• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1721-1737
• /
• 2020

Human apparent age estimation has become a popular research topic and attracted great attention in recent years due to its wide applications, such as personal security and law enforcement. To achieve the goal of age estimation, a large number of methods have been pro-posed, where the models derived through the cumulative attribute coding achieve promised performance by preserving the neighbor-similarity of ages. However, these methods afore-mentioned ignore the geometric structure of extracted facial features. Indeed, the geometric structure of data greatly affects the accuracy of prediction. To this end, we propose an age estimation algorithm through joint feature selection and manifold learning paradigms, so-called Feature-selected and Geometry-preserved Least Square Regression (FGLSR). Based on this, our proposed method, compared with the others, not only preserves the geometry structures within facial representations, but also selects the discriminative features. Moreover, a deep learning extension based FGLSR is proposed later, namely Feature selected and Geometry preserved Neural Network (FGNN). Finally, related experiments are conducted on Morph2 and FG-Net datasets for FGLSR and on Morph2 datasets for FGNN. Experimental results testify our method achieve the best performances.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.5
• /
• pp.660-667
• /
• 2006

This paper presents a novel region-based snake method for vessel segmentation. According to geometric shape analysis of the vessel structure with different scale, an efficient statistical estimation of vessel branches is introduced into the energy objective function, which applies not only the vessel intensity information, but also geometric information of line-like structure in the image. The defined energy function is minimized using the gradient descent method and a new region-based speed function is obtained, which is more accurate to the vessel structure and not sensitive to the initial condition. The narrow band algorithm in the level set framework implements the proposed method, the solution of which is steady. The segmentation experiments are shown on several images. Compared with other geometric active contour models, the proposed method is more efficient and robust.

• International journal of advanced smart convergence
• /
• v.5 no.4
• /
• pp.1-9
• /
• 2016

In order to reconstruct a 3D model in video sequences, to select key frames that are easy to estimate a geometric model is essential. This paper proposes a method to easily extract informative frames from a handheld video. The method combines selection criteria based on appropriate-baseline determination between frames, frame jumping for fast searching in the video, geometric robust information criterion (GRIC) scores for the frame-to-frame homography and fundamental matrix, and blurry-frame removal. Through experiments with videos taken in indoor space, the proposed method shows creating a more robust 3D point cloud than existing methods, even in the presence of motion blur and degenerate motions.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.20 no.6
• /
• pp.369-378
• /
• 2016

The design spectrum for Korea, which is known to belong to an intra-plate region, is developed from the ground motion records of the earthquakes occurred in Korea and overseas intra-plate regions. The horizontal spectrum is defined as geometric mean spectrum, GMRotI50. From the statistical analysis of the geometric mean spectra, a mean plus one standard deviation spectrum in lognormal distribution is obtained. Regression analysis is performed on this curve to determine the shape of spectrum including transition periods. The developed design spectrum is valid for the estimation both spectral acceleration and displacement.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.427-430
• /
• 1989

For on-line ARMA spectral estimation, the fast transversal filter algorithm of extended least squares method(ETS FTF) is presented. The projection operator, a key tool for geometric approach, is used in the derivation of the algorithm. ELS FTF is a fast time update recursion which is based on the fact that the correlation matrix of ARMA model satisfies the shift invariance property in each block, and thus it takes 10N+31 MADPR.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.105-106
• /
• 2007

We present a fast reconstruction technique for elliptic objects, which can be applied to real-time computer tomography (CT) for simple geometric objects. It will be also shown that only 3 projections are needed to reconstruct an ellipse. A piecewise quadratic model is also proposed for more efficient Kalman filter based support estimation, which is used for the fast reconstruction technique. The performance of the piecewise quadratic model is compared with that of the existing piecewise linear model. Simulation results for the fast reconstruction are also presented.

• Journal of Korean Society of Steel Construction
• /
• v.19 no.3
• /
• pp.313-321
• /
• 2007

The study discussed in this paper presents a method of estimating sources of geometric errors in suspension bridges in use, based on geometric survey data. A geometric error is defined as the difference between the survey data and the design geometry of a main cable. It is assumed that the geometric error in a suspension bridge is caused by the variations in the weight of the stiffening girder and the deformation of the anchorage foundations due to the creep of soil. The variations in the girder weight and the deformation of the foundation were estimated by constructing a matrix of factors that affect suspension bridges due to the variations. To check the validity of the proposed method, it was applied to the Kwang-An Bridge, and the sources of geometric errors in the bridge were estimated using the survey data.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2003.07b
• /
• pp.1227-1230
• /
• 2003

In this paper, we propose a pose estimation method using local map acquired from 2d laser range finder information. The proposed method uses extended kalman filter. The state equation is a navigation system equation of Nomad Super Scout II. The measurement equation is a map-based measurement equation using a SICK PLS 101-112 sensor. We describe a map consisting of geometric features such as plane, edge and corner. For pose estimation we scan external environments by laser rage finer. And then these data are fed to kalman filter to estimate robot pose and position. The proposed method enables very fast simultaneous map building and pose estimation.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.34-39
• /
• 1999

If the on-line cutting conditions (e.g. speed, feedrate, radial and axal depth of cuts) can be identified in an end milling process, much information about cutting forces will be estimated from the cutting force model. Therefore, those estimated conditions can be applied to monitoring and control areas. In this paper, a real-time estimation algorithm for radial and axial depth of cuts is studied in end milling using the averaging cutting forces per tooth. The analytical estimation models of depth of cuts are derived from the geometric cutting force model. The validity of the estimation models is verified on a horizontal machining center through the experiments in various cutting conditions.

• Journal of Korean Society of Steel Construction
• /
• v.21 no.3
• /
• pp.203-210
• /
• 2009

If there are some construction works that affect the stability of buried pipelines, the pipelines should be moved to guarantee their safety. In this paper, modeling methods for analyzing the movement of pipelines were sought, and the step-by-step stress estimation method of moving pipelines was developed. Some factors affecting of pipeline response such as the element type, the element size, boundary modeling, and geometric non-linearity were quantitatively investigated. In addition, some conditions in which accuracy and effectiveness can be compromised in the analysis of long pipelines were identified. A neural network was used to estimate the pipeline stress. The inputs to the neural network included step-by-step displacements, and the output was the resulting stress at each movement step. After training the neural network, it can be used to estimate pipeline stresses at some sub-steps that are not included in the training. A Windows-based stress estimation program was developed.