Learning shape and texture progression for young child face aging

Face aging (FA) for young faces refers to rendering the aging faces at target age for an individual, generally under 20s, which is an important topic of facial age analysis. Unlike traditional FA for adults, it is challenging to age children with one deep learning-based FA network, since there are deformations of facial shapes and variations of textural details. To alleviate the deficiency, a unified FA framework for young faces is proposed, which consists of two decoupled networks to apply aging image translation. It explicitly models transformations of geometry and appearance using two components: GD-GAN, which simulates the Geometric Deformation using Generative Adversarial Network; TV-GAN, which simulates the Textural Variations guided by the age-related saliency map. Extensive experiments demonstrate that our method has advantages over the state-of-the-art methods in terms of synthesizing visually plausible images for young faces, as well as preserving the personalized features.     

Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.     

An improved method to visualize two regions of interest synchronously in microfluidics

Multiphase flow in mini/micro channels has been widely studied for its potential in many industrial applications. The normal experimental method cannot capture two separate regions of interest (ROI) with a long distance synchronously for the limited field of views. In order to solve this problem, an improved experimental method is proposed and validated with experimental results. Prism groups are applied to reflect the two regions of interest to a very small shooting zone. Though the actual distance between the two regions is far, the reflected regions adjoin with each other on the top surface of the prisms. Thus, the two regions can be captured synchronously with one image using a small field of view. Two types of configurations with 4 prisms and 6 prisms are compared using gas-liquid and liquid-liquid experimental results. The resolution of the two configurations is similar, while the maximum amplification ratio is smaller for the latter configuration with 6 prisms. The first type is more suitable for experimental studies focusing on the formation and breakup of dispersed phases near two branches. The second configuration is recommended for cases focusing on the formation and fully developed hydraulic characteristics of the dispersed phase. The proposed method is very efficient for studies of hydraulic, heat and mass transfer characteristics of multiphase flows in mini/micro channels.     

Prism coupling method to evaluate the light extraction efficiency of outcoupling substrates

One of the key challenges in organic light-emitting diodes (OLEDs) for lighting applications is efficient light extraction from the planar, multi-layered OLED stack. Several different light extraction approaches are being explored currently by researchers, however characterizing light extraction films after fabricating OLEDs is not a viable approach when the outcoupling films have large surface roughness and is time consuming as well. Here we apply prism coupling method (PCM), a simple and elegant tool, to characterize outcoupling films. We show the effectiveness of PCM in estimating light extraction efficiency of outcoupling films. PCM can expedite selection and optimization of various light extraction approaches without the need to build OLEDs. The experimental results are corroborated by the optical simulations done using ray tracing method taking into account Mie scattering from wavelength sized spherical inclusions in an outcoupling film.     

基于深度概率图模型的鲁棒人脸画像合成

针对基于数据驱动的人脸画像合成算法像素特征缺乏对光照变化和复杂背景的鲁棒性,常合成低质量的画像的问题,文中提出基于深度概率图模型的鲁棒人脸画像合成算法.采用预处理方法调整测试照片的光照亮度和人脸姿态,使之与训练照片一致.采用深度特征代替像素特征进行近邻匹配,采用深度概率图模型对画像重建权重和深度特征权重联合建模,得到合成画像的最佳重构表示.为了提高画像合成速度,提出快速近邻搜索方法.实验验证文中算法的鲁棒性和快速性.     

Basic human–robot interaction system running on an embedded platform

Robotics will be a dominant area in society throughout future generations. Its presence is currently increasing in most daily life settings, with devices and mechanisms that facilitate the accomplishment of diverse tasks, as well as in work scenarios, where machines perform more and more jobs. This increase in the presence of autonomous robotic systems in society is due to their great efficiency and security compared to human capacity, which is thanks mainly to the enormous precision of their sensor and actuator systems. Among these, vision sensors are of the utmost importance. Humans and many animals naturally enjoy powerful perception systems, but, in robotics, this constitutes a constant line of research. In addition to having a high capacity for reasoning and decision-making, these robots incorporate important advances in their perceptual systems, allowing them to interact effectively in the working environments of this new industrial revolution. Drawing on the most basic interaction between humans, looking at the face, an innovative system is presented in this paper, which was developed for an autonomous and DIY robot. This system is composed of three modules. First, the face detection component, which detects human faces in the current image. Second, the scene representation algorithm, which offers a wider field of view than that of the single camera used, mounted on a servo-pan unit. Third, the active memory component, which was designed and implemented according to two competing dynamics: life and salience. The algorithm intelligently moves the servo-pan unit with the aim of finding new faces, follow existing ones and forgetting those that no longer appear on the scene. The system was developed and validated using a low-cost platform based on a Raspberry Pi3 board.     

Emotion recognition at the edge with AI specific low power architectures

Nowadays Deep Learning is applied in almost every research field and helps getting amazing results in a great number of challenging tasks. The main problem is that this kind of learning and consequently Neural Networks that can be defined deep, are resource intensive. They need specialized hardware to perform computation in a reasonable time. Many tasks are mandatory to be as much real-time as possible . It is needed to optimize many components such as code, algorithms, numeric accuracy and hardware, to make them “efficient and usable”. All these optimizations can help us to produce incredibly accurate and fast learning models. The paper reports a study in this direction for the challenging face detection and emotion recognition tasks.     

Prism Signal Processing of Coriolis meter data for gasoline fuel injection monitoring

Prism Signal Processing is a new recursive FIR technique offering rapid filter design and calculation. It has previously been applied to Coriolis mass flow metering to generate fast (48 kHz) flow measurement updates, facilitating for the first time the direct mass flow measurement of individual fuel pulses injected into a laboratory diesel fuel injection test bench. In this paper we describe an augmented sensor signal filtering scheme which enables rapid tracking of the desired mode of flow tube vibration while notching out undesired modes. The new scheme is applied to a gasoline injection test bench where the vibrational interference is greater than for the previously described diesel system due to increased hydraulic shock. The paper presents experimental findings which illustrate the further challenges to be overcome in order to achieve the goal of traceable direct mass flow measurement of individual fuel injection pulses. For example, when a fuel pulse is shorter than the resonant period of the flow tube, the observed phase difference appears to show dependence on the instantaneous phase of the flow tube vibration.     

Effect of seepage force on tunnel face stability reinforced with multi-step pipe grouting

Tunneling in difficult geological conditions is often inevitable especially in urban areas. Ground improvement and reinforcement techniques are required to guarantee safe tunnel excavations and/or to prevent damage to adjacent structures. The steel pipe-reinforced multi-step grouting method has been recently applied to tunnel sites as an auxiliary technique in Korea for impermeabilization in underwater tunnels as well as for reinforcement. However, this technique has been usually employed empirically without much understanding with regard to its effect on the tunnel safety. In this study, the face stability with steel pipe-reinforced multi-step grouting in underwater tunnels was evaluated by simultaneously considering two factors: one is the effective stress acting on the tunnel face calculated by limit theorem and limit equilibrium method; the other is the seepage force obtained by means of numerical analysis. This study revealed that the influence of the steel pipe-reinforced multi-step grouting on the support pressure required for the stability of the tunnel face in dry condition is not significant while there is relatively a significant reduction in seepage forces by adopting the technique in the underwater tunnel. The effect of permeability anisotropy on the seepage force acting on the tunnel face was also assessed by conducting a coupled analysis.     

膜分离技术在加氢裂化装置低分气提浓制氢气中的应用

为提浓回收利用低分气中的氢气,中国石油长庆石化公司在加氢裂化装置上设置了Prism膜分离单元。标定结果表明,自2010年建成投产以来,Prism膜分离单元已连续稳定运行了4 a多;膜系统的实际处理能力为4 600~5 500 m3/h,比设计指标低1 500~2 400 m3/h;虽然产品氢(渗透气)中H2的体积分数只有约92%(比设计指标低约6个百分点),但完全能满足加氢裂化装置的用氢要求;氢回收率大于设计指标要求的88%。