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.     

Ensemble relation network with multi-level measure

Fine-grained few-shot learning is a difficult task in image classification. The reason is that the discriminative features of fine-grained images are often located in local areas of the image, while most of the existing few-shotlearning image classification methods only use top-level features and adopt a single measure. In that way, the localfeatures of the sample cannot be learned well. In response to this problem, ensemble relation network with multi-level measure (ERN-MM) is proposed in this paper. It adds the relation modules in the shallow feature space tocompare the similarity between the samples in the local features, and finally integrates the similarity scores from thefeature spaces to assign the label of the query samples. So the proposed method ERN-MM can use local details andglobal information of different grains. Experimental results on different fine-grained datasets show that the proposedmethod achieves good classification performance and also proves its rationality.     

An IoT-Aware System for Managing Patients’ Waiting Time Using Bluetooth Low-Energy Technology

It is a common observation that whenever patients arrives at the front desk of a hospital, outpatient clinic, or other health-associated centers, they have to first queue up in a line and wait to fill in their registration form to get admitted. The long waiting time without any status updates is the most common complaint, concerning health officials. In this paper, UrNext, a location-aware mobile-based solution using Bluetooth low-energy (BLE) technology is presented to solve the problem. Recently, a technology-oriented method, the Internet of Things (IoT), has been gaining popularity in helping to solve some of the healthcare sector’s problems. The implementation of this solution could be illustrated through a simple example of when a patient arrives at a clinic for a consultation. Instead of having to wait in long lines, that patient will be greeted automatically, receive a push notification of an admittance along with an estimated waiting time for a consultation session. This will not only provide the patients with a sense of freedom but would also reduce the uncertainty levels that are generally observed, thus saving both time and money. This work aims to improve the clinics’ quality of services, organize queues and minimize waiting times, leading to patients’ comfort while reducing the burden on nurses and receptionists. The results demonstrate that the presented system is successful in its performance and helps achieves a pleasant and conducive clinic visitation process with higher productivity.     

High-roubustness keystroke recognition method based on acoustic spatial gradient

For the fluctuation of CFCC caused by environmental noise is the main reason for the low accuracy of keystroke detection,the spatial characteristics of adjacent between CFCC were studied,and the spatial gradient structure of CFCC based on points was established.On this basis,the effect of CFCC spatial gradient on keystroke content recognition and the selection of precise neighborhood points were studied on training and testing.Finally,a high-robustness keystroke recognition algorithm based on acoustic signals was constructed.Extensive experiments in different environments demonstrate that the proposed CFCC spatial gradient sound feature achieves great performance and the recognition accuracy is 96.15%.     

Local jet pattern: a robust descriptor for texture classification

Multimedia Tools and Applications - Methods based on locally encoded image features have recently become popular for texture classification tasks, particularly in the existence of large intra-class...     

Ultra-wideband balun and power divider using coplanar waveguide to microstrip transitions

An ultra-wideband transition from coplanar waveguide (CPW) to a pair of microstrip lines is presented in this letter. It is shown that the proposed transition can be used to devise an ultra-wideband T-junction power divider with equally split in-phase output signals. More importantly, it is demonstrated that the out-of-phase magnetic currents in the slots of the CPW can be utilized to achieve an out-of-phase power divider or a balun. Both the T-junction power divider and the balun benefit from compact size and good performance over an ultra wide frequency band from 3 to 16 GHz. Prototypes of both proposed devices are fabricated and measured to provide an experimental verification on the concept and numerically predicted features.     

Product appearance detection based on visual keywords matching

The product appearance detection device based on the USB (Universal Serial Bus) camera is studied. The USB camera is used as the front device of the image acquisition and the host computer is a PC for the detection system. Aiming at low resolution of USB camera, the super-resolution image reconstruction method based on sparse representation is used to overcome the low resolution for the low-cost imaging sensor and improve the image resolution. A method of product appearance detection based on visual keywords is proposed. Visual keywords are used to describe characteristics of defects. Visual keyword extraction is performed on sample images and test images, and visual keywords are used for matching. Identify defective products by setting different thresholds. Experiments show that the proposed system has better detection results and offers good robustness to the angle and illumination of the image from the product appearance. In this paper, the theory of visual keywords is applied to product appearance detection for the first time, which provides a reference for further research.     

采用信道估计法的基站VSWR实时检测

为解决无线基站宽带工作频带内电压驻波比(Voltage Standing Wave Ratio,VSWR)的实时测量，提出了一种采用信道估计法的测量方案。该方案实现简单，在基带处理单元高速率位置发送数据，依次抓取射频通道反馈和反射数据，分别求取信道响应序列，结合工厂装备测试数据，计算驻波反射系数和反射点位置。发送信号采用宽带正交频分复用信号，能检测到工作频段内任何频点处的驻波异常。有用信号前加循环前缀，并引入峰值抵消核，能正确检测到多个反射点驻波。仿真结果表明，该方案驻波测量精度和单回波点位置精度达到预期，多回波点测量能抓准外部主要故障点，在基站VSWR实时测量中具有良好的应用前景。     

Novel design to improve band to band tunneling and gate induced drain leakages (GIDL) in cylindrical gate all around (GAA) MOSFET

Microsystem Technologies - In this paper a cylindrical Dual Metal (DM) Dielectric Engineered (DE) Gate All Around (GAA) MOSFET has been proposed to resolve a big issue of Gate Inducted Drain...