• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.85-88
• /
• 2011

Fuzzy C-Means (FCM) 알고리듬은 가장 널리 사용되는 군집화 알고리듬 중 하나로 다양한 응용 분야에서 사용되고 있다. 하지만 FCM은 여러 가지 문제점을 가지고 있으며 초기 원형 설정이 그 중 하나이다. FCM은 국부 최적해에 수렴하므로 초기 원형 설정에 따라 클러스터링 결과가 달라진다. 이 논문에서는 이러한 FCM의 초기 원형 설정 문제를 개선하기 위하여 커널밀도 추정 (kernel density estimation) 기법을 활용하는 방법을 제안한다. 제안한 방법에서는 먼저 커널 밀도 추정을 수행한 후 밀도가 높은 지역에 클러스터의 초기 원형을 설정하고 원형이 설정된 영역의 밀도를 감소시키는 과정을 반복함으로써 효율적으로 초기 원형을 설정할 수 있다. 제안된 방법이 일반적으로 사용되는 무작위 초기화 방법에 비해 효율적이라는 사실은 실험결과를 통해 확인할 수 있다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.9 no.1 s.24
• /
• pp.99-108
• /
• 2006

In this paper, we analyzed the characteristics of emitter geolocation coverage area within which the emitter lies with a specified probability based on the LOBs(Line of Bearing) of sensors. Stansfield and MSD algorithms were applied to calculate BPE(Best Point Estimate), EEP(Elliptical Error Probable) and CEP(Circular Error Probable), They used the weighting factors composed of ${\sigma}_{Phi}$ (bearing error), QF(quality factor), $P_{e}$ (probability being inside) to optimize the performance. The characteristics of EEP was investigated in the change of them and those of CEP was analyzed based on the deployment of sensors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1659-1664
• /
• 2011

Fuzzy C-Means (FCM) is one of the most widely used clustering algorithms and has been used in many applications successfully. However, FCM has some shortcomings and initial prototype selection is one of them. As FCM is only guaranteed to converge on a local optimum, different initial prototype results in different clustering. Therefore, much care should be given to the selection of initial prototype. In this paper, a new initialization method for FCM using kernel density estimation (KDE) is proposed to resolve the initialization problem. KDE can be used to estimate non-parametric data distribution and is useful in estimating local density. After KDE, in the proposed method, one initial point is placed at the most dense region and the density of that region is reduced. By iterating the process, initial prototype can be obtained. The initial prototype such obtained showed better result than the randomly selected one commonly used in FCM, which was demonstrated by experimental results.

• Korean Journal of Plant Tissue Culture
• /
• v.28 no.2
• /
• pp.109-112
• /
• 2001

Sieve element area and sieve pore formed generally from plasmodesmata. Sieve pore formed by the fusion of several tiny vesicles with plasmodesmata, or those with cell wall after the destruction of special region of newly formed cell wall or those finally with circular arranged form from tissure culture of Streptanthus. The tiny vesicles were produced from dispersed nucleolus or heterochromatin. The sieve area and sieve pore formed from tissue cultured cells were shown round tube form similar to those of natural plants. Sieve area and sieve pore were produced by various methods, and it suggested that the basic materials of the construction of sieve pore originated from the vesicles.

• Journal of Korea Multimedia Society
• /
• v.9 no.2
• /
• pp.172-188
• /
• 2006

Sensor localization is one of the fundamental problems in wireless sensor networks. Previous localization algorithms can be classified into two categories, the GGB (Global Geometry-Based) approaches and the LGB (Local Geometry-Based). In the GGB approaches, there are a fixed set of reference nodes of which the coordinates are pre-determined. Other nodes determine their positions based on the distances from the fixed reference nodes. In the LGB approaches, meanwhile, the reference node set is not fixed, but grows up dynamically. Most GGB algorithms assume that the nodes are deployed in a convex shape area. They fail if either nodes are in a concave shape area or there are obstacles that block the communications between nodes. Meanwhile, the LGB approach is vulnerable to the errors in the distance estimations. In this paper, we propose new localization algorithms to cope with those two limits. The key technique employed in our algorithms is to determine, in a fully distributed fashion, if a node is in the line-of-sight from another. Based on the technique, we present two localization algorithms, one for anchor-based, another for anchor-free localization, and compare them with the previous algorithms.

• The Journal of the Acoustical Society of Korea
• /
• v.10 no.6
• /
• pp.82-100
• /
• 1991

본 연구에서는 회전톱날에서 발생하는 공기소음원 규명의 실현가능성을 검토하였다. 음향인텐시 티법은 3차원 선도, 인벤시티 벡터에너지선도, 동고선도 등의 표현에 유용한 장점을 갖고 있다. 근거리 음장 거동에 대한 추정, 주파수영역에서의 벡터 또는 스칼라 음향인텐시티는 소음원규명의목적으로 사 용되는 측정기법이다. 결과에 따르면 난류는 원형톱날의 이 부근에 나타나며, 톱날의 변동압력 측정에서 와류구조의 영향에 대한 근거는 측정된 음향인텐시티에 의해 도출된다. 도한 회전속도가 증가함에 딸k, 상호작용은 도플러현상을 일으키는 중요한 소음메타니즘이 될 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.10a
• /
• pp.754-757
• /
• 2003

In Oriental medicine, the shape of collarette that formed with position in iris of patients often used by health diagnotcian to grasp health condition. In this paper, we present method that effectively extract collarette that exist in Iris image. After proposed method detert iris area using circular edge detector, derides boundary candidate point through radial line search and threshold value establishment. And boundary candidate line is treated to use nearest neighbor calculation at each boundary candidate point, finally extracts collarette through linear interpolation. As a result of experimenting about iris images, We Confirmed that can be used as assistant tool of diagnostic system that can presume state of ventriculus of human body.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.212-215
• /
• 2010

본 논문은 카메라 영상을 통해 사용자의 손동작을 인식하여 가상의 물체를 증강시키는 인터페이스를 제안한다. 사용자는 영상의 일부를 원형으로 그려주는 특정한 손동작을 취하여 영역을 선택하고 시스템은 이를 인식하여 물체를 증강 시킨다. 손동작을 인식하기 위하여 먼저 손 외곽선을 찾아낸 후, 찾아낸 외곽선의 곡률을 계산하여 손가락의 위치를 알아낸다. 알아낸 손가락의 상대적인 위치와 개수를 이용하여 손동작을 구분한다. 또한 적은 연산량으로도 안정적으로 물체를 증강 시킬 수 있도록 이전 프레임에서 자세추정에 사용된 특징점들을 이용하여 현재 프레임에서 필요한 인라이어를 찾아 낼 수 있는 방법을 제시한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.2
• /
• pp.160-167
• /
• 2016

This paper reports a localization method of a mobile robot using ceiling image. The ceiling has landmarks which are not distinguishablefrom one another. The location of every landmark in a map is given a priori while correspondence is not given between a detected landmark and a landmark in the map. Only the initial pose of the robot relative to the landmarks is given. The method uses particle filter approach for localization. Along with estimating robot pose, the method also associates a landmark in the map to a landmark detected from the ceiling image. The method is tested in an indoor environment which has circular landmarks on the ceiling. The test verifies the feasibility of the method in an environment where range data to walls or to beacons are not available or severely corrupted with noise. This method is useful for localization in a warehouse where measurement by Laser range finder and range data to beacons of RF or ultrasonic signal have large uncertainty.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.19-27
• /
• 2021

In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods.