• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.1B
• /
• pp.1-7
• /
• 2008

In group location management, when a transportation system(TS) with multiple mobile subscribers(MSs) changes location area(LA), location management is performed by group location registration by TS, instead of individual location registrations by MSs. In previous works, although it is assumed that LA in group location management is the same as that in individual location management, it is not appropriate to assume the same sized LAs since MSs in a TS have different characteristics from MSs which are not in a TS from the aspect of the speed and aggregate call arrival rates. Thus, in this paper, we propose an efficient location management scheme based on individual and group location managements with different sized LAs, and the performance of the proposed scheme is analyzed from the aspect of signaling cost at the wireless interface. Results reveal that the proposed scheme outperforms the conventional scheme by selecting an appropriate sized LA for group location management.

• The KIPS Transactions:PartC
• /
• v.14C no.4
• /
• pp.359-364
• /
• 2007

Current researches on the overlay multicast mechanism in the mobile ad hoc network (MANET) maintain the network topology information of the dynamically changing MANET, which may cause severe overhead. In this paper, we propose a new overlay multicast mechanism, the region-based overlay multicast in MANET(ROME), using the geometric locations of group members. In ROME, the physical topology is divided into small regions and the scope of location updates of group members is limited to a single region. ROME provides scalability by using the coordinate of the center point of a destination region as the destination of a data packet instead of the list of member addresses of that region. Our simulation results show that ROME gives better performance in terms of the packet overhead than other schemes.

• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.27-34
• /
• 2004

This thesis proposes a face detection algorithm using the color and edge informations in color image. The proposed algorithm segments skin color by Cb and Cr in YCbCr coordinates. Then face candidate regions are made after morphological filtering and labeling. For the regions, the Sobel vortical operation and horizontal projection are performed in the Y luminance components. The peak value indicates the eye location. Similarly, the chin location is detected by the Sobel horizontal operation and horizontal projection. The computer simulation shows that the proposed method gains similar detection rates of previous method and prevent facial region from including neck by detection of chin.

• Annual Conference of KIPS
• /
• 2005.05a
• /
• pp.789-792
• /
• 2005

최근 급격히 발전한 휴대폰은 다양한 기능을 가지고 있다. 그 중 디지털 카메라의 기능을 겸비한 휴대폰은 디지털 카메라의 판매량을 앞서고 있고, 메가픽셀의 고화소 디카폰의 개발로 대중화가 더욱 가속화되고 있다. 카메라폰을 응용한 연구분야로는 생체인식기술을 적용할 수 있으며, 본 논문은 제약이 많은 휴대폰 환경에서 홍채인식기술을 적용하기 위한 휴대폰 카메라로 취득된 얼굴영상에서의 눈 영역을 검출하는 방법을 제안한다. 얼굴영상에서 눈은 피부나 머리카락보다 빛에 대한 반사율이 높아 각막에 specular reflection이 생기게 되고, 동공은 눈의 다른 지역에 비해 흑화소가 많다는 특징을 가지고 있다. 이러한 두 가지 특징을 이용하여 동공 후보 영역을 선정하였고, 선정된 이진영상에서 수평 프로파일과 수직 프로파일을 적용하여 동공 후보 영역을 줄이면서 동공의 중심 위치를 검출한다. 본 연구는 휴대폰 환경을 고려하였기 때문에 최소한의 메모리 사용과 적은 연산량을 목표로 하여 눈의 위치를 검출 한다. 실험 결과, 입력 영상 내에 일정크기의 동공영역이 존재할 경우 높은 눈 영역 추출 성공률을 보이며, 본 연구에서 제안한 알고리즘을 실제 휴대폰에서 수행한 결과 평균571.6ms의 시간이 소요됨을 알 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.97-100
• /
• 2013

In this paper, we propose a detection method of the character rather than cursive, containing many components of the vertical and horizontal direction in complex background image. The characters have many dense corners but the background has few sparse corners. So we use harris corner detector and cluster the corners by using the position of the detected corners for detecting character regions. To merge or filter character regions, we analysis a histogram of gray image of character regions. In each improved region, we compare histograms of R, G, B channels to detect characters.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.376-378
• /
• 2006

본 논문에서는 소동물 양전자방출단층촬영 영상(Positron Emission Tomography, PET) 내 종양영역을 자동분할하고 분할된 윤곽선주변의 기하학적 위험구간에 따른 종양의 형태특성을 분석하기 위한 방법을 제시한다. PET 영상내 검출된 종양영역의 신뢰성을 위해 위음성(False negative, FN) 및 위양성(False positive, FP)의 위험구간을 같이 제공하는 것이 필요하다. 따라서, 방사선 특이적 특성이 반영된 명암값을 기반으로 Fuzzy C-Means(FCM) 클러스터링을 수행하여 종양영역을 자동 분할한다. 분활된 종양영역의 위험구간은 클러스터 간 공유되는 영역의 소속값을 이용하여 위음성, 위양성을 계산한다. 또한, 임의의 소속값 임계치 변화를 통해 위험구간의 변화에 따른 종양의 형태적 특성변화를 관측한다. 이러한 지역적 변화의 관측을 통해 위험구간의 형태학적 위치를 판단할 수 있어 위험구간에 따른 추가적인 잔여 암의 위치 및 형태 파악을 용이하게 한다.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.81-86
• /
• 2003

In this paper, we propose the tracking method of moving object which use extracted object by difference between background image and target image in fixed domain. As a extraction method of object, calculate not pixel of full image but predefined some edge pixel of image to get a position of new object. Since the center area Is excluded from calculation, the extraction time is efficiently reduced. To extract object in the predefined area, get a starting point in advance and then extract size of width and height of object. Central coordinate is used to track moved object.

• Journal of the Institute of Convergence Signal Processing
• /
• v.13 no.2
• /
• pp.77-82
• /
• 2012

This paper presents a hardware-implemented face regions stabilization algorithm that stabilizes facial regions using the locations and sizes of human faces found by a face detection system. Face detection algorithms extract facial features or patterns determining the presence of a face from a video source and detect faces via a classifier trained on example faces. But face detection results has big variations in the detected locations and sizes of faces by slight shaking. To address this problem, the high frequency reduce filter that reduces variations in the detected face regions by taking into account the face range information between the current and previous video frames are implemented in addition to center distance comparison and zooming operations.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.405-412
• /
• 2012

After the spatial discrepancy between SLI(Street-Level Imagery) and vector map is removed by their conflation, the corresponding building regions can be found based on SLI parameters. The building region correspondence, however, is not perfect even after the conflation. This paper aims to improve the correspondence of building regions by region splitting of an SLI. Regions are initialized by the seed lines, projection of building objects onto SLI scene. First, sky images are generated by filtering, segmentation, and sky region detection. Candidates for split lines are detected by edge detector, and then images are splitted into building regions by optimal split lines based on color difference and sky existence. The experiments demonstrated that the proposed region splitting method had improved the accuracy of building region correspondence from 83.3% to 89.7%. The result can be utilized effectively for enhancement of SLI services.

• 한국ITS학회:학술대회논문집
• /
• 2002.11a
• /
• pp.210-213
• /
• 2002

차량 대기열 측정에 관한 연구는 효과적인 교통 통제를 위해서 필수적인 요소이다. 이를 위해 본 논문에서는 영역기반 영상처리를 이용한 차량 대기열 분석에 관한 방법을 제안한다. 도로 영상에서 영역을 설정하고 각 영역에서의 차량 검출방법을 통하여 차량 대기열의 길이를 계산하였다. 이때 차량의 검출은 영역 처리를 이용하였고 대기열 측정은 검출된 차량의 최종단 위치를 파악하여 계산하였다. 이러한 방법은 차량 통행량 분석에 이용하여 능동적 교통 신호 체계에 응용될 수 있다.