• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.87-92
• /
• 2003

This paper describes a system for tracking multiple faces in an input video sequence using facial convex hull based facial segmentation and robust hausdorff distance. The algorithm adapts skin color reference map in YCbCr color space and hair color reference map in RGB color space for classifying face region. Then, we obtain an initial face model with preprocessing and convex hull. For tracking, this algorithm computes displacement of the point set between frames using a robust hausdorff distance and the best possible displacement is selected. Finally, the initial face model is updated using the displacement. We provide an example to illustrate the proposed tracking algorithm, which efficiently tracks rotating and zooming faces as well as existing multiple faces in video sequences obtained from CCD camera.

• Advances in aircraft and spacecraft science
• /
• v.1 no.4
• /
• pp.443-454
• /
• 2014

An experimental study was conducted to investigate the effect of Reynolds number on compressible convex-corner flows, which correspond to an upper surface of a deflected flap of an aircraft wing. The flow is naturally developed along a flat plate with two different lengths, resulting in different incoming boundary layer thicknesses or Reynolds numbers. It is found that boundary layer Reynolds number, ranging from $8.04{\times}10^4$ to $1.63{\times}10^5$, has a minor influence on flow expansion and compression near the corner apex in the transonic flow regime, but not for the subsonic expansion flow. For shock-induced separated flow, higher peak pressure fluctuations are observed at smaller Reynolds number, corresponding to the excursion phenomena and the shorter region of shock-induced boundary layer separation. An explicit correlation of separation length with deflection angle is also presented.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.137-144
• /
• 2014

This paper proposes a novel procedure that uses a combination of overlapped basic convex shapes to decompose 2D silhouette image. A basic convex shape is used here as a structuring element to give a meaningful interpretation to 2D images. Poisson equation is utilized to obtain the basic shapes for either the whole image or a partial region or segment of an image. The reconstruction procedure is used to combine the basic convex shapes to generate the original shape. The decomposition process involves a merging stage, filtering stage and finalized by compromising stage. The merging procedure is based on solving Poisson's equation for two regions satisfying the same symmetrical conditions which leads to finding equivalencies between basic shapes that need to be merged. We implemented and tested our novel algorithm using 2D silhouette images. The test results showed that the proposed algorithm lead to an efficient shape decomposition procedure that transforms any shape into a simpler basic convex shapes.

• Journal of applied mathematics & informatics
• /
• v.27 no.1_2
• /
• pp.233-243
• /
• 2009

This paper concerns an algorithm that combines line search and trust region step for nonlinear optimization problems. Unlike traditional trust region methods, we incorporate the Armijo line search technique into trust region method to solve the subproblem. In addition, the subproblem is solved accurately, but instead solved by inaccurate method. If a trial step is not accepted, our algorithm performs the Armijo line search from the failed point to find a suitable steplength. At each iteration, the subproblem is solved only one time. In contrast to interior methods, the optimal solution is derived by iterating from outside of the feasible region. In numerical experiment, we apply the algorithm to nonlinear portfolio optimization problems, primary numerical results are presented.

• Journal of applied mathematics & informatics
• /
• v.16 no.1_2
• /
• pp.125-142
• /
• 2004

We analyze the convergence properties of Powell's UOBYQA method. A distinguished feature of the method is its use of two trust region radii. We first study the convergence of the method when the objective function is quadratic. We then prove that it is globally convergent for general objective functions when the second trust region radius p converges to zero. This gives a justification for the use of p as a stopping criterion. Finally, we show that a variant of this method is superlinearly convergent when the objective function is strictly convex at the solution.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.783-788
• /
• 2003

In this paper, we present a new approach to detect and recognize human face in the image from vision camera equipped on the mobile robot platform. Due to the mobility of camera platform, obtained facial image is small and pose-various. For this condition, new algorithm should cope with these constraints and can detect and recognize face in nearly real time. In detection step, ‘coarse to fine’ detection strategy is used. Firstly, region boundary including face is roughly located by dual ellipse templates of facial color and on this region, the locations of three main facial features- two eyes and mouth-are estimated. For this, simplified facial feature maps using characteristic chrominance are made out and candidate pixels are segmented as eye or mouth pixels group. These candidate facial features are verified whether the length and orientation of feature pairs are suitable for face geometry. In recognition step, pseudo-convex hull area of gray face image is defined which area includes feature triangle connecting two eyes and mouth. And random lattice line set are composed and laid on this convex hull area, and then 2D appearance of this area is represented. From these procedures, facial information of detected face is obtained and face DB images are similarly processed for each person class. Based on facial information of these areas, distance measure of match of lattice lines is calculated and face image is recognized using this measure as a classifier. This proposed detection and recognition algorithms overcome the constraints of previous approach [15], make real-time face detection and recognition possible, and guarantee the correct recognition irregardless of some pose variation of face. The usefulness at mobile robot application is demonstrated.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1853-1858
• /
• 2021

O-rings fill the gaps between mechanical parts. Until now, the sorting of defective products has been performed visually and manually, so classification errors often occur. Therefore, a camera-based defect classification system without human intervention is required. However, a binarization process is required to separate the required region from the background in the camera input image. In this paper, an adaptive binarization technique that considers the surrounding pixel values is applied to solve the problem that single-threshold binarization is difficult to apply due to factors such as changes in ambient lighting or reflections. In addition, the convex hull technique is also applied to compensate for the missing pixel part. And the learning model to be applied to the separated region applies the residual error-based deep learning neural network model, which is advantageous when the defective characteristic is non-linear. It is suggested that the proposed system through experiments can be applied to the automation of O-ring defect detection.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.2
• /
• pp.41-47
• /
• 2007

A fine segmentation algorithm is proposed for extracting objects in an image, which have both weak boundaries and highly non-convex shapes. The image has simple background colors or simple object colors. Two concepts, geometric attraction-driven flow (GADF) and edge-regions are combined to detect boundaries of objects in a sub-pixel resolution. The main strategy to segment the boundaries is to construct initial curves close to objects by using edge-regions and then to make a curve evolution in GADF. Since the initial curves are close to objects regardless of shapes, highly non-convex shapes are easily detected and dependence on initial curves in boundary-based segmentation algorithms is naturally removed. Weak boundaries are also detected because the orientation of GADF is obtained regardless of the strength of boundaries. For a fine segmentation, we additionally propose a local region competition algorithm to detect perceptible boundaries which are used for the extraction of objects without visual loss of detailed shapes. We have successfully accomplished the fine segmentation of objects from images taken in the studio and aphids from images of soybean leaves.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.3
• /
• pp.46-54
• /
• 2008

Most commercial CCD/CMOS image sensors have CFA(Color Filter Array) where each pixel gathers light of a selective color to reduce the sensor size and cost. There are many algorithms proposed to reconstruct the original clolr image by adopting pettern recognition of regularization methods to name a few. However the resulting image still suffer from errors such as flase color, zipper effect. In this paper we propose an adaptive edge weight demosaicking algorithm that is based on POCS(Projection Onto Convex Sets) not only to improve the entire image's PSNR but also to reduce the edge region's errors that affect subjective image quality. As a result, the proposed algorithm reconstruct better quality images especially at the edge region.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.162-165
• /
• 2017

The proposed paper extracts the region of interest from the x-lay input image and compares it with the reference image. The x-ray image has the same shape, but the size, direction and position of the object are photographed differently. In this way, we measure the erection difference of darkness and darkness using the similarity measurement method for the same object. Distance measurement also calculates the distance between two points with vector coordinates (x, y, z) of x-lay data. Experimental results show that the proposed method improves the accuracy of ROI extraction and the reference image matching time is more efficient than the conventional method.