• 스마트미디어저널
• /
• 제9권1호
• /
• pp.23-29
• /
• 2020

This paper presents an approach for dynamic hand gesture recognition by using algorithm based on 3D Convolutional Neural Network (3D_CNN), which is later extended to 3D Residual Networks (3D_ResNet), and the neural network based key frame selection. Typically, 3D deep neural network is used to classify gestures from the input of image frames, randomly sampled from a video data. In this work, to improve the classification performance, we employ key frames which represent the overall video, as the input of the classification network. The key frames are extracted by SegNet instead of conventional clustering algorithms for video summarization (VSUMM) which require heavy computation. By using a deep neural network, key frame selection can be performed in a real-time system. Experiments are conducted using 3D convolutional kernels such as 3D_CNN, Inflated 3D_CNN (I3D) and 3D_ResNet for gesture classification. Our algorithm achieved up to 97.8% of classification accuracy on the Cambridge gesture dataset. The experimental results show that the proposed approach is efficient and outperforms existing methods.

• 대한인간공학회지
• /
• 제31권4호
• /
• pp.533-540
• /
• 2012

Objective: This paper targets a framework of a hand gesture based interface design. Background: While a modeling of contact-based interfaces has focused on users' ergonomic interface designs and real-time technologies, an implementation of a contactless interface needs error-free classifications as an essential prior condition. These trends made many research studies concentrate on the designs of feature vectors, learning models and their tests. Even though there have been remarkable advances in this field, the ignorance of ergonomics and users' cognitions result in several problems including a user's uneasy behaviors. Method: In order to incorporate compatibilities considering users' comfortable behaviors and device's classification abilities simultaneously, classification-oriented gestures are extracted using the suggested human-hand model and closed-loop classification procedures. Out of the extracted gestures, the compatibility-oriented gestures are acquired though human's ergonomic and cognitive experiments. Then, the obtained hand gestures are converted into a series of hand behaviors - Handycon - which is mapped into several functions in a mobile device. Results: This Handycon model guarantees users' easy behavior and helps fast understandings as well as the high classification rate. Conclusion and Application: The suggested framework contributes to develop a hand gesture-based contactless interface model considering compatibilities between human and device. The suggested procedures can be applied effectively into other contactless interface designs.

• 한국멀티미디어학회논문지
• /
• 제19권5호
• /
• pp.874-880
• /
• 2016

The gesture classification has been applied to many fields. But it is not efficient in the environment for game interface with low specification devices such as mobile and tablet, In this paper, we propose a effective way for realistic game interface using k-nearest neighbors algorithm for gesture classification. It is time consuming by realtime rendering process in game interface. To reduce the process time while preserving the accuracy, a reconstruction method to minimize error between training and test data sets is also proposed. The experimental results show that the proposed method is better than the conventional methods in both accuracy and time.

• 로봇학회논문지
• /
• 제3권2호
• /
• pp.81-90
• /
• 2008

While increasing demand of the service for the disabled and the elderly people, assistive technologies have been developed rapidly. The natural signal of human such as voice or gesture has been applied to the system for assisting the disabled and the elderly people. As an example of such kind of human robot interface, the Soft Remote Control System has been developed by HWRS-ERC in $KAIST^[1]$. This system is a vision-based hand gesture recognition system for controlling home appliances such as television, lamp and curtain. One of the most important technologies of the system is the hand gesture recognition algorithm. The frequently occurred problems which lower the recognition rate of hand gesture are inter-person variation and intra-person variation. Intra-person variation can be handled by inducing fuzzy concept. In this paper, we propose multivariate fuzzy decision tree(MFDT) learning and classification algorithm for hand motion recognition. To recognize hand gesture of a new user, the most proper recognition model among several well trained models is selected using model selection algorithm and incrementally adapted to the user's hand gesture. For the general performance of MFDT as a classifier, we show classification rate using the benchmark data of the UCI repository. For the performance of hand gesture recognition, we tested using hand gesture data which is collected from 10 people for 15 days. The experimental results show that the classification and user adaptation performance of proposed algorithm is better than general fuzzy decision tree.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(3)
• /
• pp.121-124
• /
• 2000

In this paper, we propose a pen gesture recognition system for user interface in multimedia terminal which requires fast processing time and high recognition rate. It is realtime and interaction system between graphic and text module. Text editing in recognition system is performed by pen gesture in graphic module or direct editing in text module, and has all 14 editing functions. The pen gesture recognition is performed by searching classification features that extracted from input strokes at pen gesture model. The pen gesture model has been constructed by classification features, ie, cross number, direction change, direction code number, position relation, distance ratio information about defined 15 types. The proposed recognition system has obtained 98% correct recognition rate and 30msec average processing time in a recognition experiment.

• 전자공학회논문지
• /
• 제50권6호
• /
• pp.238-245
• /
• 2013

제스처 인식은 자연스러운 사용자 인터페이스를 위해 활발히 연구되는 중요한 분야이다. 본 논문에서는 키넥트 카메라로부터 입력되는 사용자의 3차원 관절(joint) 정보를 해석하여 제스처를 인식하는 방법이 제안된다. 대상으로 하는 제스처의 분포 특성에 따라 분류 트리를 설계하고 입력 패턴을 분류한다. 그리고 제스처를 리샘플링 및 정규화 하여 일정한 구간으로 나누고 각 구간의 체인코드 히스토그램을 추출한다. 트리의 각 노드별로 분류된 제스처에 다중 클래스 SVM(Multiclass Support Vector Machine)를 적용하여 학습한다. 이후 입력 데이터를 구성된 트리로 분류한 다음, 학습된 다중 클래스 SVM을 적용하여 제스처를 분류한다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.518-520
• /
• 2021

본 논문에서는 텍스트 분류에 사용된 textNAS를 다변수 시계열 데이터에 적용 가능하도록 수정하여 이를 통한 손동작 인식 방법을 제안한다. 이를 사용하면 다변수 시계열 데이터 분류를 통한 행동 인식, 감정 인식, 손동작 인식 등 다양한 분야에 적용 가능하다. 그리고 분류에 적합한 딥러닝 모델을 학습을 통해 자동으로 찾아줘 사용자의 부담을 덜어주며 높은 성능의 클래스 분류 정확도를 얻을 수 있다. 손동작 인식 데이터셋인 DHG-14/28과 Shrec'17 데이터셋에 제안한 방법을 적용하여 기존의 모델보다 높은 클래스 분류 정확도를 얻을 수 있었다. 분류 정확도는 DHG-14/28의 경우 98.72%, 98.16%, Shrec'17 14 class/28 class는 97.82%, 98.39%를 얻었다.

• 한국멀티미디어학회논문지
• /
• 제16권12호
• /
• pp.1393-1402
• /
• 2013

Hand gesture is one of the most popular communication methods in everyday life. In human-computer interaction applications, hand gesture recognition provides a natural way of communication between humans and computers. There are mainly two methods of hand gesture recognition: glove-based method and vision-based method. In this paper, we propose a vision-based hand gesture recognition method using Kinect. By using the depth information is efficient and robust to achieve the hand detection process. The finger labeling makes the system achieve pose classification according to the finger name and the relationship between each fingers. It also make the classification more effective and accutate. Two kinds of gesture sets can be recognized by our system. According to the experiment, the average accuracy of American Sign Language(ASL) number gesture set is 94.33%, and that of general gestures set is 95.01%. Since our system runs in real-time and has a high recognition rate, we can embed it into various applications.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2008년도 학술대회 1부
• /
• pp.517-521
• /
• 2008

Hand motion classification problem is considered as basis for sign or gesture recognition. We promote optical flow as main feature extracted from images sequences to simultaneously segment the motion's area by its magnitude and characterize the motion' s directions by its orientation. We manage the flow orientation histogram as motion descriptor. A motion is encoded by concatenating the flow orientation histogram from several frames. We utilize simple histogram matching to classify the motion sequences. Attempted experiments show the feasibility of our method for hand motion localization and classification.

• 한국콘텐츠학회논문지
• /
• 제13권4호
• /
• pp.64-72
• /
• 2013

본 연구에서는 다차원의 데이터 인식에 유리한 SVM을 이용한 동적 동작인식 알고리즘을 제안한다. 우선, Kinect 비디오 프레임에서 동작의 시작과 끝을 찾아 의미있는 동작 프레임을 분할하고, 프레임 수를 동일하게 정규화시킨다. 정규화된 프레임에서 인체 모델에 기반한 인체 부위의 위치와 부위 사이의 관계를 이용한 동작 특징을 추출하여 동작인식을 수행한다. 동작인식기인 C-SVM는 각 동작에 대해 positive 데이터와 negative 데이터로 구성된 학습 데이터로 학습된다. 최종 동작 선정은 각 C-SVM의 결과값 중 가장 큰 값을 갖는 동작으로 한다. 제안하는 동작인식 알고리즘은 플래시 구연동화에서 더 나아가 유아가 능동적으로 구연동화에 참여할 수 있도록 고안된 체감형 동화 콘텐츠에 동작 인터페이스로 적용되었다.