• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.06a
• /
• pp.284-285
• /
• 2013

Kinect를 통해 Color영상과 Depth영상을 받아온 후, 사람과 사람의 스켈레톤이 검출되도록 했다. 스켈레톤이 검출되면 머리 위치를 중심으로 얼굴 유효영역을 만들고, 효율적인 얼굴 검출로 사용자 인식이 가능하도록 했다. 스켈레톤 검출 및 추적을 통해, 4가지 감정에 대해 제스쳐를 정의했으며, 각 감정에 따른 제스쳐를 취했을 때 정의한 감정이 인식되는지 실험했다. 실험 결과, 제스쳐를 통한 감정 인식 성공률이 86~88% 나왔으며, 이 제스쳐 인식이 다른 감정인식 방법과 융합될 필요가 있다.

• Asian Pacific Journal of Cancer Prevention
• /
• v.17 no.11
• /
• pp.4869-4873
• /
• 2016

Colonoscopy is currently the best technique available for the detection of colon cancer or colorectal polyps or other precursor lesions. Computer aided detection (CAD) is based on very complex pattern recognition. Local binary patterns (LBPs) are strong illumination invariant texture primitives. Histograms of binary patterns computed across regions are used to describe textures. Every pixel is contrasted relative to gray levels of neighbourhood pixels. In this study, colorectal polyp detection was performed with colonoscopy video frames, with classification via J48 and Fuzzy. Features such as color, discrete cosine transform (DCT) and LBP were used in confirming the superiority of the proposed method in colorectal polyp detection. The performance was better than with other current methods.

• Proceedings of the Korea Contents Association Conference
• /
• 2015.05a
• /
• pp.303-304
• /
• 2015

최근 차량을 이용한 범죄가 점점 증가하고 있고, 그로인해 범죄 차량의 식별 또한 많은 사람들의 관심을 받고 있다. 본 논문에서는 차량 식별을 위해 방범용 CCTV 영상을 이용한다. 차량 방범을 위한 CCTV 이미지 속에서 얻을 수 있는 차량 내 정보는 크게 번호판, 모델, 크기, 색상 등 여러 가지가 있는데, 본 논문에서는 그중 하나인 색상을 인식하는 방법에 대하여 제안한다. 기존에는 여러 가지 색상공간을 이용하여 추출하는 방법을 많이 사용했는데, 단순히 색상공간만으로는 무채색의 차량 추출이 어렵다. 이를 보완하기 위해 HSI 색상공간과 히스토그램의 분산을 분석하는 방법을 제안한다. 이를 이용하여 차량을 보다 정확한 색상별로 검색하는 것이 가능하며, 또한 차량 외의 다른 물체들의 색상 인식에도 응용 가능하다.

• International Journal of Contents
• /
• v.12 no.3
• /
• pp.42-46
• /
• 2016

Kinetic typography is technology such as color, scale, position of the letter changes dynamically with time and it communicates information with aesthetics and originality. The purpose of this study is to identify the design factors in the formativeness of Hangul and present and implement the interaction design method of unique Hangul kinetic typography based on the scientific structure of Hangul. We implemented the Hangul kinetic typography system, which varies in sizes and motion directions according to a viewer's movement and exhibited in a media art event. To do this, we used a viewer's skeleton information on typography synchronization. The results indicated that Hangul kinetic typography has potential not only as a means to communicate with viewers but also as a medium to show the artistic value of Hangul.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2373-2378
• /
• 2005

An emotion detection algorithm using frontal facial image is presented in this paper. The algorithm is composed of three main stages: image processing stage and facial feature extraction stage, and emotion detection stage. In image processing stage, the face region and facial component is extracted by using fuzzy color filter, virtual face model, and histogram analysis method. The features for emotion detection are extracted from facial component in facial feature extraction stage. In emotion detection stage, the fuzzy classifier is adopted to recognize emotion from extracted features. It is shown by experiment results that the proposed algorithm can detect emotion well.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.4
• /
• pp.379-384
• /
• 2009

A human gaze detection and tracing method is importantly required for HMI(Human-Machine-Interface) like a Human-Serving robot. This paper proposed a novel three-dimension (3D) human gaze estimation method by using a face recognition, an orientation estimation and SVMs (Support Vector Machines). 2,400 images with the pan orientation range of $-90^{\circ}{\sim}90^{\circ}$ and tilt range of $-40^{\circ}{\sim}70^{\circ}$ with intervals unit of $10^{\circ}$ were used. A stereo camera was used to obtain the global coordinate of the center point between eyes and Gabor filter banks of horizontal and vertical orientation with 4 scales were used to extract the facial features. The experiment result shows that the error rate of proposed method is much improved than Liddell's.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.563-566
• /
• 1999

The functional diagnosis instrument should be preceded first to both the accurate selection of exact acupoint and discrimination. so the measuring and stimulating method are improved to SPAC pattern to evaluate impedance existed in the body. As a result, the resistance factor between skin and probe, the dipolization of cell was reduced so that the judgement of acupoint is advanced. After extraction of optimization parameter of SPAC pattern which the high discrimination efficiency and the lowest affection on the human body is controlled by using microprocessor to enhance conviction. The discrimination efficiency was confirmed by meridian visualization system. Also mechanism of probe was improved to increase efficiency of image recognition processing. The image of discriminated acupoint with probe is obtained by using a camera, the location on the tip of probe is recognized and processed. And then these are converted to virtual color by proportional to measuring current level of scan point on skin.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.593-596
• /
• 1999

In this paper, we propose an image retrieval system using the MBCM(Modified Borda Count method) in CME(Combining Multiple Experts). It combines color-, shape- and texture-based retrieval sub-systems. CME method can complementarily combine results of each retrieval system, which uses different features. There are some problems when the Borda count method in pattern recognition is applied to image retrieval. Thus, we propose a modified Borda count method to solve these problems. In the experiment, our method reduces false positive errors and produces better results than that of each retrieval module that uses only one feature.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.43-45
• /
• 2011

본 논문은 동영상 내 삽입된 자막을 문자인식이 가능하도록 문자영역을 이루는 화소를 추출하는 방법을 제안한다. 최초 자막영상을 통계학적 방법을 이용하여 색상극성을 결정한다. 이 후 색상극성에 따른 잡음제거 방법을 명암값기반과 형태학적기반으로 달리한다. 제안된 방법은 각 색상결정에 따른 적합한 잡음제거를 수행함으로서 추출된 화소들이 이루는 문자영역의 영상을 이용하여 문자인식을 수행하였을 때 기존방법보다 높은 문자인식률을 보였다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.2
• /
• pp.374-382
• /
• 2007

Robot mobility and intelligence become more important for robots to be used in various fields other than automation. The main purpose of providing mobility to a robot is to extend the robot's manipulability. In this paper, we introduce a small humanoid robot that can autonomously play golf as an example of incorporating robot intelligence, mobility, and manipulability. The robot has 12 degrees of freedom for legs and has various basic walking patterns. It can move to a desired position and change orientation by combining the basic waking patterns. The robot has a color CCD camera and can extract coordinates of the objects in the environments. The small humanoid robot has 8 degrees of freedom for arms and can play golf autonomously with two kinds of dexterous swing motions. Kinematic analysis of the robot arms, vision data processing for the recognition of the environments, algorithm for playing robotic golf have been performed or proposed. The experimental results show that the robot can play golf autonomously.