An Effective Dynamic Gesture Recognition System Based on the Feature Vector Reduction for SURF and LCS

Barros, Pablo; Júnior, Nestor T. M.; Bisneto, Juvenal M.; Fernandes, Bruno; Bezerra, Byron Leite Dantas; Fernandes, Stênio

doi:10.1007/978-3-642-40728-4_52

Cited by 7 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to classify the depth CIPBR feature vectors, a hybridization between two classifiers that generated good results in the literature of dynamic gesture classification is proposed: DTW and HMM [ 5 , 28 , 29 ].…”

Section: Hybrid Approach For Gesture Recognition With a Depth Mapmentioning

confidence: 99%

“…There are three types of gesture recognition systems: based on devices attached to the body [ 3 ], based on gesture tracking [ 4 ] and based on computer vision techniques [ 5 ]. The first category uses sensors, such as wearable devices with accelerometers and markers, to capture a gesture and its corresponding movement.…”

Section: Introductionmentioning

confidence: 99%

“…In the last step of gesture recognition of systems based on computer vision techniques, a classifier is trained using the extracted descriptors in order to recognize the gestures [ 24 ]. Barros et al [ 5 , 25 ] presented a gesture recognition system that achieved higher classification rates in comparison to other methods using dynamic time warping (DTW) [ 26 ] and hidden Markov model (HMM) [ 27 ] classifiers. Kim et al [ 28 ] also used DTW as a classifier to recognize gestures captured by a depth sensor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps

Santos¹,

Fernandes²,

Bezerra³

2015

Sensors

View full text Add to dashboard Cite

The hand is an important part of the body used to express information through gestures, and its movements can be used in dynamic gesture recognition systems based on computer vision with practical applications, such as medical, games and sign language. Although depth sensors have led to great progress in gesture recognition, hand gesture recognition still is an open problem because of its complexity, which is due to the large number of small articulations in a hand. This paper proposes a novel approach for hand gesture recognition with depth maps generated by the Microsoft Kinect Sensor (Microsoft, Redmond, WA, USA) using a variation of the CIPBR (convex invariant position based on RANSAC) algorithm and a hybrid classifier composed of dynamic time warping (DTW) and Hidden Markov models (HMM), called the hybrid approach for gesture recognition with depth maps (HAGR-D). The experiments show that the proposed model overcomes other algorithms presented in the literature in hand gesture recognition tasks, achieving a classification rate of 97.49% in the MSRGesture3D dataset and 98.43% in the RPPDI dynamic gesture dataset.

show abstract

Section: Hybrid Approach For Gesture Recognition With a Depth Mapmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps

Santos¹,

Fernandes²,

Bezerra³

2015

Sensors

View full text Add to dashboard Cite

show abstract

“…To solve this, two approaches is adapted in this work. At first one, Particle Swarm Optimization [23] chose the better feature vectors size and the selector algorithm proposed by Barros et al [6] receives PSO size output and choose the candidate features for this vectors.…”

Section: Classifier Module Based On Hmmmentioning

confidence: 99%

“…There are three different categories for systems based in human gesture recognition: systems based on the hand gesture captured by gloves or external sensors [4], system which make the device tracking to generate a gesture path [5]. The last category use a camera to capture the gesture in images and extract features from it using computer vision techniques to interpret the gesture [6], [7].…”

Section: Introductionmentioning

confidence: 99%

A Dynamic Gesture Recognition System based on CIPBR Algorithm

et al. 2014

View full text Add to dashboard Cite

Dynamic gesture recognition has been studied actually for it big application in several areas such as virtual reality, games and sign language. But some problems have to be solved in computer applications, such as response time and classification rate, which directly affect the real-time usage. This paper proposes a novel algorithm called Convex Invariant Position Based on Ransac which improved the good results in dynamic gesture recognition problem. The proposed method is combined with a adapted PSO variation to reduce features and a HMM and three DTW variations as classifiers.

show abstract

RETRACTED ARTICLE: Machine learning based sign language recognition: a review and its research frontier

Elakkiya

2020

J Ambient Intell Human Comput

View full text Add to dashboard Cite

An Effective Dynamic Gesture Recognition System Based on the Feature Vector Reduction for SURF and LCS

Cited by 7 publications

References 11 publications

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps

HAGR-D: A Novel Approach for Gesture Recognition with Depth Maps

A Dynamic Gesture Recognition System based on CIPBR Algorithm

RETRACTED ARTICLE: Machine learning based sign language recognition: a review and its research frontier

Contact Info

Product

Resources

About