HEGM: A hierarchical elastic graph matching for hand gesture recognition

A hierarchical scheme for elastic graph matching applied to hand gesture recognition is proposed. The proposed algorithm exploits the relative discriminatory capabilities of visual features scattered on the images, assigning the corresponding weights to each feature. A boosting algorithm is used to determine the structure of the hierarchy of a given graph. The graph is expressed by annotating the nodes of interest over the target object to form a bunch graph. Three annotation techniques, manual, semi-automatic, and automatic annotation are used to determine the position of the nodes. The scheme and the annotation approaches are applied to explore the hand gesture recognition performance. A number of filter banks are applied to hand gestures images to investigate the effect of using different feature representation approaches. Experimental results show that the hierarchical elastic graph matching (HEGM) approach classified the hand posture with a gesture recognition accuracy of 99.85% when visual features were extracted by utilizing the Histogram of Oriented Gradient (HOG) representation. The results also provide the performance measures from the aspect of recognition accuracy to matching benefits, node positions correlation and consistency on three annotation approaches, showing that the semi-automatic annotation method is more efficient and accurate than the other two methods.     

Fast and robust face recognition via coding residual map learning based adaptive masking

Robust face recognition (FR) is an active topic in computer vision and biometrics, while face occlusion is one of the most challenging problems for robust FR. Recently, the representation (or coding) based FR schemes with sparse coding coefficients and coding residual have demonstrated good robustness to face occlusion; however, the high complexity of l₁-minimization makes them less useful in practical applications. In this paper we propose a novel coding residual map learning scheme for fast and robust FR based on the fact that occluded pixels usually have higher coding residuals when representing an occluded face image over the non-occluded training samples. A dictionary is learned to code the training samples, and the distribution of coding residuals is computed. Consequently, a residual map is learned to detect the occlusions by adaptive thresholding. Finally the face image is identified by masking the detected occlusion pixels from face representation. Experiments on benchmark databases show that the proposed scheme has much lower time complexity but comparable FR accuracy with other popular approaches.     

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.     

k-NN classification of handwritten characters via accelerated GAT correlation

This paper addresses the problem of reinforcing the ability of the k-NN classification of handwritten characters via distortion-tolerant template matching techniques with a limited quantity of data. We compare three kinds of matching techniques: the conventional simple correlation, the tangent distance, and the global affine transformation (GAT) correlation. Although the k-NN classification method is straightforward and powerful, it consumes a lot of time. Therefore, to reduce the computational cost of matching in k-NN classification, we propose accelerating the GAT correlation method by reformulating its computational model and adopting efficient lookup tables. Recognition experiments performed on the IPTP CDROM1B handwritten numerical database show that the matching techniques of the simple correlation, the tangent distance, and the accelerated GAT correlation achieved recognition rates of 97.07%, 97.50%, and 98.70%, respectively. The computation time ratios of the tangent distance and the accelerated GAT correlation to the simple correlation are 26.3 and 36.5 to 1.0, respectively.     

An economic–ecological model to evaluate impacts of nutrient abatement in the Baltic Sea

This paper presents a coupled economic–ecological model that integrates a catchment model with a marine model and incorporates economic data to analyse the long-term economic and ecological consequences of nutrient abatement in the Baltic Sea. The spatially explicit model describes dynamics of soil phosphorus in arable land, developments of nutrient concentrations and phytoplankton biomass in the sea basins, and inter-annual variation in nutrient loads and biophysical processes. The performance of the model is demonstrated by computing the least-cost solution to reach the good environmental state of the sea – as implied by the Baltic Sea Action Plan – within a time span of 40 years. The total cost of achieving this target is 1487 M€ annually. Spatially optimal allocation of load reductions differs from the load reduction targets of the Baltic Sea Action Plan, and focuses more on the control of phosphorus loads.     

A comprehensive approach to evaluating watershed models for predicting river flow regimes critical to downstream ecosystem services

Selection of strategies that help reduce riverine inputs requires numerical models that accurately quantify hydrologic processes. While numerous models exist, information on how to evaluate and select the most robust models is limited. Toward this end, we developed a comprehensive approach that helps evaluate watershed models in their ability to simulate flow regimes critical to downstream ecosystem services. We demonstrated the method using the Soil and Water Assessment Tool (SWAT), the Hydrological Simulation Program–FORTRAN (HSPF) model, and Distributed Large Basin Runoff Model (DLBRM) applied to the Maumee River Basin (USA). The approach helped in identifying that each model simulated flows within acceptable ranges. However, each was limited in its ability to simulate flows triggered by extreme weather events, owing to algorithms not being optimized for such events and mismatched physiographic watershed conditions. Ultimately, we found HSPF to best predict river flow, whereas SWAT offered the most flexibility for evaluating agricultural management practices.     

面向增量同生主题的维吾尔文爬虫的研究

针对传统的主题爬虫对网页信息缺乏在知识层面上的处理和理解的问题进行了研究,提出了一种面向增量同生主题的维吾尔文爬虫,通过建立一个增量主题词库优化传统的主题模型,来描述维吾尔文关键词的应用语境及场景,提高了计算网页相关度的准确率。用改进的IC主题敏感算法来预测子页面优先级,过滤无关的网页地址。依据上述方法编写爬虫系统,用构建的维吾尔文语料库进行实验,表明了基于此模型的爬虫具有更好的稳定性和准确度。     

文本分类中训练集相关数量指标的影响研究

针对训练集对分类性能的影响,从训练集的文本数、类别数以及特征项数这三项数量指标出发进行研究。使用多因素方差分析方法及多种语料库定量探讨该三项数量指标对分类性能的影响规律。结果发现特征项数对分类性能的影响在不同的文本数和类别数时是不同的,分类性能受训练集的这三项指标的交互影响,通过对训练集的这三项指标进行优化,提出了从分类算法、特征项选择法以外提高分类性能的途径。在真实数据上的实验结果表明,该方法可有效提高分类性能。     

一种快速的判别公共向量分类方法

在传统DCV的基础上,提出了一种改进的快速DCV分类方法。该方法与传统的DCV分类方法相比,在保证识别率相同的情况下具有较快的分类速率。传统的DCV分类方法通过计算特征向量之间的距离来进行分类,而所提快速DCV分类方法则通过标量计算完成分类。理论分析及复杂度计算表明,快速DCV分类方法的分类速率是传统DCV分类方法的2倍左右,在Yale、ORL和PIE 3种人脸数据库得到的对比仿真实验结果验证了该算法的有效性。