• Annual Conference of KIPS
• /
• 2002.11a
• /
• pp.633-636
• /
• 2002

기존에 얼굴인식이나 얼굴영역을 추출하는 방법들은 대부분 얼굴의 외곽선은 고려하지 않은 상태에서 얼굴의 특징인 눈, 코, 입 부분만을 추출하는 경우가 많아 정확한 얼굴을 추출하기가 어려웠다. 본 논문에서는 얼굴의 색상과 영역분할 기법(Region Segmentation technique)을 함께 사용해서 얼굴부분과 얼굴의 특징을 추출하여 보다 정확한 얼굴 부분을 분할하고자 한다. 얼굴추출방법을 대표색상 추출과정과 실제 영역을 분할하여 얼굴부분을 추출하는 과정으로 나누어 히스토그램을 이용하여 대표색상을 추출한 후, 영역분할 기법을 이용하여 대표색상을 포함하고 있는 영역에 대해 얼굴이라는 가정을 배제하고, 이미지들을 객체(Object)화 하여 조건에 맞지 않는 객체들을 모두 제거함으로써, 정확한 얼굴부분을 분할해 낸다.

• Annual Conference of KIPS
• /
• 2003.05a
• /
• pp.611-614
• /
• 2003

본 논문에서는 컨베이어 벨트상에서 이송되는 대용량 소포영상의 획득과정을 통해 ROI(Region of Interest) 고속추출하기 위한 개념모델을 제시하고, 바코드와 같은 정규패턴을 고속으로 추출하여 단계적으로 검증한 것이다. 불필요한 영역을 검사하기 위한 조건과 유사한 패턴을 단계적으로 제거하는 방법을 적용한 것이다. $4,096{\times}4,096$이상의 대용량 영상에서 여러 종류의 2차원 바코드 ROI를 추출에 대해 약 200msec 이내에 완료되고, 거의 100%에 가까운 신뢰도로 바코드 영역을 추출할 수 있도록 한 것이다.

• Annual Conference of KIPS
• /
• 2003.05a
• /
• pp.615-618
• /
• 2003

본 논문에서는 컨베이어 벨트상에서 이송되는 대용량 소포영상의 획득과정을 통해 ROI(Region of Interest) 고속추출하기 위한 방법 중에서 소포의 면적을 산출하기 위한 외형 좌표값을 산출하는 방법을 제시한 것이다. 이송하는 과정에서 높이센서의 값과 투입되는 각도에 따라 최장길이가 다르지만 이 값도 산출이 용이하다 이와 같은 정보와 결합하여 소포의 부피를 산출을 위해 사용될 수 있는 소포의 외형 좌표값들의 산출 방법과 활용방법을 제시한 것이다. 초기과정에는 불필요한 영역을 검사하기 위한 조건과 유사한 패턴을 단계적으로 제거하는 방법을 적용하였다. $4,096{\times}4,096$ 이상의 대용량 영상에서 불필요한 영역 제거 시간을 포함하여 평균 30.85msec 이내에 추출이 가능한 방법을 제시한 것이다.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2914-2916
• /
• 1999

A power distribution facility map is composed of distribution facility information regions, cadastral regions and grid lines. In this map, our goal is automatic interpretation of power distribution region. For the goal, it is the first work to extract the power distribution facility region. In this paper, we propose a method to extract power distribution facility regions. The proposed method is consist of two phases, binarization phase and extending phase. The first phase generate a power distribution facility image using threshold value. The image contains many part of power distribution facility regions, but not all. The second phase extends thinned image which is generated by appling thinning operator to the power distribution facility image.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.11 no.5
• /
• pp.347-352
• /
• 1998

In this paper, the extraction and optimization of SPICE parameters on SONOSFET for NVSM circuit design were discussed. SONOSFET devices with different channel widths and lengths were fabricated using conventional 1.2 um n-well CMOS process. And, electric properties for dc parameters and capacitance parameters were measured on wafer. SPICE parameters for the SONOSFET were extracted from the UC Berkeley level 3 model for the MOSFET. And, local optimization of Ids-Vgs curves has carried out in the bias region of subthreshold, linear, saturation respectively. Finally, the extracted SPICE parameters were optimized globally by comparing drain current (Ids), output conductance(gds), transconductance(gm) curves with theoretical curves in whole region of bias conditions. It is shown that the conventional model for the MOSFET can be applied to the SONOSFET modeling except sidewalk effect.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.02a
• /
• pp.64-72
• /
• 2004

Correction of shadow effects is critical step for image interpretation and feature extraction from aerial imagery. In this paper, an efficient algorithm to correct shadow effects from aerial color imagery is presented. The following steps have been performed to remove the shadow effect. First, the shadow regions are precisely located using the solar position and the height of ground objects derived from LIDAR (Light Detection and Ranging) data. Subsequently, segmentation of context regions is implemented for accurate correction with existing digital map. Next step, to calculate correction factor the comparison between the context region and the same non-shadowed context region is made. Finally, corrected image is generated by correcting the shadow effect. The result presented here helps to accurately extract and interpret geo-spatial information from aerial color imagery

• Journal of Korea Multimedia Society
• /
• v.11 no.6
• /
• pp.787-795
• /
• 2008

Human recognition on camera is an interesting topic in computer vision. While fingerprint and face recognition have been become common, gait is considered as a new biometric feature for distance recognition. In this paper, we propose a gait recognition algorithm based on the knee angle, 2 feet distance, walking velocity and head direction of a person who appear in camera view on one gait cycle. The background subtraction method firstly use for binary moving object extraction and then base on it we continue detect the leg region, head region and get gait features (leg angle, leg swing amplitude). Another feature, walking speed, also can be detected after a gait cycle finished. And then, we compute the errors between calculated features and stored features for recognition. This method gives good results when we performed testing using indoor and outdoor landscape in both lateral, oblique view.

• Korean Journal of Remote Sensing
• /
• v.11 no.1
• /
• pp.47-64
• /
• 1995

In this paper, an algorithm that finds man-made structures in a praylevel aerial images is proposed to perform stereo matching. An extracted contour of buildings must have a high accuracy in order to get a good feature-based stereo matching result. Therefore this study focuses on the use of edge following in the original image rather than use of ordinary edge filters. The Algorithm is composed of two main categories; one is to find candidate regions in the whole image and the other is to extract exact contours of each building which each candidate region.. The region growing method using the centroid linkage method of variance value is used to find candidate regions of building and the contour line tracing algorithm based on an adge following method is used to extract exact contours. The result shows that the almost contours of building composed of line segments are extracted.

• Food Science and Preservation
• /
• v.4 no.1
• /
• pp.61-68
• /
• 1997

To enhance the utilization of garlic shoots as food material, the nutritional and volatile flavor com pounds were investigated for garlic shoots, both cold and warm region type garlic shoots. Proximate composition of cold and warm region type was as follows, respectively; crude protein 2%, crude lipid 0.4%, crude ash 1.1% and 1.5%, crude fiber 1.3% and 1.5%. The major fatty acids of 2 varieties of garlic shoots were linoleic, palmitic and linolenic acid, and their desaturation ratio of them was comparatively high, showing 73.7 and 66.8%, respectively. Free sugars were composed of glucose, sucrose, fructose, arabinose and sorbitol. In the total amino acid analysis, the major amino acids were glutamic acid and aspartic acid. The volatile flavor compounds of fresh garlic shoots extracted by hexane and Likens-Nikerson steam distillation apparatus were identified to be methyl-2-propenyl disulfide, diallyl disufide, propenyl propyl disulfide, di-2-propyl-trisulfide, 2-vinyl-1,3-dithiane, and 2-vinyl-4H-1,3-dithiin. Hexane was more effective than steam distillation for extraction of volatile components of garlic shoots.

• Annual Conference of KIPS
• /
• 2004.05a
• /
• pp.1641-1644
• /
• 2004

3차원 볼륨데이터에서 분할 대상영역의 밝기 값이 다양하면서 밝기 값이 유사한 영역과 인접한 경우 3차원 영역확장(region growing) 방법을 사용하여 영역을 분할하기 위해서는 영역확장의 중요한 요인인 동질성 기준 값의 적절한 선택이 요구된다. 본 논문에서는 영역 복셀(voxel)의 1차 미분 값의 크기인 기울기 크기(gradient magnitude)만으로 영역의 경계를 찾기가 쉽지않은 대상의 분할을 위해 볼륨데이터의 지역적인 밝기 값의 변화의 특징을 고려하면서 분할 대상영역의 복셀의 2차 미분(second partial derivation)을 행렬의 요소(element)로 갖는 Hessian 행렬의 고유치(eigenvalue)를 영역확장의 문턱치 결정에 이용하였다. 제안한 알고리즘은 3차원 영역확장의 결과에 가장 큰 영향을 미치는 적절한 문턱치의 선택으로 대상영역의 분할을 성공적으로 수행하여 3차원 영역확장의 단점을 보완하였다.