Two-dimensional complete neighborhood preserving embedding

Complete neighborhood preserving embedding (CNPE) is an improvement to the neighborhood preserving embedding (NPE) algorithm, which can address the singularity and stability problems of NPE and at the same time preserve useful discriminative information. However, CNPE works with vectorized representations of data, and thus, the original 2D face image matrices should be previously transformed into the same dimensional vectors. Such a matrix-to-vector transform usually leads to a high-dimensional image vector space, which makes the eigenanalysis quite difficult and time-consuming. Beyond computational issues, some spatial structural information between nearby pixels may be lost after vectorization. In this paper, we develop a new scheme for image feature extraction, namely, two-dimensional complete neighborhood preserving embedding (2D-CNPE). 2D-CNPE builds the eigenmatrix and the weight matrix which characterize local neighborhood properties of data directly based on the original face images, and then, the optimal embedding axes are obtained by performing an eigen-decomposition. Experimental results on three face databases show that the proposed 2D-CNPE achieves better performance than other feature extraction methods, such as Eigenfaces, Fisherfaces, and 2D-PCA.     

A region dissimilarity relation that combines feature-space and spatial information for color image segmentation.

This paper proposes a methodology that incorporates principles from cluster analysis and graph representation to achieve efficient image segmentation results. More specifically, a feature-based, inter-region dissimilarity relation is considered here in order to determine the dissimilarity matrix in a graph-based segmentation scheme. The calculation of the dissimilarity function between adjacent elementary image regions is based on the proximity of each region's feature vector to the main clusters that are formed by the image samples in the feature space. In contrast to typical segmentation approaches of the literature, the global feature space information is included in the spatial graph representation that was derived from the initial Watershed partitioning. A region grouping process is applied next to form the final segmentation results. The proposed approach was also compared to approaches that use feature-based, or spatial information exclusively, to indicate its effectiveness.     

Supervised optimal locality preserving projection

In the past few years, the computer vision and pattern recognition community has witnessed a rapid growth of a new kind of feature extraction method, the manifold learning methods, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among these methods, locality preserving projection (LPP) is one of the most promising feature extraction techniques. Unlike the unsupervised learning scheme of LPP, this paper follows the supervised learning scheme, i.e. it uses both local information and class information to model the similarity of the data. Based on novel similarity, we propose two feature extraction algorithms, supervised optimal locality preserving projection (SOLPP) and normalized Laplacian-based supervised optimal locality preserving projection (NL-SOLPP). Optimal here means that the extracted features via SOLPP (or NL-SOLPP) are statistically uncorrelated and orthogonal. We compare the proposed SOLPP and NL-SOLPP with LPP, orthogonal locality preserving projection (OLPP) and uncorrelated locality preserving projection (ULPP) on publicly available data sets. Experimental results show that the proposed SOLPP and NL-SOLPP achieve much higher recognition accuracy.     

Facial expression recognition based on dual-feature fusion and improved random forest classifier

Facial expression recognition (FER) is an important means for machines to understand the changes in the facial expression of human beings. Expression recognition using single-modal facial images, such as gray scale, may suffer from illumination changes and the lack of detailed expression-related information. In this study, multi-modal facial images, such as facial gray scale, depth, and local binary pattern (LBP), are used to recognize six basic facial expressions, namely, happiness, sadness, anger, disgust, fear, and surprise. Facial depth images are used for robust face detection initially. The deep geometric feature is represented by point displacement and angle variation in facial landmark points with the help of depth information. The local appearance feature, which is obtained by concatenating LBP histograms of expression-prominent patches, is utilized to recognize those expression changes that are difficult to capture by only the geometric changes. Thereafter, an improved random forest classifier based on feature selection is used to recognize different facial expressions. Results of comparative evaluations in benchmarking datasets show that the proposed method outperforms several state-of-the-art FER approaches that are based on hand-crafted features. The capability of the proposed method is comparable to that of the popular convolutional neural-network-based FER approach but with fewer demands for training data and a high-performance hardware platform.     

Adaptive smoothing via contextual and local discontinuities

A novel adaptive smoothing approach is proposed for noise removal and feature preservation where two distinct measures are simultaneously adopted to detect discontinuities in an image. Inhomogeneity underlying an image is employed as a multiscale measure to detect contextual discontinuities for feature preservation and control of the smoothing speed, while local spatial gradient is used for detection of variable local discontinuities during smoothing. Unlike previous adaptive smoothing approaches, two discontinuity measures are combined in our algorithm for synergy in preserving nontrivial features, which leads to a constrained anisotropic diffusion process that inhomogeneity offers intrinsic constraints for selective smoothing. Thanks to the use of intrinsic constraints, our smoothing scheme is insensitive to termination times and the resultant images in a wide range of iterations are applicable to achieve nearly identical results for various early vision tasks. Our algorithm is formally analyzed and related to anisotropic diffusion. Comparative results indicate that our algorithm yields favorable smoothing results, and its application in extraction of hydrographic objects demonstrates its usefulness as a tool for early vision.     

Feature extraction method based on spectral dimensional edge preservation filtering for hyperspectral image classification

ABSTRACT

A large amount of spectral and spatial information contained in hyperspectral imagery has provided a great opportunity to effectively characterize and identify the surface materials of interest. Feature extraction plays a very important role for hyperspectral data classification, which can reduce noise from the original data and improve the separability of land classes. A novel feature extraction technique based on spectral dimensional edge preserving filter is proposed in this paper. A series of Gaussian filters are applied in the spatial domain of the hyperspectral image to produce the guidance image, then, the edge preserving filter which is guided by the guidance image is adopted and applied in the spectral domain of the hyperspectral data to get the feature. For the feature is produced by filtering in the spectral domain, the spectral curves of the feature are more continues, which avoids the spectral discontinuity problems result from the traditional two-dimensional spatial filter. The guidance image is obtained by filtering the original image in the spatial domain, so, the spatial and the spectral information are integrated together in the following spectral edge preserving filtering process. We carefully adjusted the parameters of the filter and applied it to different real hyperspectral remote sensing images, with the support vector machine, multinomial logistic regression, and random forest serving as the classifier, by comparing with other feature extraction methods presented in recent literature, the results indicate that the proposed methodology always has a great performance in different kinds of cases.     

基于2维偏最小二乘法的图像局部特征提取及其在面部表情识别中的应用

为了更有效地提取图像的局部特征,提出了一种基于2维偏最小二乘法(two-dimensional partial leastsquare,2DPLS)的图像局部特征提取方法,并将其应用于面部表情识别中。该方法首先利用局部二元模式(localbinary pattern,LBP)算子提取一幅图像中所有子块的纹理特征,并将其组合成局部纹理特征矩阵。由于样本图像被转化为局部纹理特征矩阵,因此可将传统PLS方法推广为2DPLS方法,用来提取其中的判别信息。2DPLS方法通过对类成员关系矩阵的构造进行相应的修改,使其适应样本的矩阵形式,并能体现出人脸局部信息重要性的差异。同时,对于类成员关系协方差矩阵的奇异性问题,也推导出了其广义逆的解析解。基于JAFFE人脸表情库的实验结果表明,该方法不但可以有效地提取图像局部特征,并能取得良好的表情识别效果。     

基于深度学习的人脸颜值评估系统

针对人脸颜值评估系统正确率和实时性低的问题,提出了一种基于深度学习的人脸颜值评估系统.该系统利用基于HOG特征的方法进行人脸检测,采用FaceNet预训练模型提取人脸特征值,提出基于Softmax分类层和ReLU回归层的双层决策模型,并结合人脸局部特征量化值进行人脸颜值评估.在SCUT-FBP5500数据集上进行实验,...     

基于Trace变换的人脸特征提取技术研究*

为了提高人脸特征的稳定性和区分度,提出了一种基于Trace变换的人脸特征提取算法。算法通过几种不同的泛函函数对预处理后的人脸图像进行组合作用,得到该图像的一个Trace特征向量,从而建立了一种新的人脸特征表达方式。基于ORL人脸数据库的实验结果表明,该算法所提出的人脸特征对同一个人不同表情、不同光照条件下的图像变化能够保持较好的稳定性,同时对不同人的人脸图像具有较高的区分能力,在人脸识别的实际应用中是一种可行的方法。     

基于小波矩的面部特征匹配定位方法

面部特征是实现面部表情分类与刻画面部表情强度的重要信息。提出了结合金字塔分解技术和小波矩的面部特征匹配定位方法。该方法通过小波矩实现图像信息的多尺度表征,而应用金字塔分解在金字塔图像各层之间传递信息并最终实现局部处理与全局处理之间的联系。实验结果表明,提出的方法可以在面部特征发生较大形变时依旧取得较好面部特征匹配定位结果。     

Improving forest type classification using the vegetation local difference index

A spatial feature extraction method was applied to increase the accuracy of land-cover classification of forest type information extraction. Traditional spatial feature extraction applications use high-resolution images. However, improving the classification accuracy is difficult when using medium-resolution images, such as a 30 m resolution Enhanced Thematic Mapper Plus (ETM+) image. In this study, we demonstrated a novel method that used the vegetation local difference index (VLDI) derived from the normalized difference vegetation index (NDVI), which were calculated based on the topographically corrected ETM+ image, to delineate spatial features. A simple maximum likelihood classifier and two different ways to use spatial information were introduced in this study as the frameworks to incorporate both spectral and spatial information for analysis. The results of the experiments, where Landsat ETM+ and digital elevation model (DEM) images, together with ground truth data acquired in the study area were used, show that combining the spatial information extracted from medium-resolution images and spectral information improved both classification accuracy and visual qualities. Moreover, the use of spatial information extracted through the proposed method greatly improved the classification performance of particular forest types, such as sparse woodlands.     

Pan-sharpening based on common saliency feature analysis and multiscale spatial information extraction for multiple remote sensing images

ABSTRACT

The requirements of spectral and spatial quality differ from region to region in remote sensing images. The employment of saliency in pan-sharpening methods is an effective approach to fulfil this kind of demands. Common saliency feature analysis, which considers the mutual information between multiple images, can ensure the consistency and accuracy when assigning saliency to regions in different images. Thus, we propose a pan-sharpening method based on common saliency feature analysis and multiscale spatial information extraction for multiple remote sensing images. Firstly, we extract spatial information by the guided filter and accurate intensity component estimation. Then, a common saliency feature analysis method based on global contrast calculation and intensity feature extraction is designed to obtain preliminary pixel-wise saliency estimation, which is subsequently integrated with text-featured based compensation to generate adaptive injection gains. The introduction of common saliency feature analysis guarantees that the same pan-sharpening strategy will be applied to regions with similar features in multiple images. Finally, the injection gains are used to implement the detail injection. Our proposal satisfies diverse needs of spatial and spectral information for different regions in the single image and guarantees that regions with similar features in different images are treated consistently in the process of pan-sharpening. Both visual and quantitative results demonstrate that our method has better performance in guaranteeing consistency in multiple images, improving spatial quality and preserving spectral fidelity.     

小波系数指导的全色锐化网络

针对现有全色锐化网络无法同时兼顾空间信息与光谱信息保留的问题,提出一种基于小波系数指导的由融合网络和指导网络组成的全色锐化网络。融合网络分别提取PAN和MS图像的多级特征,并在同一级别进行特征的选择和融合,融合后的特征分别用于指导后一级别特征的提取;指导网络用于学习HRMS与已知的输入图像的小波系数之间的映射关系,并利用学习到的映射对融合网络的输出提供额外的监督。实验结果表明,该方法能够在保留MS图像光谱信息的同时恢复尽可能多的空间信息。在模拟数据集和真实数据集上的对比实验也表明,该方法融合效果优于其他传统方法和深度学习方法,具有一定的实用价值。     

Kernel class-wise locality preserving projection

In the recent years, the pattern recognition community paid more attention to a new kind of feature extraction method, the manifold learning methods, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among them, locality preserving projection (LPP) is one of the most promising feature extraction techniques. However, when LPP is applied to the classification tasks, it shows some limitations, such as the ignorance of the label information. In this paper, we propose a novel local structure based feature extraction method, called class-wise locality preserving projection (CLPP). CLPP utilizes class information to guide the procedure of feature extraction. In CLPP, the local structure of the original data is constructed according to a certain kind of similarity between data points, which takes special consideration of both the local information and the class information. The kernelized (nonlinear) counterpart of this linear feature extractor is also established in the paper. Moreover, a kernel version of CLPP namely Kernel CLPP (KCLPP) is developed through applying the kernel trick to CLPP to increase its performance on nonlinear feature extraction. Experiments on ORL face database and YALE face database are performed to test and evaluate the proposed algorithm.     

注意力分层双线性池化残差网络的表情识别

由于人脸表情图像具有细微的类间差异信息和类内公有信息,提取具有判别性的局部特征成为关键问题,为此提出了一种注意力分层双线性池化残差网络。该模型采用有效的通道注意力机制显式地建模各通道的重要程度,为输出特征图分配不同的权重,按权重值大小定位显著区域。并添加了一个新的分层双线性池化层,集成多个跨层双线性特征来捕获层间部分特征关系,以端到端的深度学习方式在特征图中进行空间池化,使所提网络模型更适合精细的面部表情分类。分别在FER-2013和CK+数据集上对设计的网络进行实验,最高识别率分别为73.84%和98.79%,达到了具有竞争性的分类准确率,适用于细微的面部表情图像识别任务。     

3D reconstruction and face recognition using kernel-based ICA and neural networks

Kernel-based nonlinear characteristic extraction and classification algorithms are popular new research directions in machine learning. In this paper, we propose an improved photometric stereo scheme based on improved kernel-independent component analysis method to reconstruct 3D human faces. Next, we fetch the information of 3D faces for facial face recognition. For reconstruction, we obtain the correct normal vector’s sequence to form the surface, and use a method for enforcing integrability to reconstruct 3D objects. We test our algorithm on a number of real images captured from the Yale Face Database B, and use three kinds of methods to fetch characteristic values. Those methods are called contour-based, circle-based, and feature-based methods. Then, a three-layer, feed-forward neural network trained by a back-propagation algorithm is used to realize a classifier. All the experimental results were compared to those of the existing human face reconstruction and recognition approaches tested on the same images. The experimental results demonstrate that the proposed improved kernel independent component analysis (IKICA) method is efficient in reconstruction and face recognition applications.     

基于归一化方差的多分辨率图像融合方法

针对遥感多光谱图像空间分辨率较低的问题,论文提出了一种基于归一化方差的多分辨率图像融合方法。该方法首先对图像进行二维小波变换,然后根据高频小波系数的均值和方差来定义图像局部灰度相关矩,从而得到包含更多信息和有效特征的融合图像。试验结果证明融合图像在保留地物光谱信息和提高空间细节表现能力上都具有很好的效果。     

A wavelet-based dominant feature extraction algorithm for palm-print recognition

In this paper, a multi-resolution feature extraction algorithm for palm-print recognition is proposed based on two-dimensional discrete wavelet transform (2D-DWT), which efficiently exploits the local spatial variations in a palm-print image. The entire image is segmented into several small spatial modules and the effect of modularization in terms of the entropy content of the palm-print images has been investigated. A palm-print recognition scheme is developed based on extracting dominant wavelet features from each of these local modules. In the selection of the dominant features, a threshold criterion is proposed, which not only drastically reduces the feature dimension but also captures precisely the detail variations within the palm-print image. It is shown that, because of modularization of the palm-print image, the discriminating capabilities of the proposed features are enhanced, which results in a very high within-class compactness and between-class separability of the extracted features. The effect of using different mother wavelets for the purpose of feature extraction has been also investigated. A principal component analysis is performed to further reduce the feature dimension. From our extensive experimentations on different palm-print databases, it is found that the performance of the proposed method in terms of recognition accuracy and computational complexity is superior to that of some of the recent methods.