• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3962-3980
• /
• 2019

To deal with single sample face recognition, this paper presents a patch based semi-supervised linear regression (PSLR) algorithm, which draws facial variation information from unlabeled samples. Each facial image is divided into overlapped patches, and a regression model with mapping matrix will be constructed on each patch. Then, we adjust these matrices by mapping unlabeled patches to $[1,1,{\cdots},1]^T$. The solutions of all the mapping matrices are integrated into an overall objective function, which uses ${\ell}_{2,1}$-norm minimization constraints to improve discrimination ability of mapping matrices and reduce the impact of noise. After mapping matrices are computed, we adopt majority-voting strategy to classify the probe samples. To further learn the discrimination information between probe samples and obtain more robust mapping matrices, we also propose a multistage PSLR (MPSLR) algorithm, which iteratively updates the training dataset by adding those reliably labeled probe samples into it. The effectiveness of our approaches is evaluated using three public facial databases. Experimental results prove that our approaches are robust to illumination, expression and occlusion.

• Journal of the Korean Geographical Society
• /
• v.33 no.3
• /
• pp.435-446
• /
• 1998

This Paper reports that a new remote sensing techlique focused on a narrow and long strip target (e.g. 15m wide and 100km long) has been specifically developed for pipeline ROW (Right-Of-Way) recovery monitoring. With video it was possible to isolate the maior vegetation communities of the narrow pipeline ROW with acceptable spatial precision by visual or quantitative methods. It was particuarly useful when used to assess a variety of spatial patch dynamics for ROW recovery through digital change-detection techniques in a GIS environment. The main conclusion of this paper is that VSM is a realistic operational technique for a pipeline ROW application. The results also indicate that VSM could be extensively used for other examples of linear thematic mapping.

• Journal of Digital Contents Society
• /
• v.19 no.9
• /
• pp.1727-1737
• /
• 2018

In this paper, we propose a system to detect spatial structures in land cover maps and to detect time-series spatial structure changes. At first, the proposed system detects patches in a certain area at different times and calculates their measures to analyse spatial structure patterns of the area. Then the system conducts patch mapping among the detected time-series patches and decides 6 types of patch changes such as keeping, creating, disappearing, splitting, merging, and changing in a mixed way. Also, the system stores the patch-based spatial structure patterns of time-series land cover maps in binary form to extract changes. This demonstrated that the proposed change detection system can be used as a basis for planning the reconstruction of the urban spatial structure by measuring the degree of urban sprawl.

• Journal of Biomedical Engineering Research
• /
• v.27 no.2
• /
• pp.64-72
• /
• 2006

The present study introduces a new cortical patch-based source model for EEG/MEG cortical source imaging to consider anatomical constraints more precisely. Conventional source models for EEG/MEG cortical source imaging have used coarse cortical surface mesh or sampled small number of vertices from fine surface mesh, and thus they failed to utilize full anatomical information which nowadays we can get with sub-millimeter modeling accuracy. Conventional ones placed a single dipolar source on each cortical patch and estimated its intensity by means of various inverse algorithms; whereas the suggested cortical patch-based model integrates whole cortical area to construct lead field matrix and estimates current density that is assumed to be constant in each cortical patch. We applied the proposed and conventional models to realistic EEG data and compared the results quantitatively. The quantitative comparisons showed that the proposed model can provide more precise spatial descriptions of neuronal source distribution.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.22 no.5
• /
• pp.463-474
• /
• 2009

Double symmetric patch repair of existing structures always causes membrane action only, however, in many cases this technique is not practical. On the other hand, the bending stiffness of the patch and the skin increases as tensile loading is increased and affects the bending deformation significantly in the case of single-sided patch repair. In this study, the p-convergent full layerwise model has been proposed to determine the stress concentration factor in the vicinity of a circular hole as well as across the thickness of plates with single-sided patch repair. In assumed displacement field, the strain-displacement relations and 3-D constitutive equations of a layer are obtained by the combination of 2-D and 3-D hierarchical shape functions. The transfinite mapping technique has been used to represent a circular boundary and Gauss-Lobatto numerical integration is implemented in order to directly obtain stresses occurred at the nodal points of each layer without other extrapolation techniques. The accuracy and simplicity of the present model are verified with comparison of the previous results in literatures using experiment and conventional 3-D finite element. Also, the bending effect has been investigated with various patch types like square, circular and annular shape.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.1A
• /
• pp.39-48
• /
• 2012

This study deals with numerical determination of stress intensity factors of adhesively patch-repaired plates with cracks at V-shaped or semicircular notches. The p-convergent anisoparametric model are considered and then three-dimensional virtual crack closure technique is presented using formulations of anisoparametric elements. In assumed displacement fields of an element, strain-displacement relations and three-dimensional constitutive equations are derived with three-dimensional hierarchical shape functions expanded from one-dimensional Lobatto functions. Transfinite mapping technique is used to represent a circular boundary. The present model provides accuracy and simplicity in terms of stress concentration factor, stress distribution, the number of degrees of freedom, and non-dimensional stress intensity factor as compared with previous works in literatures. Stress intensity factors obtained by the three-dimensional virtual crack closure technique are estimated with respect to the variation of width of finite plate, radius of notch root, angular inclination of V-shaped notch, and crack length.

• Proceedings of the KIEE Conference
• /
• 2015.07a
• /
• pp.1435-1435
• /
• 2015

광고 및 홍보의 마케팅 수단의 일환으로써 점포별로 QR코드를 사용하는 사례가 급격히 늘고 있다. 정보도트의 일종인 QR코드의 경우는 스마트폰과 더불어 홍보수단의 일환으로 활용되는 사례가 증가하고 있는 반면 QR코드는 정보를 표현할 수 있는 디자인의 범위가 좁고, 전송할 수 있는 Data의 용량이 적으며, 어두운 환경에서의 인식률이 저하되는 단점이 있다. 이에 기존의 QR코드 보다 다양한 디자인이 가능하고 대용량의 Data 전송이 가능한 컬러코드가 대두되고 있다. 컬러코드란 4가지 색상(빨강, 파랑, 초록, 검정)을 이용한 매트릭스 형태의 코드로 각종 디지털 정보를 저장하는 새로운 개념의 데이터 표현 기술이며, 이는 각 컬러에 디지털 정보를 매핑(mapping)하여 콘텐츠나 URL 등의 실제 정보들을 제공하는 역할을 하도록 설계되어 있다. 8MP CMOS센서기반 Colored LED Patch 인식 기법은 VLC에 포함되는 하나의 기술로서 차세대 조명 및 정보 디스플레이 장치로 각광을 받고 있는 반도체 조명 기술인 광원 정보 인식 기법이다. 따라서, 본 논문에서는 8MP CMOS센서 기반 컬러코드 LED Patch 인식 기법에 대해 제안하였다. 8MP CMOS 센서를 이용한 Colored LED Patch 인식 기법 중 하나로서 위치 정보 서비스 등 다양한 정보 획득이 가능하도록 연구하였으며, 동영상, 웹사이트 링크 등 여러 형식에 적용이 가능하도록 하였다. 본 연구에서 사용되는 8MP CMOS센서를 기반 Colored LED Patch 인식 기법을 통해 컬러코드는 코드 플랫폼으로 연결되어 콘텐츠의 위치를 파악하고 이용자에게 콘텐츠 및 정보가 전송된다. 이는 QR코드보다 높은 인식률로 빠르고 편리하게 정보를 제공할 수 있었다. 본 논문에서는 상기 제안 기술을 통하여 LED Patch의 높은 주목성과 가시성을 확보하여 보다 효과적인 광고 및 홍보의 시인성을 확보할 수 있다. 향후 본 제안기술을 통하여 사회 안전망을 위한 위치 및 정보 서비스 제공이 가능하며, 효과적인 광고 효과를 도출할 수 있을 것으로 사료된다.

• Transactions of Materials Processing
• /
• v.13 no.1
• /
• pp.90-101
• /
• 2004

An inverse mosaic method has been proposed to generate an initial blank shape from the final product shape. Differently from the geometric mapping method, the method can handle triangular patches. However, the generated blank shape is strongly dependent on the order of determination of nodes. In order to compensate the dependency error smoothing technique has been also developed. Although the accuracy has been improved greatly compared with the geometrical mapping method, the method has limitation, due to the no incorporation of plasticity theory. Even though the accuracy of the radius vector method is already proved. the method requires initial guess to start the method. In order to compromise the limitation of the present method and the radius vector method, the method has been connected to the radius vector method. The efficiency of the present optimal blank design method has been verified with some chosen examples.

• ALGAE
• /
• v.23 no.1
• /
• pp.83-90
• /
• 2008

Eelgrass beds are very productive and provide nursery functions for a variety of fish and shellfish species. Management for the conservation of eelgrass beds along the Korean coasts is critical, and requires comprehensive strategies such as vegetation mapping. We suggest a mapping method to spatial distribution and quantify of eelgrass beds using a digital echosounder. Echosounding data were collected from the northeast part of Kwangyang Bay, on the south of Korea, in March, 2007. A transducer was attached to a boat equipped with a DGPS. The boat completed a transect survey scanning whole eelgrass beds of 11.7 km2 with a speed of 1.5-2 m s-1 (3-4 knot). The acoustic reflectivity of eelgrass allowed for detection and explicit measurements of canopy cover and height. The results showed that eelgrass bed was distributed in depth from 1.19 to 3.6 m (below MSL) and total dry weight biomass of 4.1 ton with a vegetation area of 4.05 km2. This technique was found to be an effective way to undertake the patch size and biomass of eelgrass over large areas as nondestructive sampling.

• Korean Journal of Agricultural Science
• /
• v.41 no.3
• /
• pp.205-211
• /
• 2014

Focused on Mt. Bogdkhan nature reserve in Mongolia, this study was conducted as a fundamental research to discover a tendency and characteristics of forest damage and to draw up measures for proper plans of forest restoration through an analysis of year-to year change using satellite images. In specific, land cover mapping was conducted by using Landsat images from 1994 to 2011, and then year-to year change was analyzed to investigate the features of forest damage in Mt. Bogdkhan. The results showed that the whole area of a reservation in Mongolia in 2011 was about $416.89km^2$; among them, forest area was $167,87km^2$, accounting for about 40.3%, followed by bare patch and grassland area (58.6%) and urban dry area (1.1%). In particular, compared in 1994, the area of forest in 2011 has increased by $6.12km^2$; while bare patch and grassland area has decreased by $10.81km^2$. Primary causes of forest degradation occurred in Mt. Bogdkhan nature reserve included illegal logging for fuel, forest and grassland degradation caused by domestic animals grazing, man-made forest fire, and disaster caused by insect pest.