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。     

Synergistic flame retardant effects of activated carbon and molybdenum oxide in poly(vinyl chloride)

The synergistic effects of activated carbon (AC) and molybdenum oxide (MoO₃) in improving the flame retardancy of poly(vinyl chloride) (PVC) were investigated. The effects of AC, MoO₃ and their mixture with a mass ratio of 1:1 on the flame retardancy and smoke suppression properties of PVC were studied using the limiting oxygen index and cone calorimeter tests. It was found that the flame retardancy of the relatively cheaper AC was slightly weaker than that of MoO₃. In addition, the incorporation of AC and MoO₃ greatly reduced the total heat release and improved smoke suppressant property of PVC composites. When the total content of AC and MoO₃ was 10 phr, PVC/AC/MoO₃ had the lowest peak heat release rate and peak smoke production rate values of 173.80 kW m^?2 and 0.1472 m² s^?1, which represented reductions of 47.3 and 59.9%, respectively, compared with those of PVC. Furthermore, thermogravimetric analysis and gel content tests were used to analyze the flame retardant mechanism of AC and MoO₃, with results showing that AC could promote early crosslinking in PVC. Char residue left after heating at 500 °C was analyzed using scanning electron microscopy and Raman spectroscopy, and the results showed that MoO₃ produced the most compact char, with the smallest and most organized carbonaceous microstructures. © 2017 Society of Chemical Industry     

Experimental investigation of unconfined spherical and cylindrical flame propagation in hydrogen-air mixtures

This paper presents results of experimental investigations on spherical and cylindrical flame propagation in pre-mixed H₂/air-mixtures in unconfined and semi-confined geometries. The experiments were performed in a facility consisting of two transparent solid walls with 1 m² area and four weak side walls made from thin plastic film. The gap size between the solid walls was varied stepwise from thin layer geometry (6 mm) to cube geometry (1 m). A wide range of H₂/air-mixtures with volumetric hydrogen concentrations from 10% to 45% H₂ was ignited between the transparent solid walls. The propagating flame front and its structure was observed with a large scale high speed shadow system. Results of spherical and cylindrical flame propagation up to a radius of 0.5 m were analyzed. The presented spherical burning velocity model is used to discuss the self-acceleration phenomena in unconfined and unobstructed pre-mixed H₂/air flames.     

A facile method for preparation of PGS@ZB‐N and gas‐sol alternating synergistic effect for fire resistance of EVA

Through the simple precipitation of palygorskite (PGS) by zinc borate (ZB) (to make PGS@ZB) and the decoration of PGS@ZB by dodecylamine (N), a novel organic‐inorganic@inorganic hybrid flame retardant of PGS@ZB‐N was prepared and was incorporated with ethylene vinyl acetate copolymer (EVA) to improve its flame retardance. The structure and morphology of PGS@ZB‐N were characterized by Fourier transform infrared (FTIR) spectroscopy, X‐ray diffraction (XRD), and scanning electron microscopy (SEM), and it was confirmed that the PGS@ZB‐N hybrid had been successfully prepared. The flame retardancy and burning behavior of EVA/PGS@ZB‐N/EG (EG = expandable graphite) composite were studied through thermogravimetric analysis (TGA), limiting oxygen index (LOI), UL‐94 (by the vertical burning test), and cone calorimeter test (CCT) characterizations. The prepared EVA/PGS@ZB‐N/EG composite obtained an LOI value of 41.2% with the addition of 30 wt% PGS@ZB‐N/EG. It was found that EVA/PGS@ZB‐N/EG was protected through a gas phase and condensed phase alternating synergistic effect mechanism.     

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.