• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1106-1110
• /
• 2004

A human sign language is generally composed of both static and dynamic gestures. Each gesture is represented by a hand shape, its position, and hand movement (for a dynamic gesture). One of the problems found in automated sign language translation is on segmenting a hand movement that is part of a transitional movement from one hand gesture to another. This transitional gesture conveys no meaning, but serves as a connecting period between two consecutive gestures. Based on the observation that many dynamic gestures as appeared in Thai sign language dictionary are of quasi-periodic nature, a method was developed to differentiate between a (meaningful) dynamic gesture and a transitional movement. However, there are some meaningful dynamic gestures that are of non-periodic nature. Those gestures cannot be distinguished from a transitional movement by using the signal quasi-periodicity. This paper proposes a hybrid method using a combination of the periodicity-based gesture segmentation method with a HMM-based gesture classifier. The HMM classifier is used here to detect dynamic signs of non-periodic nature. Combined with the periodic-based gesture segmentation method, this hybrid scheme can be used to identify segments of a transitional movement. In addition, due to the use of quasi-periodic nature of many dynamic sign gestures, dimensionality of the HMM part of the proposed method is significantly reduced, resulting in computational saving as compared with a standard HMM-based method. Through experiment with real measurement, the proposed method's recognition performance is reported.

• Proceedings of the Korean Powder Metallurgy Institute Conference
• /
• 1997.10a
• /
• pp.7-7
• /
• 1997

During sintering of very porous green bodies, as obtained by compaction of hard powders - such as tungsten carbide or ceramics - or by injection moulding, important shrinkage occurs. Due to heterogeneous green density field, gravity effects, friction on the support, thermal gradients, etc., this shrinkage is often non-uniform, which' may induce significant shape changes. As the ratio of compact dimension to powder size is very high, the mechanics of continuum is relevant to model such phenomena. Thus numerical techniques, such as the finite element method can be used to simulate the sintering process and predict the final shape of the sintered part. Such type of simulation has much been developed in the last decade firstly for hot isostatic pressing and next for die compaction. Finite element modelling has been recently applied to free sintering. The simulation of sintering should be based on constitutive equations describing the thermo-mechanical behaviour of the material under any state of stress and any temperature which may arise within the sintering body. These equations can be drawn either from experimental data or from micromechanical models. The experiments usually consist in free sintering and sinter-forging tests. Indeed applying more complex loading conditions at high temperature under controlled atmosphere is delicate. Micromechanical models describe the constitutive behaviour of aggregates of spheres from the deformation of two-sphere contact either by viscous flow or grain boundary diffusion. Such models are not able to describe complex microstructure and mechanisms as observed in real materials but they can give some basic information on the formulation of constitutive equations. Practically both experimental and theoretical approaches can be coupled to identify the constitutive equations. Such procedure has been performed for modelling the sintering of compacts obtained by die pressing of a mixture of tungsten carbide and cobalt powders. The constitutive behaviour of this material during sintering has been described by a linear viscous constitutive model, whose functions have been fitted from results of free sintering and sinter-forging experiments. This model has next been introduced in ABAQUS finite element code to simulate the sintering of heterogeneous green compacts of various geometries at constant temperature. Examples of simulations are shown and compared with experiments.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.10
• /
• pp.99-106
• /
• 2002

This paper proposes an error compensation method that improves accuracy with geometry information of injection molding parts. Geometric information can give an improved accuracy in reverse engineering. Measuring data can not lead to get accurate geometric model, including errors of physical parts and measuring machines. Measuring data include errors which can be classified into two types. One is molding error in product, the other is measuring error. Measuring error includes optical error of laser scanner, deformation by probe forces of CMM and machine error. It is important to compensate these in reverse engineering. Least square method (LSM) provides the cloud data with a geometry compensation, improving accuracy of geometry. Also, the functional shape of a part and design concept can be reconstructed by error compensation using geometry information.

• Wind and Structures
• /
• v.6 no.6
• /
• pp.471-484
• /
• 2003

The rain-wind induced vibration of stays is a phenomenon discovered recently and not well explained yet. As it is influenced by a wide range of physical parameters (cable size and shape, wind speed, direction and turbulence, rain intensity, material repellency and roughness, cable weight, damping and pre-strain), this peculiar phenomenon is difficult to reproduce in laboratory controlled conditions. A successful wind tunnel experimental campaign, in which some basic physical quantities were measured, allowed an extensive analysis as to identify the parameters of the rain-wind induced excitation. The unsteady pressure field and water thickness around a cable model were measured under rainy-excited conditions. The knowledge of those parameters provided helpful information about the air-flow around the cable and allowed to clarify the physical phenomenon which produces the excitation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.587-591
• /
• 1996

Usually triangular patches are used to transfer geometric shape in Rpaid Prototyping CAM system. STL, a list of triangles, is de facto in RP industry. Because STL has no topology data, it can cause errornous results. So, STL should be verified before using. After adding support structures to anchor the part to the platform and to prevent sagging or distortion, slicing and layer by layer manufacturing process are done. But triangular patch is surface model and cannot provide dufficient information on geometry in the above processes. So, geometric modeling is necessary in verifying STL, adding support structures, and slicing. It is natural that triangle based modeling is the best when traingular patches are used as input. Considering support structures, solid and faces coexist in RP process. Therefore non-manifold modeler is required. In this study, triangle based non-manifold geometric modeling is proposed for RP system consitent with STL input.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.05a
• /
• pp.816-819
• /
• 2000

Recently the styrofoam has been used fur material of press die pattern. The object of this research is to develope an automated laser system for manufacture of press die pattern which depends chiefly on handwork during its process. After converting 3-D CAD model into cross-sectional shape information, the unnecessary part of the section is vapored away by laser. The depth and width of cut are mainly under the control of laser power and beam feed rate. The optimum manufacturing conditions are obtained by preliminary experiments. It is necessary fur precise styrofoam pattern manufacturing to develope laser system which has sufficient motion accuracy and program or beam path generation and automatic control of this system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.182-182
• /
• 2000

This paper proposes a self tuning fuzzy inference method by the genetic algorithm in the fuzzy-sliding mode control for a robot. Using this method, the number of inference rules and the shape of membership functions are optimized without an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. And, it is guaranteed that the selected solution become the global optimal solution by optimizing the Akaike's information criterion. The trajectory trucking experiment of the polishing robot system shows that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the proposed fuzzy-sliding model controller provides reliable tracking performance during the polishing process.

• The KIPS Transactions:PartD
• /
• v.11D no.1
• /
• pp.39-50
• /
• 2004

GML proposed to offer interoperability of geography information is specifying various dynamic object schema for application in the wireless environment. These GML dynamic object schema supports the expression of moving objects that the position and shape change consecutively over time, so practical use of GML is increased in location-based service that provides various application services based on location information of moving objects. In particular, the conventional query languages about GML have been studied with priority given to the integration of geographic information, the support of spatial operations, and etc. However, it lacks the support for moving objects queries. Therefore, in this paper, we propose the moving objects query language that supports moving objects queries for GML documents by extension of XQuery that is standard in query language. Also, data model, algebra operation and various moving objects operators for the proposed query language are designed, and we apply the proposed query language to tornado government organization system to show that the proposed query language can be used effectively in various location-based service.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.900-911
• /
• 2015

In this paper, 3D face recognition model is designed by using Polynomial based RBFNN(Radial Basis Function Neural Network) and PNN(Polynomial Neural Network). Also recognition rate is performed by this model. In existing 2D face recognition model, the degradation of recognition rate may occur in external environments such as face features using a brightness of the video. So 3D face recognition is performed by using 3D scanner for improving disadvantage of 2D face recognition. In the preprocessing part, obtained 3D face images for the variation of each pose are changed as front image by using pose compensation. The depth data of face image shape is extracted by using Multiple point signature. And whole area of face depth information is obtained by using the tip of a nose as a reference point. Parameter optimization is carried out with the aid of both ABC(Artificial Bee Colony) and PSO(Particle Swarm Optimization) for effective training and recognition. Experimental data for face recognition is built up by the face images of students and researchers in IC&CI Lab of Suwon University. By using the images of 3D face extracted in IC&CI Lab. the performance of 3D face recognition is evaluated and compared according to two types of models as well as point signature method based on two kinds of depth data information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.