The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
A dynamic facial expression recognition method based on the auto-regressive (AR) models using combined features of both shape and texture features is proposed in this paper. The AR model is effective to model complicated facial motions. In this work, six AR models are first learned for six basic expressions based on the fusion of shape and texture features of the difference between the neutral image...
Nowadays, content-based image-retrieval techniques constitute powerful tools for archiving and mining of large remote sensing image databases. High spatial resolution images are complex and differ widely in their content, even in the same category. All images are more or less textured and structured. If the image to recognize is somewhat or very structured, a shape feature will be somewhat or very...
In this paper, a direct torque hysteresis controller (DTHC) driving a permanent magnet synchronous machine is discussed. A two-level, three-phase conventional inverter is used as means of power conversion. Advantages such as a low switching frequency as well as further opportunities of the DTHC are specified. The simulation results show a high degree of potential for the DTHC in future applications.
A drive train system (DTS) powered by an ideal voltage source and driving a permanent magnet synchronous motor (PMSM) is discussed in this paper. A two-level, three-phase conventional inverter with no harmonic filters on both AC and DC sides is used as means of power conditioning. This DTS is modelled as a double oscillator according to a simplified drive train in an electric vehicle. Commonly used...
In this paper, a novel method is proposed for the Traffic Sign Recognition (TSR) using the Principle Component Analysis (PCA) and the Multi-Layer Perceptrons (MLPs) network. In particular, the candidate signs are individually detected from two chroma components in the YCbCr space and then classified into three shape classes: circle, square, and triangle based on computing the rotated version correlations...
This paper investigates a control strategy for grid-connected wind energy conversion systems with doubly-fed induction generators, that employs a novel d-q hysteresis current regulator in the inner control loops. Although the current control is implemented in a rotating reference frame synchronous to the positive sequence space vector of the grid voltage, it can be used to generate negative sequence...
The authors propose a new parameter definition method and nail chip transformation method to superimpose nail chips onto dorsal-sided hand images with wrist rotation. Parameters for superimposing a nail chip on a fingernail are obtained using the center of gravity of the fingernail and the first and second principal component vector. A new transformation method was developed by including artificial...
This paper describes grasp point selection on an item of clothing randomly placed on a table. The input data for our proposed method is a range image captured from a fixed, 3D range camera. Hem elements are extracted from the data, and their relationships are characterized for both similarity measures and grasp point evaluation. Experiments using real images, targeting a piece of clothing, show the...
We present an approach for object class learning using a part-based shape categorization in RGB-augmented 3D point clouds captured from cluttered indoor scenes with a Kinect-like sensor. We propose an unsupervised hierarchical learning procedure which allows to symbolically classify shape parts by different specificity levels of detailedness of their surface-structural appearance. Further, a hierarchical...
Highly articulated robots have the potential to play a key role in minimally invasive surgeries by providing improved access to hard-to-reach anatomy. Estimating their shape inside the body and combining it with 3D preoperative scans of the anatomy enable the surgeon to visualize how the entire robot interacts with the internal organs. As the robot progresses inside the body, the position and orientation...
Learning to predict the effects of actions applied to pairs of objects is a difficult task that requires learning complex relations with sparse, incomplete and noisy information. Our Knowledge Propagation approach propagates affordance predictions by exploiting similarities among object properties, action parameters and resulting effects. The knowledge is propagated in a graph where a missing edge,...
We consider a coupled model of linear elasticity with Navier-Stokes equations. Two subdomains Ω1 and Ω2 are considered. In Ω1 there is a linear elasticity model. In Ω2 there is the fluid transport which is modeled by nonlinear Navier-Stokes equations. A propitiate interface conditions should be provided. We want to determine the shape and topological derivatives in Ω2.
WEB Services convert the applications into a WEB application, which can publish its function or message to the rest of world. The basic WEB Services platform is XML + HTTP The types of WEB Services have been explained. WEB Services platform elements are illustrated. The ScalabelVector Graphics (SVG) is explained in detail. The advantages of SVG are illustrated using practical examples, such as SVG-Ellipse,...
A pixel-by-pixel scanning that is usually performed by a single point-like sensor or probe is being widely used in the applications such as scanning probe microscopy techniques. Typically their scanning time is several seconds to minutes long due to a raster scanning that needs to be conducted for capturing every single point on the surface of the sample area. To improve the scanning efficiency, recent...
In content-based image retrieval, and for this critical issue of image feature fusion, paper proposes a new method to determine the weights for multi-feature fusion. In this paper, color histogram, color correlogram, gray level co-occurrence matrix, Tamura and Hu moments, this five kinds of feature extraction method was adopted. Firstly, use these five features conducted single feature retrieval on...
Facial landmarking is a fundamental step in machine-based face analysis. The majority of existing techniques handle such an issue based on 2D images; however, they suffer from illumination and pose variations that largely degrade landmarking performance. The emergence of 3D data provides us with an alternative to overcome these unsolved problems in the 2D domain. This paper proposes a novel approach...
An increasing number of MPI applications are being ported to take advantage of the compute power offered by GPUs. Data movement continues to be the major bottleneck on GPU clusters, more so when data is non-contiguous, which is common in scientific applications. The existing techniques of optimizing MPI data type processing, to improve performance of non-contiguous data movement, handle only certain...
To improve the robustness against variation in shooting angles, we previously proposed using an asymptotic expansion of the Gabor transform of ear images to compute the Gabor features of other poses and using these estimates in multiple linear discriminant analysis to enhance feature discriminability. Extending this study, the accuracies are compared with other standard methods that can be used to...
This paper reports on a feasibility study of contactless hand biometrics using an RGB-Depth (RGB-D) camera such as the Kinect v2 prototype. The RGB, depth, and near-infrared (near-IR) spectra provide access to information such as palm print, hand shape, finger joint location, and vein patterns. Extraction of the hand is first done using depth data. The frames with the best palm position are selected,...
Core region detection of handwritten cursive words is an important step towards their automatic recognition. Several preprocessing operations such as height normalization, slant estimation etc. Are often based on this core region. This is particularly useful for word recognition of major Indian scripts, which have large character sets. The main parts of majority of these characters belong to the core...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.