• Journal of Biosystems Engineering
• /
• 제24권5호
• /
• pp.431-438
• /
• 1999

The environmental control based on interactive thermoregulatory behavior for swine production has many advantages over the conventional temperature-based control methods. Therefore, this study was conducted to compare various feature selection methods using postural images of growing pigs under various environmental conditions. A color CCD camera was used to capture the behavioral images which were then modified to binary images. The binary images were processed by thresholding, edge detection, and thinning techniques to separate the pigs from their background. Following feature were used for the input patterns to the neural network ; \circled1 perimeter, \circled2 area, \circled3 Fourier coefficients (5$\times$5), \circled4 combination of (\circled1 ＋ \circled2), \circled5 combination of (\circled1 ＋ \circled3), \circled6 combination of (\circled2 ＋ \circled3), and \circled7 combination of (\circled1 ＋ \circled2 ＋ \circled3). Using the above each input pattern, the neural network could classify training images with the success rates of 96%, 96%, 96%, 100%, 100%, 96%, 100%, and testing images with those of 88%, 86%, 93%, 96%, 91%, 90%, 98%, respectively. Thus, the combination of perimeter, area and Fourier coefficients of the thinning images as neural network features gave the best performance (98%) in the behavioral classification.

• 대한기관식도과학회지
• /
• 제17권1호
• /
• pp.14-18
• /
• 2011

The diagnosis and treatment of early gastrointestinal cancers is the gastroenterologists' mission because of national cancer screening program in South Korea. The detection of early cancers is emphasized, because these were previously treated with surgical treatment can be currently cured with endoscopic treatment. Gastroenterologists who achieved at least on some level can make an exact diagnosis regardless of what type of endoscopy, but generally, there are some required conditions for an optimal diagnosis. First, clinically important lesions have to be detected easily. Second, the border and morphology of lesions have to be characterized easily. Third, lesions have to be diagnosed exactly. Precancers and early cancers are often subtle and can pose a challenge to gastroenterologists to visualize using standard white light endoscopy. The use of dye solutions aids the diagnosis of early gastrointestinal cancers, however, it is a quite cumbersome to use dye solutions all the time and the solution often bothers the exact observation by pooling into the depression or ulceration of the lesion. To overcome this weakness, newer endoscopes are now developed so called "image enhanced endoscopy" using optical and/or electronic methods such as narrow band imaging (NBI), autofluorescence imaging (AFI), i-scan, flexible spectral imaging color enhancement (FICE) and confocal endomicroscopy (CLE).

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권3호
• /
• pp.166-171
• /
• 2009

In recent years, video detection systems have been implemented in various infrastructures such as airport, public transportation, power generation system, water dam and so on. Recognizing moving objects in video sequence is an important problem in computer vision, with applications in several fields, such as video surveillance and target tracking. Segmentation and tracking of multiple vehicles in crowded situations is made difficult by inter-object occlusion. In the system described in this paper, the mean shift algorithm is firstly used to filter and segment a color vehicle image in order to get candidate regions. These candidate regions are then analyzed and classified in order to decide whether a candidate region contains a license plate or not. And then some characters in the license plate is recognized by using the fuzzy ARTMAP neural network, which is a relatively new architecture of the neural network family and has the capability to learn incrementally unlike the conventional BP network. We finally design a license plate recognition system using the mean shift algorithm and fuzzy ARTMAP neural network and show its performance via some computer simulations.

• 전자공학회논문지
• /
• 제54권1호
• /
• pp.88-95
• /
• 2017

본 논문에서는 웨이블릿 변환 영역에서 엔트로피 가중치와 웨버 대비 도를 이용한 세일리언시 검출 방법을 제안한다. 본 논문의 방법은 기존의 일반적인 방법과 마찬가지로 국부적인 세일리언시를 결정하는 상향식 검출과 전역적인 세일리언시를 구성하는 하향식 검출을 결합하는 구조를 가진다. 먼저, CIE Lab 컬러 영상에 대하여 웨이블릿 변환을 수행하고, 저주파 부밴드에 대하여 웨버 대비도 계산하고 이를 저주파 계수에 부가하여 전역 세일리언시를 구한다. 다음으로, 고주파 부밴드의 엔트로피를 이용한 가중치를 가우시안 필터에 적용하여 국부 세일리언시를 구한다. 마지막으로 국부 세일리언시와 전역 세일리언시의 비선형 결합을 통하여 최종 세일리언시를 검출한다. 제안 방법의 성능 평가를 위해 2개의 영상 데이터베이스에 대하여 모의실험을 수행하였다. 기존의 방법과 비교하여 본 논문의 방법은 우수한 세일리언시 검출 결과를 나타내었다.

• 한국멀티미디어학회논문지
• /
• 제9권2호
• /
• pp.160-171
• /
• 2006

본 논문에서는 복잡한 배경, 심한 조명 변화 등의 다양한 환경 변화에서도 얼굴을 정확히 검출하기 위하여 영역 분할을 이용한 얼굴 검출을 제안한다. 입력된 영상에서 배경요소들로, 인한 검출 오류를 줄이기 위하여 JSEG 방법을 사용하여 영상을 영역 단위로 분할한다. 분할된 각 영역에서 사전 정의된 피부색에 해당되는 픽셀들을 추출한다. 각 영역에서 추출된 픽셀들의 비율을 이용하여 얼굴 후보 영역을 결정한다. 그리고 결정된 얼굴 후보 영역에서 얼굴요소에 해당되는 눈과 눈썹이 위치 정보와 색상 정보를 이용하여 최종 얼굴 영역을 검출한다. 본 논문에서 제안한 방법을 이용하여 다양한 제약 조건을 지닌 영상들에 대하여 얼굴을 검출해본 결과, 배경이 복잡한 영상, 조명 변화가 심한 영상, 얼굴 크기가 다양한 영상, 얼굴이 다수 존재하는 영상들에서 좋은 검출 결과를 보여주었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.427-430
• /
• 2007

본 논문에서는 화재에 의한 인적물적 피해를 최소화하기 위하여 조기에 화재를 영상처리 기법을 이용하여 검출하는 방법을 제안한다. 인공조명으로 부터 화염을 판별하기 위해 화염의 고유한 색정보를 이용하여 화염후보영역을 판별하고 화염후보영역이 아닌 경우는 배경과 현재 프레임의 밝기차이와 채도를 측정하여 연기후보영역을 판별한다. 그러나 단순한 밝기 및 색체 정보만으로 화염이나 연기로 판별할 경우 오인식할 경우가 많아 화염 및 연기 후보영역에 대해 움직임을 측정한다. 각 후보영역에 대해 전형적인 움직임이 검출되면 최종적으로 화염인 경우는 활동성 정보를 이용하여 화염으로 판별하고 연기인 경우는 경계검출법을 적용하여 최종 연기 영역을 검출한다. 제안하는 방법에 대해 실제 CCTV 카메라의 영상신호에 적용한 시뮬레이션을 통해 효과적으로 화염과 연기를 동시에 검출할 수 있음을 확인하였다.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.49-56
• /
• 2020

Detecting shadows in images and restoring or removing them was a very challenging task in computer vision. Traditional researches used color information, edges, and thresholds to detect shadows, but there were errors such as not considering the penumbra area of shadow or even detecting a black area that is not a shadow. Deep learning has been successful in various fields of computer vision, and research on applying deep learning has started in the field of shadow detection and removal. However, it was very difficult and time-consuming to collect data for network learning, and there were many limited conditions for shooting. In particular, it was more difficult to obtain shadow data from buildings and satellite images, which hindered the progress of the research. In this paper, we propose a method for generating shadow data from buildings and satellites using Unity3D. In the virtual Unity space, 3D objects existing in the real world were placed, and shadows were generated using lights effects to shoot. Through this, it is possible to get all three types of images (shadow-free, shadow image, shadow mask) necessary for shadow detection and removal when training deep learning networks. The method proposed in this paper contributes to helping the progress of the research by providing big data in the field of building or satellite shadow detection and removal research, which is difficult for learning deep learning networks due to the absence of data. And this can be a suboptimal method. We believe that we have contributed in that we can apply virtual data to test deep learning networks before applying real data.

• 한국콘텐츠학회논문지
• /
• 제8권9호
• /
• pp.1-9
• /
• 2008

일반적으로 얼굴 추적 시 움직임에 강건한 Lucas-Kanade 추적 방법이 많이 사용된다. 그러나 얼굴이 회전되었을 경우, 정확한 얼굴 영역 검출이 어렵다. 따라서 본 논문에서는 이러한 문제점을 해결하기 위해 Lucas-Kanade 추적 방법에 평가함수를 도입하여 회전에 강건한 자동 얼굴 영역 검출 및 추적 방법을 제안하였다. 얼굴영역은 색상정보를 이용하여 자동으로 추출하였으며, Harris 코너 추출 알고리즘으로 특징점을 추출하였다. 폐색된 특징점을 구분하기위하여 특징점마다 기존 특징점과 새로운 특징점과의 차이 값을 계산한다. 만약, 특징점이 폐색되었을 경우, 잡음을 제거하기 위하여 제거하며 특징점의 개수가 일정 임계값 이하일 경우, 얼굴 영역을 다시 검출하였다. 실험결과를 통하여 얼굴 영역이 회전되었을 경우, 기존의 Lucas-Kanade 추적 방법보다 더 좋은 결과를 확인하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2005년도 추계종합학술대회
• /
• pp.1261-1264
• /
• 2005

In this paper, a new intelligent moving target tracking and surveillance system basing on the pan/tilt-embedded stereo camera system is suggested and implemented. In the proposed system, once the face area of a target is detected from the input stereo image by using a YCbCr color model and then, using this data as well as the geometric information of the tracking system, the distance and 3D information of the target are effectively extracted in real-time.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.372-375
• /
• 2003

The incidence of blindness resulting from diabetic retinopathy has significantly increased despite the intervention of insulin to control diabetes mellitus. Early signs are microaneurysms, exudates, intraretinal hemorrhages, cotton wool patches, microvascular abnormalities, and venous beading. Advanced stages include neovascularization, fibrous formations, preretinal and vitreous microhemorrhages, and retinal detachment. Microaneurysm count is important because it is an indicator of retinopathy progression. The purpose of this paper is to apply data mining to detect diabetic retinopathy patterns in routine fundus fluorescein angiography. Early symptoms are of principal interest and therefore the emphasis is on detecting microaneurysms rather than vessel tortuosity. The analysis does not involve image-recognition algorithms. Instead, mathematical filtering isolates microaneurysms, microhemorrhages, and exudates as objects of disconnected sets. A neural network is trained on their distribution to return fractal dimension. Hausdorff and box counting dimensions grade progression of the disease. The field is acquired on fluorescein angiography with resolution superior to color ophthalmoscopy, or on patterns produced by physical or mathematical simulations that model viscous fingering of water with additives percolated through porous media. A mathematical filter and neural network perform the screening process thereby eliminating the time consuming operation of determining fractal set dimension in every case.