• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.6
• /
• pp.238-245
• /
• 2013

Gesture recognition has been widely one of the research areas for natural user interface. This paper presents a novel gesture recognition method using tree classification and multiclass SVM(Support Vector Machine). In the learning step, 3D trajectory of human gesture obtained by a Kinect sensor is classified into the tree nodes according to their distributions. The gestures are resampled and we obtain the histogram of the chain code from the normalized data. Then multiclass SVM is applied to the classified gestures in the node. The input gesture classified using the constructed tree is recognized with multiclass SVM.

• Smart Media Journal
• /
• v.4 no.1
• /
• pp.16-24
• /
• 2015

In this paper, we propose a method for multi-touch tracking using MRF-based particle filters and gesture likelihood estimation Each touch (of one finger) is considered to be one object. One of frequently occurring issues is the hijacking problem which means that an object tracker can be hijacked by neighboring object. If a predicted particle is close to an adjacent object then the particle's weight should be lowered by analysing the influence of neighboring objects for avoiding hijacking problem. We define a penalty function to lower the weights of those particles. MRF is a graph representation where a node is the location of a target object and an edge describes the adjacent relation of target object. It is easy to utilize MRF as data structure of adjacent objects. Moreover, since MRF graph representation is helpful to analyze multi-touch gestures, we describe how to define gesture likelihoods based on MRF. The experimental results show that the proposed method can avoid the occurrence of hijacking problems and is able to estimate gesture likelihoods with high accuracy.

• Journal of Korea Game Society
• /
• v.11 no.6
• /
• pp.103-113
• /
• 2011

In this paper, we propose gesture recognition based 3D Serious Games to prevent dementia. These games are designed to enhance the effect of preventing dementia by helping increase brain usage and physical activities of users by the entire body gesture recognition. The existing cameras used for gesture recognition technology are limited in terms of recognition ratio and operation range. For more stable recognition of the body gestures, we recognized users with a 3D depth camera, obtained joint data of users, and analyzed joint motions to recognize gestures of the body. Game contents were designed to practice memory, reasoning, calculation, and spatial recognition focusing on the atrophy of brain cells as a major cause of dementia. Game results of each user were saved and analyzed to measure how their recognition skills improved.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.723-730
• /
• 2013

This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.580-582
• /
• 2012

본 논문에서는 얼굴검출을 통한 실시간 피부색 모델링과 거리정보를 결합하여 손 영역을 검출하고 손 움직임에 따른 방향 및 원 제스처 인식을 위한 규칙 기반 인식방법을 제안한다. 기존과는 달리 손좌표를 사용하는 대신 기존 프레임과 현재 프레임에서의 손 좌표 차이를 이용하여 제스처 구간을 설정하고 자연스러운 제스처 동작에서의 속도변화를 고려할 수 있도록 한다. 실험 데이터는 5명을 대상으로 4방향과 원을 포함하여 총 5가지 제스처를 10회씩 실행하여 획득하였다. 이들 데이터에 대한 인식 실험에서 97%의 인식률을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.393-395
• /
• 2012

다양한 스마트 기기의 출현과 함께 정보보호를 위한 보다 강건한 사용자 인증 시스템에 대한 요구도 증대되고 있다. 하지만 스마트 기기별로 호환성을 유지하면서도 사용자 인증을 수행하기 위해서는 각 기기에서 공통적으로 제공되는 센서의 활용이 필요하며, 영상 기반 다중 생체 인식에 기반을 둔 사용자 인증 시스템은 이에 대한 대안이 될 수 있다. 본 논문에서는 전통적으로 사용자 인증에 사용되고 있는 얼굴 인식과 더불어 영상 기반의 제스처 인식을 함께 사용함으로서 호환성을 유지하면서도 강건한 사용자 인증 시스템을 제안하였다. 그리고 제스처 인식 데이터베이스의 하나인 ChaLearn 데이터에 적용하여 인식 성능을 평가하였다. 그 결과 기존의 스마트 기기에서 가속도계, 자이로스코프 또는 터치 패널에 의한 제스처 인식이 아니라 영상 기반의 제스처 인식을 사용하여 호환성의 확보뿐만 아니라 사용자 인증 성능 또한 개선할 수 있음을 확인하였다.

• Journal of Advanced Navigation Technology
• /
• v.17 no.2
• /
• pp.247-254
• /
• 2013

The task of 3D gesture recognition for controlling equipments is highly challenging due to the propagation of 3D smart TV recently. In this paper, the AdaBoost algorithm is applied to 3D gesture recognition by using Kinect sensor. By tracking time interval trajectory of hand, wrist and arm by Kinect, AdaBoost algorithm is used to train and classify 3D gesture. Experimental results demonstrate that the proposed method can successfully extract trained gestures from continuous hand, wrist and arm motion in real time.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.621-625
• /
• 2010

This paper presents a hand motion tracking method for hand gesture interface using a camera in mobile devices such as a smart phone and PDA. When a camera moves according to the hand gesture of the user, global optical flows are generated. Therefore, robust hand movement estimation is possible by considering dominant optical flow based on histogram analysis of the motion direction. A continuous hand gesture is segmented into unit gestures by motion state estimation using motion phase, which is determined by velocity and acceleration of the estimated hand motion. Feature vectors are extracted during movement states and hand gestures are recognized at the end state of each gesture. Support vector machine (SVM), k-nearest neighborhood classifier, and normal Bayes classifier are used for classification. SVM shows 82% recognition rate for 14 hand gestures.

• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1337-1346
• /
• 2005

In this paper, we describe an algorithm which can automatically recognize human gesture for Human-Robot interaction. In early works, many systems for recognizing human gestures work under many restricted conditions. To eliminate these restrictions, we have proposed the method that can represent 3D and 2D gesture information simultaneously, APM. This method is less sensitive to noise or appearance characteristic. First, the feature vectors are extracted using APM. The next step is constructing a gesture space by analyzing the statistical information of training images with PCA. And then, input images are compared to the model and individually symbolized to one portion of the model space. In the last step, the symbolized images are recognized with HMM as one of model gestures. The experimental results indicate that the proposed algorithm is efficient on gesture recognition, and it is very convenient to apply to humanoid robot or intelligent interface systems.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1037-1043
• /
• 2006

본 논문에서는 유비쿼터스 컴퓨팅 오피스 환경에서 가장 직관적인 HCI 수단인 손 제스처를 사용하여 대형 스크린 상의 응용 프로그램들을 쉽게 제어할 수 있는 시스템을 제안한다. 손 제스처는 손 영역의 정보, 손 중심점의 위치 변화값과 손가락 형상을 이용하여 시스템 제어에 필요한 종류들을 미리 정의해 둔다. 먼저 효율적으로 손 영역 획득을 위해 적외선 카메라를 사용하여 연속된 영상을 획득한다. 획득된 영상 프레임으로부터 구조적 템플레이트 매칭 방법을 사용하여 손의 중심(centroid) 및 손가락끝(fingertip)을 검출한다. 인식과정에서는 양손의 Euclidean distance와 손가락 형상 정보를 이용하여 미리 정의된 제스처와 비교하여 인식을 행한다. 본 논문에서 제안한 비전 기반 hand gesture 제어 시스템은 인간과 컴퓨터의 상호작용을 이해하는데 많은 이점을 제공할 수 있다. 실험 결과를 통해 본 논문에서 제안한 방법의 효율성을 입증한다.