Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.     

基于多尺度双线性卷积神经网络的多角度下车型精细识别

针对多角度下车辆出现一定的尺度变化和形变导致很难被准确识别的问题，提出基于多尺度双线性卷积神经网络（MS-B-CNN）的车型精细识别模型。首先，对双线性卷积神经网络（B-CNN）算法进行改进，提出MS-B-CNN算法对不同卷积层的特征进行了多尺度融合，以提高特征表达能力；此外，还采用基于中心损失函数与Softmax损失函数联合学习的策略，在Softmax损失函数基础上分别对训练集每个类别在特征空间维护一个类中心，在训练过程中新增加样本时，网络会约束样本的分类中心距离，以提高多角度情况下的车型识别的能力。实验结果显示，该车型识别模型在CompCars数据集上的正确率达到了93.63%，验证了模型在多角度情况下的准确性和鲁棒性。     

Low cycle fatigue behavior of a eutectic 80Au/20Sn solder alloy

The eutectic 80Au/20Sn solder alloy is widely used in high power electronics and optoelectronics packaging. In this study, low cycle fatigue behavior of a eutectic 80Au/20Sn solder alloy is reported. The 80Au/20Sn solder shows a quasi-static fracture characteristic at high strain rates, and then gradually transforms from a transgranular fracture (dominated by fatigue damage) to intergranular fracture (dominated by creep damage) at low strain rates with increasing temperature. Coffin-Manson and Morrow models are proposed to evaluate the low cycle fatigue behavior of the 80Au/20Sn solder. Besides, the 80Au/20Sn solder has enhanced fatigue resistance compared to the 63Sn/37Pb solder.     

粉土界面恒刚度循环剪切试验研究

竖向循环荷载作用下桩土界面的作用机理是研究桩土摩擦疲劳的关键。针对循环荷载作用下桩-粉土界面的剪切性能,使用改进的剪切试验装置在恒刚度条件下进行循环剪切试验,研究循环次数、累积位移和法向刚度对其摩擦疲劳性能、循环后单调剪切性能的影响。试验结果表明,粉土在循环剪切过程中,法向应力和剪应力在初始10个循环内随循环数增加快速衰减,随着循环进行,逐渐趋于稳定;单次循环内在剪切位移方向变化时,土体呈现表现出剪缩-剪胀-剪缩交替现象,总体变形呈现剪缩的趋势;循环荷载作用下,粉土界面的法向应力和剪应力随法向刚度增大衰减速率增大,达到稳定的累积循环位移越小;粉土循环后的单调剪切、法向应力恢复的单调剪切的剪应力比小于首次单调剪切试验值,且法向应力恢复的循环后剪切试验的剪胀程度较小,表明循环剪切过程中界面处粉土颗粒棱角破碎,颗粒变得光滑。在对试验数据分析的基础上,提出了与累积位移、法向刚度和初始应力相关的无量纲累积位移,建立了法向应力和界面摩擦角随累积位移的衰减方程。     

视频侦查中人像智能分析应用及算法优化

人像智能分析指的是对视频或录像中的人像进行结构化和可视化分析,对目标人物进行性别、年龄、发型等特征的智能识别,这项技术在视频侦查中有极高的应用价值。人像识别早期的算法是通过人工提取特征,通过学习低级视觉特征来针对不同属性进行分类学习,这种基于传统方法的模型表现常常不尽如人意。在计算机视觉领域,通过海量图像数据学习的神经网络比传统方法有更丰富的信息量和特征可以被提取。文章尝试通过深度学习技术训练神经网络模型对行人进行检测和识别,对于衣着不同的行人进行智能识别,具有更好的鲁棒性,提升了视频人像识别的准确率,拓展了人工智能技术在身份识别领域的应用。     

Road Extraction from High Resolution Remote Sensing Image based on Shape Analysis with Gestalt Theory

Simulating the psychological experience of human vision，a road extraction model based on the format tower is proposed to extract the road in the high resolution remote sensing image from the perspective of morphology.Firstly，based on the spectral and texture information，the suspected road targets are extracted by using segmentation technology.Then these targets are classified according to their reliability and extract the road targets for each category.Finally，three types of identified road information are verified and merged，and the continuous smooth road extraction results are obtained.Experiments on real high resolution images show that the results are consistent with the visual perception of the human eye，and the overall classification accuracy is higher，indicating that the algorithm is effective and feasible and has good use value.     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.     

Word length and lexical activation: Longer is better.

Many models of spoken word recognition posit the existence of lexical and sublexical representations, with excitatory and inhibitory mechanisms used to affect the activation levels of such representations. Bottom-up evidence provides excitatory input, and inhibition from phonetically similar representations leads to lexical competition. In such a system, long words should produce stronger lexical activation than short words, for 2 reasons: Long words provide more bottom-up evidence than short words, and short words are subject to greater inhibition due to the existence of more similar words. Four experiments provide evidence for this view. In addition, reaction-time-based partitioning of the data shows that long words generate greater activation that is available both earlier and for a longer time than is the case for short words. As a result, lexical influences on phoneme identification are extremely robust for long words but are quite fragile and condition-dependent for short words. Models of word recognition must consider words of all lengths to capture the true dynamics of lexical activation. (PsycINFO Database Record (c) 2010 APA, all rights reserved)