Clustering Method Evaluation for Hidden Markov Model Based Real-Time Gesture Recognition

Prasad, Jay Shankar; Nandi, Gora Chand

doi:10.1109/artcom.2009.99

Cited by 12 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the feature extraction technique is concerned about the gray scale images so the background was chosen dark. Every ISL gesture implies some class or word which could be captured by waving both hands in a very appropriate manner [7]. We created repository of training and testing samples with huge number of images (sequence of images) of 22 specific kind of ISL class/word under various light illumination condition as shown in Fig.…”

Section: Generation Of Isl Video Training Samplesmentioning

confidence: 99%

“…The hand trajectory is utilized as a feature vector for DTW [2], hand contour [3], combination of color, motion and hand position is utilized for hand gesture recognition [4,7]. The hand skin color information is used for extracting the histogram [5] .The histogram of the local direction of edges in an image contributes an important feature [9,10].…”

Section: Feature Extractionmentioning

confidence: 99%

“…The classification approach is based on the hand gestures trajectory, hand shape and hand motion [6]. HMM would be used as a robust classifier for gesture recognition [7,8]. This paper demonstrates the statistical techniques for recognition of ISL gestures in real time which comprises of both the hands.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recognition of Isolated Indian Sign Language Gesture in Real Time

Nandy

Prasad

Mondal

et al. 2010

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

Abstract. Indian Sign Language (ISL) consists of static as well as dynamic hand gestures for communication among deaf and dumb persons. Most of the ISL gestures are produced using both hands. A video database is created and utilized which contains several videos, for a large number of signs. Direction histogram is the feature used for classification due to its appeal for illumination and orientation invariance. Two different approaches utilized for recognition are Euclidean distance and K-nearest neighbor metrics.

show abstract

Section: Generation Of Isl Video Training Samplesmentioning

confidence: 99%

Section: Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of Isolated Indian Sign Language Gesture in Real Time

Nandy

Prasad

Mondal

et al. 2010

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…These commonly include Hidden Markov Models (Moni & Ali, 2009;Wilson & Bobick, 2000;Yamato, Ohya, & Ishii, 1992), neural network approaches (Kleinsmith, 2004;Touzet, 1997;Varkonyi-Koczy & Tusor, 2011), and clustering (Prasad & Nandi, 2009;Schlomer, Poppinga, Henze, & Boll, 2008). Our approach utilizes the Growing Neural Gas (GNG) algorithm (Angelopoulou, Psarrou, Garcia-Rodriguez, & Gupta, 2010;Fritzke, 1995;Stergiopoulou & Papamarkos, 2006) in order to effect clustering of gesture representations; to act as an associative memory for robotic response (Touzet, 1997;Yanik et al, 2012); and to track a moving distribution of input patterns (Holmstrom, 2002).…”

Section: Key Components Of Our Human-robot Communication Loopmentioning

confidence: 99%

Design and Evaluation of a Nonverbal Communication Platform between Assistive Robots and their Users

Threatt

Green

Brooks

et al. 2013

Distributed, Ambient, and Pervasive Interactions

View full text Add to dashboard Cite

Assistive robotics will become integral to the everyday lives of a human population that is increasingly mobile, older, urban-centric and networked. The overwhelming demands on healthcare delivery alone will compel the adoption of assistive robotics. How will we communicate with such robots, and how will they communicate with us? This research makes the case for a relatively "artificial" mode of nonverbal human-robot communication that is non-disruptive, non-competitive, and non-invasive human-robot communication that we envision will be willingly invited into our private and working lives over time. This research proposes a nonverbal communication (NVC) platform be conveyed by familiar lights and sounds, and elaborated here are experiments with our NVC platform in a rehabilitation hospital. This NVC is embedded into the Assistive Robotic Table (ART), developed within our lab, that supports the well-being of an expanding population of older adults and those with limited mobility. The broader aim of this research is to afford people robot-assistants that exist and interact with them in the recesses, rather than in the foreground, of their intimate and social lives. With support from our larger research team, I designed and evaluated several alternative modes of nonverbal robot communication with the objective of establishing a nonverbal, human-robot communication loop that evolves with users and can be modified by users. The study was conducted with 10-13 clinicians-doctors and occupational, physical, and speech therapists-at a local rehabilitation This work would not have been made possible without Jessica Merino. Jessica is more than a colleague and friend-she has become family. Thank you for your efforts, your insights, your guidance, and your willingness to always push me and this work to its greatest possible conclusion.

show abstract

“…The Markov process was named after Markov. Markov process is loss of modern probability theory branch of stochastic process theory in a class, it has been widely used in many fields, such as remote control, control, biology, social sciences and other fields of science and technology, and in these areas has shown an important role [4][5]. Hidden Markov Model (HMM) has a lot of mature the method is an exact matching time-varying data technology has been widely applied in the research such as speech recognition, biological signal analysis, pattern recognition, fault diagnosis.…”

Section: Hidden Markov Modelmentioning

confidence: 99%

Evaluation and Prediction of Sport Status Based on Variable Step Size Hidden Markov Model

Gong¹,

Liu²

2017

dtetr

View full text Add to dashboard Cite

Abstract. In order to early accurately assess and predict the exercise state of sports, based on Hidden Markov Model, the autocorrelation coefficient of selection and prediction of future events was significantly related to state step according to the history of the state of the event, the weight of a future state prediction based on information entropy was established as the time-varying forgetting factor; the time-varying forgetting factor was introduced, and the time varying tracking factor was established by the active window mechanism, transition probability matrix was adjusted by the relationship between the state information of event history and difference step state of transition probability matrix. Thus, the state predicting method based on variable step recursive Hidden Markov Model was established. Finally, through specific examples, this method can accurately assess and predict the exercise state of sports and improve analysis accuracy and ability.

show abstract

Clustering Method Evaluation for Hidden Markov Model Based Real-Time Gesture Recognition

Cited by 12 publications

References 10 publications

Recognition of Isolated Indian Sign Language Gesture in Real Time

Recognition of Isolated Indian Sign Language Gesture in Real Time

Design and Evaluation of a Nonverbal Communication Platform between Assistive Robots and their Users

Evaluation and Prediction of Sport Status Based on Variable Step Size Hidden Markov Model

Contact Info

Product

Resources

About