• Journal of Fashion Business
• /
• v.7 no.4
• /
• pp.78-92
• /
• 2003

The upper-body characteristics of the right-handed and the left-handed are examined and compared through 1-dimensional measurement and 2-dimensional measurement. The results were as follows: 1. According to 1-dimensional measurement results, the clearest differences were seen in girth items rather than height or length items. In particular, hand girth, lower arm girth, and upper arm girth were bigger on the left side in the left-handed group and the right side in the right-handed group. This is thought to be relevant to the arm muscles frequently used. 2. According to 2-dimensional measurement results, significant differences appeared in the females of the left-handed group: shoulder point among width items. In the right-handed group, some differences of significance were shown in females (shoulder point, rear armpit point, and B.P. point among width items) and males (front neck point among extreme vertical distance items). In summary, the body type characteristics of the left-handed and the right-handed reveal great differences in the items related to arm length and arm girth. In other words, the sleeve and shoulder patterns production based on the right-handed don't rightly reflect the somatotype characteristics of the left-handed. In addition, in the cases of athletes, laborers, and the disabled who frequently use particular muscles or parts of the body, this sort of research in the patterns is consistently needed in order to reflect the size differences in girth items in upper body.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.847-850
• /
• 2016

뇌-컴퓨터 인터페이스(Brain-Computer Interface: BCI) 기술의 중요성 및 활용도가 증대됨으로써 EEG(electroencephalogram: EEG)기반의 사용자 인터페이스에 대한 개발 및 연구가 활발히 진행되고 있다. 그러나 뇌파 발생 훈련이 되어 있지 않은 사용자는 EEG 기반의 사용자 인터페이스를 사용하기가 어렵다. 따라서 본 논문에서는 향후 뇌파 훈련을 위한 시뮬레이터를 개발하고자, 그 전단계로 사용자에게서 공통적으로 정확도가 높게 측정되는 채널 및 특징점을 비교, 분석 하였다. 피험자 3명의 왼손 동작 상상과 오른손 동작 상상으로 발생된 EEG 생체신호로부터 ERD/ERS를 확인하고, 8개의 특징점을 추출하여 SVM 분류 알고리즘을 기반으로 정확도를 측정하였으며, ${\mu}$대역 채널 AF4, F4에서의 특징 MAV에서 가장 우수한 성능을 보였다.

• Journal of Digital Convergence
• /
• v.11 no.7
• /
• pp.157-163
• /
• 2013

In this paper, we propose a vision and depth information based real-time hand gesture interface method using finger joint estimation. For this, the areas of left and right hands are segmented after mapping of the visual image and depth information image, and labeling and boundary noise removal is performed. Then, the centroid point and rotation angle of each hand area are calculated. Afterwards, a circle is expanded at following pattern from a centroid point of the hand to detect joint points and end points of the finger by obtaining the midway points of the hand boundary crossing and the hand model is recognized. Experimental results that our method enabled fingertip distinction and recognized various hand gestures fast and accurately. As a result of the experiment on various hand poses with the hidden fingers using both hands, the accuracy showed over 90% and the performance indicated over 25 fps. The proposed method can be used as a without contacts input interface in HCI control, education, and game applications.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.343-345
• /
• 2012

오늘날 우리는 생활속에서 여러 디지털기기들을 사용하고 있다. 새로운 종류의 여러 디지털기기들이 나타났지만 기존에 사용하던 입력장치의 틀에 얽매여 있다. 키보드, 마우스, 리모콘, 터치패널 등처럼 항상 별도의 컨트롤러를 지녀야 하는 불편함에서 벗어나지 못하고 있다. 이런 이유로 최근에 별도의 컨트롤러 없이 사용자의 움직임을 인식하여 다양한 기능을 수행할 수 있는 키넥트에 대한 관심이 높아지고 있다. 본 연구에서는 키넥트에서 인식하는 손의 움직임 정보를 인식하여 키보드와 마우스를 비롯한 기존 입력장치의 임무를 대신하는 것을 목표로 한다. 키보드 모드는 화면상에 가상의 버튼들을 배치한 후 손의 위치 정보가 버튼안에 있을 때 이벤트를 발생시키는 방법으로 구현한다. 마우스모드는 오른손으로 포인터를 이동하고, 왼손으로 보조 조작이 가능하도록 구현한다. 이 연구를 통해 손이 자유롭지 못하거나 정적이지 못한 상황에서 물리적인 도구가 필요 없는 간단한 조작이 가능하다.

• Journal of Korea Game Society
• /
• v.12 no.5
• /
• pp.79-88
• /
• 2012

In this paper, we present a real-time hand pose recognition method to provide an intuitive user interface through hand poses or movements without a keyboard and a mouse. For this, the areas of right and left hands are segmented from the depth camera image, and noise removal is performed. Then, the rotation angle and the centroid point of each hand area are calculated. Subsequently, a circle is expanded at regular intervals from a centroid point of the hand to detect joint points and end points of the finger by obtaining the midway points of the hand boundary crossing. Lastly, the matching between the hand information calculated previously and the hand model of previous frame is performed, and the hand model is recognized to update the hand model for the next frame. This method enables users to predict the hidden fingers through the hand model information of the previous frame using temporal coherence in consecutive frames. As a result of the experiment on various hand poses with the hidden fingers using both hands, the accuracy showed over 95% and the performance indicated over 32 fps. The proposed method can be used as a contactless input interface in presentation, advertisement, education, and game applications.