• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.421-424
• /
• 1999

Automatic human face detection in a complex background is one of the difficult problems In this paper. we propose an effective automatic face detection system that can locate the face region in natural scene images when the system is used as a pre-processor of a face recog- nition system. We use two natural and powerful visual cues, the color and the human head shape. The outline of the human head can be generally described as being roughly elliptic in nature. In the first step of the proposed system, we have tried the approach of fitting the best Possible ellipse to the outline of the head In the next step, the method based on the human skin color space by selecting flesh tone regions in color images and histogramming their r(＝R/(R＋G＋B)) and g(＝G/R＋G＋B)) values. According to our experiment. the proposed system shows robust location results

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.27 no.1
• /
• pp.37-55
• /
• 2023

In this paper we propose a new algorithm for detecting and counting flowers in a complex background based on digital images. The algorithm mainly includes the following parts: edge contour extraction of flowers, edge contour determination of overlapped flowers and flower counting. We use a contour detection technique in Computer Vision (CV) to extract the edge contours of flowers and propose an improved algorithm with a concave point detection technique to find accurate segmentation for overlapped flowers. In this process, we first use the polygon approximation to smooth edge contours and then adopt the second-order central moments to fit ellipse contours to determine whether edge contours overlap. To obtain accurate segmentation points, we calculate the curvature of each pixel point on the edge contours with an improved Curvature Scale Space (CSS) corner detector. Finally, we successively give three adaptive judgment criteria to detect and count flowers accurately and automatically. Both experimental results and the proposed evaluation indicators reveal that the proposed algorithm is more efficient for flower counting.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• Publications of The Korean Astronomical Society
• /
• v.30 no.2
• /
• pp.401-403
• /
• 2015

We present the results of the analysis of FLS 1718+59, a galaxy-galaxy gravitational lens system in the Spitzer First Look Survey (FLS) field. A background galaxy ($z_s=0.245$) is severely distorted by a nearby elliptical galaxy ($z_l=0.08$), via gravitational lensing. The system is analysed by several methods, including surface brightness fitting, gravitational lens modeling, and spectral energy distribution fitting. From Galfit and Ellipse we measure basic parameters of the galaxy, such as the effective radius and the average surface brightness within it. gravlens yields the total mass inside the Einstein radius ($R_{Ein}$), and MAGPHYS gives us an estimate of the stellar mass inside $R_{Ein}$. By comparing these parameters, we confirm that the lens galaxy is an elliptical galaxy on the Fundamental Plane and calculate the stellar mass fraction inside $R_{Ein}$, and discuss the results with regards to the initial mass function.

• Journal of Korea Multimedia Society
• /
• v.15 no.11
• /
• pp.1273-1283
• /
• 2012

In this paper, vision-based positioning algorithm for melon harvesting robot is presented. RGB value of the input image was converted into HSI value then, melon area was extracted after performing the binarization using HUE value. After morphological filtering was applied to remove noise, outermost boundary points were obtained using border following and convex hull method. Elliptical fitting for melons was perform by the RANSAC algorithm, the center point of ellipse, the length of the short and long axis, and rotation angle were obtained. We verified the effectiveness of the proposed method by various simulation experiments and confirmed actual feasibility of the proposed method by applying to the real melon.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.37 no.3
• /
• pp.259-266
• /
• 2013

An automated cell tracking system is used to automatically analyze and track the changes in cell behavior in time-lapse cell images acquired using a microscope with a cell culture. Clustering is the partial overlapping of neighboring cells in the process of cell change. Separating clusters into individual cells is very important for cell tracking. In this study, we proposed an algorithm for separating clusters by using ellipse fitting based on a direct least square method. We extracted the contours of clusters, divided them into line segments, and then produced their fitted ellipses using a direct least square method for each line segment. All of the fitted ellipses could be used to separate their corresponding clusters. In experiments, our algorithm separated clusters with average precisions of 91% for two overlapping cells, 84% for three overlapping cells, and about 73% for four overlapping cells.

• Journal of Astronomy and Space Sciences
• /
• v.22 no.4
• /
• pp.363-376
• /
• 2005

To study the effects of giant population on dynamical substructures of the central region of NGC 7006, we examine the radial variations of ellipticity and position angle on By stellar photometry using ellipse fitting technique. Total variations of ellipticity and position angle lie in the range $0.02\~0.06\;and\;-10^{\circ}+90^{\circ}$, respectively, from the center out to three times the half light radius. Our ellipse fitting results, after removing giant populations, show that the apparent central dynamical substructures of NGC 7006 are mainly affected by red giant, horizontal branch stars. On the contrary, the contribution of light from subgiant stars to the inner dynamical substructure seems to be insignificant.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.461-464
• /
• 2000

본 논문에서는 복잡한 배경과 조명의 영향과 그리고 얼굴의 크기가 변화하는 경우에도 주어진 영상으로부터 얼굴을 검출하는 새로운 효율적인 방법을 제안한다. 정면 얼굴의 경계선이 타원과 유사한 형태를 가지며 얼굴을 수직으로 이등분하는 직선을 기준으로 얼굴의 좌우 외곽선은 반사 대칭 (reflection symmetry) 의 조건을 만족한다. 이러한 반사 대칭의 조건을 허프 (Hough) 변환과 유사한 타원 모델링에 결합하여 주어진 영상에서 얼굴을 검출한다. 얼굴이 포함된 다양한 영상에서 실험을 통하여 제안한 얼굴 검출방법의 타당성을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.184-187
• /
• 2011

셀 트래킹의 목적은 셀의 이동(translocation), 분할(mitosis), 통합(fusion), 아포토시스(apoptosis), 셀의 모양 변형, 셀들 간의 상호 작용 등을 포함하는 모든 셀의 행동들을 분석하기 위한 것이다. 셀은 시간이 경과함에 따라 새롭게 나타나기도, 죽기도 하며 한 개 이상의 셀이 부분적으로 겹쳐 클러스터를 형성하기도 하고 클러스터는 다시 여러 개의 셀로 분리되기도 한다. 본 연구에서는 현미경으로부터 얻은 이미지에서 셀 트래킹을 위한 이미지 처리 방법과 오목 정점을 이용하여 셀과 클러스터를 구분하여 계수하는 방법을 제시한다. 또한 타원 근사법(ellipse fitting)을 통해 클러스터를 몇 개의 셀로 분리하기 위한 방법을 제시하고 결과를 분석한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.598-600
• /
• 2002

영상에서 타원을 추출하는 것은 얼굴 인식, 홍채 인식과 같은 컴퓨터 비전분야에서 인식할 영역을 찾는 방법으로 상당히 유용하게 사용된다. 본 논문에서는 기존의 퍼지 C-means 기법이 초기의 클러스터 개수와 중심 값에 따라서 결과가 민감하다는 단점을 보완한 개선된 퍼지 C-means 기법을 타원 추출에 적용한다. 이것은 영상 분할(Segmentation)로부터 후보 초기 클러스터 개수 및 초기 클러스터 중심을 결정하는 방법으로서 본 논문에서는 이 기법으로 영상 클러스터링을 수행하여 타원 영역 추출에 필요한 타원 후보 영역의 최소 인접 사각형(Minimum Enclosed Rectangle)을 찾아낸다. 이렇게 찾아진 최소 인접 사각형에 대해서 면적에 맞는 초기 타원들을 영역 내에 설정한 뒤 적합도(fittness)검사를 기반으로 한 타원 검증을 실시하고 적합도가 높은 영역을 타원 영역으로 추출한다.