7,011 Hits in 3.1 sec

Learning dynamics for exemplar-based gesture recognition

A. Elgammal, V. Shet, Y. Yacoob, L.S. Davis
2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.  
This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems.  ...  The approach is based on representing each gesture as a sequence of learned body poses (exemplars).  ...  Conclusion The paper presented an approach for learning the dynamics for exemplar-based recognition systems and its application to gesture recognition.  ... 
doi:10.1109/cvpr.2003.1211405 dblp:conf/cvpr/ElgammalSYD03 fatcat:kvahqjuecjewxgjnqunrhcjqlq

Dynamic Arm Gesture Recognition Using Spherical Angle Features and Hidden Markov Models

Hyesuk Kim, Incheol Kim
2015 Advances in Human-Computer Interaction  
The AGR system learns the discrete Hidden Markov Model (HMM), an effective probabilistic graph model for gesture recognition, from the dynamic pose of the arm joints provided by the Kinect API.  ...  We introduce a vision-based arm gesture recognition (AGR) system using Kinect.  ...  In order to improve the efficiency of DTW-based gesture recognition, the system reduces the number of exemplars for each gesture class by employing AP and DTW algorithms (AP + DTW) in the training phase  ... 
doi:10.1155/2015/785349 fatcat:af4ydw53ofb6ljzthewya2xifm

Silhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds

Mohamed F. Abdelkader, Wael Abd-Almageed, Anuj Srivastava, Rama Chellappa
2011 Computer Vision and Image Understanding  
The proposed approaches not only are successfully able to represent the shape and dynamics of the different classes for recognition, but are also robust against some errors resulting from segmentation  ...  In the second approach, we use a graphical model approach similar to an exemplar-based hidden Markov model, where we cluster the gesture shapes on the shape space, and build non-parametric statistical  ...  Template-Based approach We ran our template-based approach for learning a template for each gesture and used that template for recognition.  ... 
doi:10.1016/j.cviu.2010.10.006 fatcat:foatyos5g5ck3ngwjbhuzdulsm

Hand Gesture Recognition and Voice Conversion for Hearing and Speech Aided Community

Divya K V, Harish E, Nikhil Jain D, Nirdesh Reddy B
2020 International Journal of Scientific Research in Computer Science Engineering and Information Technology  
Our aim is to design a system to help the person who trained the hearing impaired to communicate with the rest of the world using sign language or hand gesture recognition techniques.  ...  Sign language recognition (SLR) aims to interpret sign languages automatically by a computer in order to help the deaf communicate with hearing society conveniently.  ...  It usually takes a fusion of image processing and machine learning algorithms in order to build a fully-functioning computer vision system for hand gesture recognition.  ... 
doi:10.32628/cseit206346 fatcat:eldoh3louneklpeju2xfjaaq6u

Human gesture recognition using orientation segmentation feature on random rorest

Weihua Liu, Yangyu Fan, Tao Lei, Zhong Zhang
2014 2014 IEEE China Summit & International Conference on Signal and Information Processing (ChinaSIP)  
Traditional exemplar-based methods are vulnerable to gesture scaling and hand location translating.  ...  The results show that the performance of proposed method outweighs other state-of-art methods for gesture recognition.  ...  CONCLUSION A novel human gesture recognition algorithm based on random forest was proposed in this paper.  ... 
doi:10.1109/chinasip.2014.6889289 dblp:conf/chinasip/LiuFLZ14 fatcat:acbsigvvkvafrdbtue3frsmyvu

Dynamic hand gesture recognition: An exemplar-based approach from motion divergence fields

Xiaohui Shen, Gang Hua, Lance Williams, Ying Wu
2012 Image and Vision Computing  
Exemplar-based approaches for dynamic hand gesture recognition usually require a large collection of gestures to achieve high-quality performance.  ...  Besides, the average recognition time of our method for each gesture sequence is only 34.53 ms.  ...  The approaches to dynamic hand gesture recognition can be categorized into model-based methods and exemplar-based methods.  ... 
doi:10.1016/j.imavis.2011.11.003 fatcat:wxns4fcwb5bjlgnty7atolznze

A Novel Accelerometer-Based Gesture Recognition System

Ahmad Akl, Chen Feng, Shahrokh Valaee
2011 IEEE Transactions on Signal Processing  
For training, the system employs dynamic time warping as well as affinity propagation to create exemplars for each gesture while for testing, the system projects all candidate traces and also the unknown  ...  the other accelerometer-based gesture recognition systems available in the literature.  ...  To the best of our knowledge, our dictionary of gestures is the largest in published studies for accelerometer-based gesture recognition.  ... 
doi:10.1109/tsp.2011.2165707 fatcat:f4l7nf2h6rh3piwyvdtlkqjxyu

Use of Ecological Gestures in Soccer Games Running on Mobile Devices

Valere Plantevin, Bob-Antoine Jerry Menelas
2014 International Journal of Serious Games  
The system used for recognition of ecological gestures is also detailed. A primary study showed that proposed system can be exploited for real time gesture recognition on a mobile device.  ...  As in the case of Virtual Reality based systems, in order to be useful and efficient, these serious games need to be validated ecologically.  ...  They use Affinity Propagation and Dynamic Time Warping (DTW) to compute clusters on a learning set, each cluster defines by an exemplar.  ... 
doi:10.17083/ijsg.v1i4.48 fatcat:evzfzsfiqja3nojwoxhkwihqkq

Significance of Hand Gesture Recognition Systems in Vehicular Automation-A Survey

Jobin Francis, Anoop B K
2014 International Journal of Computer Applications  
Hand gesture recognition is of great importance for human computer interaction (HCI) because of its extensive applications in virtual reality and sign language recognition etc.  ...  Hand gesture recognition is a process of understanding and classifying meaningful movements by the human hands.  ...  The inexpensive depth cameras the Kinect sensors provide a valid base for gesture recognition.  ... 
doi:10.5120/17389-7931 fatcat:qmpgwijwuzdgncxxzywb6rztqa

What, Why, Where and How Do Children Think? Towards a Dynamic Model of Spatial Cognition as Action [chapter]

Marilyn Panayi
2012 Lecture Notes in Computer Science  
The model is considered as a hypothetical and dynamic construct for intervention, planning and design of interaction technology for neuro-atypical children's pedagogy and rehabilitation.  ...  A partial descriptive feature based model of Spatial Cognition in Action (SCA) is developed by the examination of children's embodied gestures that are rooted in action.  ...  Acknowledgements For child, staff, clinical, parental contributors to the original and subsequent study that generated the child gesture corpus and financial support see [1] and [2] .  ... 
doi:10.1007/978-3-642-34182-3_9 fatcat:ctji6jcy6vaslmfkkji6qc42ki

Real-time gesture recognition using deterministic boosting

R. Lockton, A. Fitzgibbon
2002 Procedings of the British Machine Vision Conference 2002  
Real-time performance is provided by a novel combination of exemplar-based classification and a new "deterministic boosting" algorithm which can allow for fast online retraining.  ...  A gesture recognition system which can reliably recognize single-hand gestures in real time on a 600Mhz notebook computer is described.  ...  Two important paradigms are (a) the learning of parametric models and (b) the recent emergence of exemplar-based strategies.  ... 
doi:10.5244/c.16.80 dblp:conf/bmvc/LocktonF02 fatcat:mr7hpm2rqfbpfcxsxnie3z27t4

Modified levenshtein distance for real-time gesture recognition

Clementine Nyirarugira, Hyo-Rim Choi, JunYoung Kim, Monson Hayes, TaeYong Kim
2013 2013 6th International Congress on Image and Signal Processing (CISP)  
In this paper, a real time dynamic gesture recognition method based on a modified Levenshtein distance is proposed.  ...  Experiments demonstrate realtime gesture recognition rates of 93.9% for gestures of variable speed.  ...  The DTW based recognition methods attempts to line up a given sequence to gestures templates. It is an exemplar based matching procedure.  ... 
doi:10.1109/cisp.2013.6745306 fatcat:spzgokwmr5akfitgoeobbpryvy

Local Frame Match Distance: A Novel Approach For Exemplar Gesture Recognition

Vassilis Athitsos, Christopher Conly, Radu Tudor Ionescu, Marius Popescu
2018 Zenodo  
To the best of our knowledge, KDA has never been used for exemplar-based gesture recognition.  ...  To the best of our knowledge, we are the first to use KDA for gesture recognition with exemplars.  ... 
doi:10.5281/zenodo.1159227 fatcat:ggvnrnkizreslcmfyaumdo4ajm

Recognizing actions by shape-motion prototype trees

Zhe Lin, Zhuolin Jiang, Larry S. Davis
2009 2009 IEEE 12th International Conference on Computer Vision  
A prototype-based approach is introduced for action recognition. The approach represents an action as a sequence of prototypes for efficient and flexible action matching in long video sequences.  ...  Experimental results demonstrate that our approach achieves recognition rates of 91.07% on a large gesture dataset (with dynamic backgrounds), 100% on the Weizmann action dataset and 95.77% on the KTH  ...  We would like to thank Weihua Zhang for helpful discussions.  ... 
doi:10.1109/iccv.2009.5459184 dblp:conf/iccv/LinJD09 fatcat:qjufoeyibngq7a7mxypkqap22a

Rhythmic interaction with a mobile device

Vuokko Lantz, Roderick Murray-Smith
2004 Proceedings of the third Nordic conference on Human-computer interaction - NordiCHI '04  
Dynamic Movement Primitives are used to learn the limit cycle behavior associated with the rhythmic gestures.  ...  We describe a rhythmic interaction mechanism for mobile devices. A PocketPC with a three degree of freedom linear acceleration meter is used as the experimental platform for data acquisition.  ...  SFI grant 00/PI.1/C067 and BRG project Continuous Gestural Interaction with Mobile devices.  ... 
doi:10.1145/1028014.1028029 dblp:conf/nordichi/LantzM04 fatcat:qgjwgau6szfvplog7nhvjtbrti
« Previous Showing results 1 — 15 out of 7,011 results