• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제27권1호
• /
• 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.

• 한국멀티미디어학회논문지
• /
• 제8권3호
• /
• pp.336-344
• /
• 2005

본 논문에서는 개선된 동적 윤곽선 모델을 이용하여 높은 시간 해상도를 가진 EBT 폐 영상에서 폐실질 영역을 검출하였다. 기존의 동적 윤곽선 모델에서 물체의 경계선을 얻기 위한 방법은 에너지 최소화 형태로서 내부에너지와 외부에너지를 조절함으로써 검출되어 질 수 있다. 그러나 이 방법에서는 초기화 지정 문제나 내부 에너지의 탄성과 구부러짐의 특성 때문에 요면 영역에 대하여 빈약한 수렴성 등의 문제점들을 가지고 있다. 본 논문에서는 이러한 요면 문제들을 해결하면서 폐실질 영역으로 수렴시키기 위해 윤곽선 상에 있는 제어 점들을 이웃 점들과 함께 각각 수직 이등분선 상의 한점에 이동시킴으로써 내부 에너지를 조절하고, 입력받은 영상의 에너지를 나타내는 외부에너지와 함께 에너지를 최소화시킴으로써 원하는 폐실질 영역에 윤곽선이 수렴할 수 있도록 하였다. 요면 영역에 대한 수렴은 이런 내부에너지에 의해 효과적으로 구현 될 수 있었고, 하나의 초기 윤곽선에서 다중 물체들도 검출될 수 있어서 의료 영상에서의 폐실질 영역 검출에 효과적으로 적용될 수 있음을 확인할 수 있었다.

• 대한의용생체공학회:의공학회지
• /
• 제26권6호
• /
• pp.357-363
• /
• 2005

Active contour models have been extensively used to segment, match, and track objects of interest in computer vision and image processing applications, particularly to locate object boundaries. With conventional methods an object boundary can be extracted by controlling the internal energy and external energy based on energy minimization. However, this still leaves a number of problems, such as initialization and poor convergence in concave regions. In particular, a contour is unable to enter a concave region based on the stretching and bending characteristic of the internal energy. Therefore, this study proposes a method that controls the internal energy by moving the local perpendicular bisector point of each control point on the contour, and determines the object boundary by minimizing the energy relative to the external energy. Convergence at a concave region can then be effectively implemented as regards the feature of interest using the internal energy, plus several objects can be detected using a multi-detection method based on the initial contour. The proposed method is compared with other conventional methods through objective validation and subjective consideration. As a result, it is anticipated that the proposed method can be efficiently applied to the detection of the pulmonary parenchyma region in medical images.

• ETRI Journal
• /
• 제33권4호
• /
• pp.547-557
• /
• 2011

This study presents an approach for extracting boundaries of various buildings, which have concave boundaries, inner yards, non-right-angled corners, and nonlinear edges. The approach comprises four steps: building point segmentation, boundary tracing, boundary grouping, and regularization. In the second and third steps, conventional algorithms are improved for more accurate boundary extraction, and in the final step, a new algorithm is presented to extract nonlinear edges. The unique characteristics of airborne light detection and ranging (LIDAR) data are considered in some steps. The performance and practicality of the presented algorithm were evaluated for buildings of various shapes, and the average omission and commission error of building polygon areas were 0.038 and 0.033, respectively.