• ETRI Journal
• /
• v.32 no.5
• /
• pp.784-794
• /
• 2010

Automatic facial expression recognition has many potential applications in different areas of human computer interaction. However, they are not yet fully realized due to the lack of an effective facial feature descriptor. In this paper, we present a new appearance-based feature descriptor, the local directional pattern (LDP), to represent facial geometry and analyze its performance in expression recognition. An LDP feature is obtained by computing the edge response values in 8 directions at each pixel and encoding them into an 8 bit binary number using the relative strength of these edge responses. The LDP descriptor, a distribution of LDP codes within an image or image patch, is used to describe each expression image. The effectiveness of dimensionality reduction techniques, such as principal component analysis and AdaBoost, is also analyzed in terms of computational cost saving and classification accuracy. Two well-known machine learning methods, template matching and support vector machine, are used for classification using the Cohn-Kanade and Japanese female facial expression databases. Better classification accuracy shows the superiority of LDP descriptor against other appearance-based feature descriptors.

• Korean Journal of Remote Sensing
• /
• v.22 no.3
• /
• pp.221-228
• /
• 2006

In this study, an integrated 3D modeling and rendering system dealing with 3D urban landscape features such as terrain, building, road and user-defined geometric ones was designed and implemented using $OPENGL\;{|}\;ES$ (Embedded System) API for mobile devices of PDA. In this system, the authoring functions are composed of several parts handling urban landscape features: vertex-based geometry modeling, editing and manipulating 3D landscape objects, generating geometrically complex type features with attributes for 3D objects, and texture mapping of complex types using image library. It is a kind of feature-based system, linked with 3D geo-based spatial feature attributes. As for the rendering process, some functions are provided: optimizing of integrated multiple 3D landscape objects, and rendering of texture-mapped 3D landscape objects. By the active-synchronized process among desktop system, OPENGL-based 3D visualization system, and mobile system, it is possible to transfer and disseminate 3D feature models through both systems. In this mobile 3D urban processing system, the main graphical user interface and core components is implemented under EVC 4.0 MFC and tested at PDA running on windows mobile and Pocket Pc. It is expected that the mobile 3D geo-spatial information systems supporting registration, modeling, and rendering functions can be effectively utilized for real time 3D urban planning and 3D mobile mapping on the site.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.383-388
• /
• 2005

Depth recovery in robot vision is an essential problem to infer the three dimensional geometry of scenes from a sequence of the two dimensional images. In the past, many studies have been proposed for the depth estimation such as stereopsis, motion parallax and blurring phenomena. Among cues for depth estimation, depth from lens translation is based on shape from motion by using feature points. This approach is derived from the correspondence of feature points detected in images and performs the depth estimation that uses information on the motion of feature points. The approaches using motion vectors suffer from the occlusion or missing part problem, and the image blur is ignored in the feature point detection. This paper presents a novel approach to the defocus technique based depth from lens translation using sequential SVD factorization. Solving such the problems requires modeling of mutual relationship between the light and optics until reaching the image plane. For this mutuality, we first discuss the optical properties of a camera system, because the image blur varies according to camera parameter settings. The camera system accounts for the camera model integrating a thin lens based camera model to explain the light and optical properties and a perspective projection camera model to explain the depth from lens translation. Then, depth from lens translation is proposed to use the feature points detected in edges of the image blur. The feature points contain the depth information derived from an amount of blur of width. The shape and motion can be estimated from the motion of feature points. This method uses the sequential SVD factorization to represent the orthogonal matrices that are singular value decomposition. Some experiments have been performed with a sequence of real and synthetic images comparing the presented method with the depth from lens translation. Experimental results have demonstrated the validity and shown the applicability of the proposed method to the depth estimation.

• School Mathematics
• /
• v.14 no.3
• /
• pp.331-355
• /
• 2012

All the method used in teaching the ellipse was to have students draw the points which have the same sum of distances from the two points so that they can confirm the shapes of the ellipse before showing them the definition of ellipse. In this process, students would not get an opportunity to think or make the definition of ellipse for themselves. This deductive way can hinder students from having clear understanding of why such definition was made. This paper introduces a method of defining the ellipse based on the similarity between a circle and an ellipse, leading into the equation. This method is possible by introducing Analytic Geometry taught in current school mathematics and Transformation Geometry. By doing so, this paper will discuss a fundamental understanding about the ellipse and the feature of the ellipse expandable by intuition. Furthermore this paper will also show various advantages which can be given by defining the ellipse in Transformation Geometry.

• ETRI Journal
• /
• v.42 no.3
• /
• pp.420-432
• /
• 2020

The reconstruction of archaeological fragments in 3D geometry is an important problem in pattern recognition and computer vision. Therefore, we implement an algorithm with the help of a 3D model to perform reconstruction from the real datasets using the slope features. This approach avoids the problem of gaps created through the loss of parts of the artifacts. Therefore, the aim of this study is to assemble the object without previous knowledge about the form of the original object. We utilize the edges of the fragments as an important feature in reconstructing the objects and apply multiple procedures to extract the 3D edge points. In order to assign the positions of the unknown parts that are supposed to match, the contour must be divided into four parts. Furthermore, to classify the fragments under reconstruction, we apply a backpropagation neural network. We test the algorithm on several models of ceramic fragments. It achieves highly accurate results in reconstructing the objects into their original forms, in spite of absent pieces.

• Korean Journal of Computational Design and Engineering
• /
• v.5 no.4
• /
• pp.312-318
• /
• 2000

In this study, an exclusive CAD/CAM system is developed for enhancing the effectiveness and productivity of CNC universal cylindrical grinding machines on which the external/facing/internal grinding cycles and the wheel dressing cycles are integratively carried out. The CAD/CAM system can manage the various processes such as geometry design, NC code generation, NC code verification, DNC operation, and so on. Especially, the feature-based modeling concept is introduced to improve the geometry design efficiency. And the NC code verification is realized by virtual manufacturing technique based on the real-time analysis of NC codes and the boolean operation between workpiece and wheel.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.98-103
• /
• 2000

The cut-off is a unique feature associated with duct acoustics due to the presence of duct walls. Duct geometry effect on sound radiation is another issue of duct acoustics. The radiation of duct internal noise to ambient from duct open ends with various geometries is studied via numerical methods. The linearized Euler's equations in generalized curvilinear coordinates are solved by the DRP finite difference scheme. A number of accurate boundary conditions are used at boundaries for the computational domain to minimize the non-physical reflections. The far field sound pressure levels are computed by the Kirchhoff integration method. We investigate the cut off phenomana and duct geometry effects on sound radiation with numerical results.

• The Journal of the Korea Contents Association
• /
• v.5 no.2
• /
• pp.199-205
• /
• 2005

In this paper, we present a face detection algorithm which uses the features of color and Geometry of faces and hairs appeared in images. after candidate area detection using color features, background areas are removed by the deviation of luminance in each of candidate areas. And then, final face area is detected using feature of geometry between face and hair. Performance of the presented algorithm is evaluated by detection rate test. The test result showed high detection rate.

• International Journal of Contents
• /
• v.5 no.4
• /
• pp.55-61
• /
• 2009

In this paper, we propose a hierarchical method for segmenting a given 3D mesh, which hierarchically clusters sharp vertices of the mesh using the metric of geodesic distance among them. Sharp vertices are extracted from the mesh by analyzing convexity that reflects global geometry. As well as speeding up the computing time, the sharp vertices of this kind avoid the problem of local optima that may occur when feature points are extracted by analyzing the convexity that reflects local geometry. For obtaining more effective results, the sharp vertices are categorized according to the priority from the viewpoint of cognitive science, and the reasonable number of clusters is automatically determined by analyzing the geometric features of the mesh.

• Korean Journal of Computational Design and Engineering
• /
• v.12 no.6
• /
• pp.413-421
• /
• 2007

3D rendering is becoming a common feature of mobile application programs with the rapid advance of mobile devices. Since the existing rendering engines do not provide triangulation functions, mobile 3D programs have focused on an efficient handling with pre-tessellated geometry. In addition, triangulation is comparatively expensive in computation, so it seems that the triangulation cannot be easily implemented on mobile devices with limited resources. Triangulation of 3D geometry is the essential process of visualization of 3D model data and many different triangulation methods have been reported. We developed a light and fast visualization process that involves constrained triangulation based on Voronoi diagram and applied it to a mobile computer application. In this paper, we applied kd-tree to the original incremental construction algorithm and produced new O(nlogn) incremental construction algorithm. And we show a simple and efficient constrained triangulation method based on Voronoi diagram. This paper also describes an implementation of mobile STEP data viewer as an application of our proposed algorithms.