• Journal of the Korean Institute of Intelligent Systems
• /
• v.8 no.3
• /
• pp.95-103
• /
• 1998

This paper deals with a problem occuring in recognition of tactile images due to the effects of imposed force at a me urement moment. Tactile image of a contact surface, used for recognition of the surface type, varies depending on the forces imposed so that a false recognition may result in. This paper fuzzifies two parameters of the contour of a tactile image with the membership function formed by considering the imposed force. Two fuzzifed paramenters are fused by the average Minkowski's dist; lnce. The proposed algorithm was implemented on the multisensor system cnmposed of an optical tact le sensor and a 6 axes forceltorque sensor. By the experiments, the proposed algorithm has shown average recognition ratio greater than 869% over all imposed force ranges and object models which is about 14% enhancement comparing to the case where only the contour information is used. The pro- ~oseda lgorithm can be used for end-effectors manipulating a deformable or fragile objects or for recognition of 3D objects by implementing on multi-fingered robot hand.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.38 no.1
• /
• pp.43-57
• /
• 2002

This paper introduces an analysis method to predicting the flow characteristic of flow field around otter board In order to develope a high performance model. In this experiment, it is used a numerical analysis of flow field through CFD(Computational Fluid Dynamic), PIV method in which quantitative, qualitative evaluation is possible. In this experiment, it is used PIV method with flow filed image around otter board in order to analysis of flow characteristic. The result compared flow pattern with analysis result through CFD and also measurement result of lift and drag force coefficient carried out in CWC(Circulating Water Channel). The numerical analysis result is matched well with experiment result of PIV in the research and it is able to verify In the physical aspect. The result is as follows ; (1) It was carried out visibility experiment using laser light sheet, and picture analysis through PIV method in order to analysis fluid field of otter-board. As a result, the tendency of qualitative fluid movement only through the fluid particle's flow could be known. (2) Since PIV analysis result is quantitative, this can be seen in velocity vector distributions, instantaneous streamline contour, and average vorticity distributions through various post processing method. As a result, the change of flow field could be confirmed. (3) At angle of attack 24$^{\circ}$ where It Is shown maximum spreading force coefficient, the analysis result of CFD and PIV had very similar flow pattern. In both case, at the otter-board post edge a little boundary layer separation was seen, but, generally they had a good flow (4) As the result of post processing with velocity vector distributions, instantaneous streamline contour and average vorticity distributions by PIV, boundary layer separation phenomenon started to happen from angle of attack 24$^{\circ}$, and from over angle of attack 28$^{\circ}$, it happen at leading edge side with the width enlarged.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.25-36
• /
• 2008

In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model.

• Journal of KIISE:Software and Applications
• /
• v.29 no.11
• /
• pp.818-825
• /
• 2002

Depth information is one of the most important factor for the recognition of a digital face image. Range images are very useful, when comparing one face with other faces, because of implicating depth information. As the processing for the whole fare produces a lot of calculations and data, face images ran be represented in terms of a vector of feature descriptors for a local area. In this paper, depth areas of a 3 dimensional(3D) face image were extracted by the contour line from some depth value. These were resampled and stored in consecutive location in feature vector using multiple feature method. A comparison between two faces was made based on their distance in the feature space, using Euclidian distance. This paper reduced the number of index data in the database and used fewer feature vectors than other methods. Proposed algorithm can be highly recognized for using local depth information and less feature vectors or the face.

• The KIPS Transactions:PartB
• /
• v.19B no.4
• /
• pp.221-224
• /
• 2012

The most famous algorithm of splitting and connecting Snake for extracting the boundary of multiple objects is the nearest method using the distance between snake points. It often can't split and connect Snake due to object topology. In this paper, its problem was discussed experimentally. The new algorithm using vector between Snake segment is proposed in order to split and connect Snake with complicated topology of objects. It is shown by experiment of two test images with 3 and 5 objects that the proposed one works better than the nearest one.

• 한국전산유체공학회:학술대회논문집
• /
• 2006.05a
• /
• pp.395-397
• /
• 2006

Air interlacing serves to protect the yarn against damage, strengthens inter-filament compactness or cohesion, and ensures fabric consistency. The air interlacing nozzle is used to introduce intermittent nips to a filament yarn so as to improve its performance in textile processing. The effect of various interlacing nozzle geometries on the interlacing process was studied. The geometries of interlacing nozzles with single or multiple air inlets located across the width of yarn channels are investigated. The basis case is the yarn channel, with a perpendicular main air inlet in the middle. Other cases have main air inlets, slightly inclined double sub air inlets, The yarn channel cross sectional shapes are either semicircular or rectangular shapes. The compressed impinging jet from the main air inlet hole hits the opposing bottom wall of the yarn channel, is divided into two branches, joins with the compressed air coming out from sub air inlet at the bottom and creates two free jets at both ends of the yarn channel. The compressed air movement in the cross-section consists of two opposing directional vortices. The CFD-FASTRAN flow parallel solver was used to perform steady simulations of impinging jet flow inside of the interlace nozzles. The vortical structure and the flow pattern such as pressure contour, particle traces, velocity vector plots inside of interlace nozzle geometry are discussed in this pater.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.515-520
• /
• 2006

계량기 숫자 인식은 일반적으로 사용되고 있는 아날로그 계량기에 카메라를 부착하여, 검침 시 숫자 계기판 영상을 전송받고, 그 영상으로부터 숫자를 추출 및 인식하는 기술이다. 계량기 숫자 인식에서는 카메라의 설치 상태 및 기타 환경적인 요인들로 인해 숫자 계기판 영상의 일관성 있는 취득이 어렵게 된다. 본 논문에서는 숫자 인식에 악영향을 미치는, 취득 영상의 상태 변화를 보정해주기 위해 잡영 제거 및 윤곽보존 숫자강화를 제안하였다. 잡영 제거를 위해 잡영을 분포 위치에 따라서 세 가지 타입으로 나누었으며, 각 타입별로 잡영 제거를 하였다. 윤곽보존 숫자강화 과정에서는 일반적인 이진화 기법이 가지는 테두리 정보손실을 최소화할 수 있도록, 숫자 테두리의 명도를 보존하면서 숫자 중심부분의 밝기를 강화시켰다. 전처리 전/후의 인식률 비교 실험을 위해 SVM(Support Vector Machines)을 사용하였으며, 학습 데이터 1,409장과 조명 상태를 달리하여 취득한 1,782의 테스트 데이터를 실험 데이터로 사용하였다. 실험 결과, 81.09%라는 성능 향상을 확인하였으며 이는 제안한 전처리 기법이 조명으로 인한 데이터의 상태 변화 문제를 해결해줌으로써 인식 성능 향상에 크게 기여한다는 것을 입증해준다.

• ETRI Journal
• /
• v.33 no.4
• /
• pp.537-546
• /
• 2011

This paper introduces an automated method for building height recovery through the integration of high-resolution satellite images and digital vector maps. A cross-correlation matching method along the vertical line locus on the Ikonos images was deployed to recover building heights. The rational function models composed of rational polynomial coefficients were utilized to create a stereopair of the epipolar resampled Ikonos images. Building footprints from the digital maps were used for locating the vertical guideline along the building edges. The digital terrain model (DTM) was generated from the contour layer in the digital maps. The terrain height derived from the DTM at each foot of the buildings was used as the starting location for image matching. At a preset incremental value of height along the vertical guidelines derived from vertical line loci, an evaluation process that is based on the cross-correlation matching of the images was carried out to test if the top of the building has reached where maximum correlation occurs. The accuracy of the reconstructed buildings was evaluated by the comparison with manually digitized 3D building data derived from aerial photographs.

• Journal of computational fluids engineering
• /
• v.14 no.4
• /
• pp.67-77
• /
• 2009

This paper is a continuation of a recent development on the Hermite-based divergence-free element method and deals with a non-isothermal fluid flow driven by the buoyancy force in a square cavity with temperature difference across the two sides. Two Hermite functions are considered for numerical computations in this paper. One is a cubic function and the other is a quartic function. The degrees-of-freedom of the cubic Hermite function are stream function and its first and second derivatives for the velocity field, and temperature and its first derivatives for the temperature field. The degrees-of-freedom of the quartic Hermite function include two second derivatives and one cross derivative of the stream function in addition to the degrees-of-freedom of the cubic stream function. This paper presents a brief review on the Hermite based divergence-free basis functions and its finite element formulations for the buoyancy driven flow. The present algorithm does not employ any upwinding or a stabilization term. However, numerical values and contour graphs for major flow variables showed good agreements with those by De Vahl Davis[6].

• Journal of Navigation and Port Research
• /
• v.30 no.5 s.111
• /
• pp.369-374
• /
• 2006

The flow analysis was made by applying the turbulent models in the complicated fuel chamber of engine. The $k-\varepsilon,\;k-\omega$, Spalart-Allmaras and reynolds stress models are used in which the hybrid grid is applied for the simulation. The velocity vector, the pressure contour, the change of residual along the iteration number, and the dynamic head are simulated for the comparison of four example cases. Computational results are compared with others. For the code's validation, 2-D bodies were simulated in advance by predicting the drag coefficients.