O(kL ²), where k is the number of blocks and L is the moment order.     

基于邻域参数动态变化的局部线性嵌入人脸识别

为了增强局部线性嵌入(LLE)算法对人脸识别中特征的分类性能,将最小生成树算法思想引入,提出一种邻域参数动态变化的新的局部线性嵌入算法.该算法采用单链聚类算法以及对其进一步优化自动确定数据点邻域,改善了一般局部线性嵌入算法固定邻域的不足,及其处理现实中大量非均匀源数据集失效问题的缺点.将改进后的算法结合支持向量机(SVM)分类器进行人脸识别,在ORL和YALE人脸数据库的平均识别率得到较高提升.仿真实验结果验证了该算法的有效性.     

基于监督局部线性嵌入特征提取的高光谱图像分类

高光谱图像的数据维数高、数据量大、数据间高度冗余等特点给图像分类带来困难,为进行有效降维、提高分类精度,提出了一种监督局部线性嵌入(SLLE)非线性流形学习特征提取方法。SLLE算法根据数据先验类标签信息所给出的新距离寻找数据点的k最近邻(NN),新距离使得类内距离小于类间距离,这使得SLLE算法更有利于分类。高光谱图像数据和UCI数据的分类结果表明了该方法的有效性。