A novel finger and hand pose estimation technique for real-time hand gesture recognition

Zhou, Yimin; Jiang, Guolai; Lin, Yaorong

doi:10.1016/j.patcog.2015.07.014

Cited by 133 publications

(51 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The finger was modeled as a cylindrical object according to the parallel edge feature of the finger, and then the finger was extracted from the prominent edge. 31 After the hand was segmented, a radial projection algorithm was used to identify the gesture. Xavier et al presented an algorithm for obtaining the fingertip position from depth maps by using a feature called radial distribution that not only describes the gesture from the overall, 32 but also locates the fingertips from local information.…”

Section: Gesture Classificationmentioning

confidence: 99%

“…Zhou et al proposed a high-level feature extraction method by extracting the fingers from the parallel edge characteristic of hand and then utilizing a radial projection algorithm to locate each finger for recognizing the gestures. 31 Fang et al proposed an electromyography (EMG) feature named differential root mean square (DRMS), 36 which takes the relationship between neighboring EMG channels into account, and the proposed system can recognize four different hand motions. Pisharady et al proposed a novel approach for hand posture and face recognition based on fuzzy-rough sets, 37 and features of the image are extracted using the computational model of the ventral stream of visual cortex.…”

Section: Research Progressmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Hand Gesture Recognition Based on High-Level Features

Wang

2018

Int. J. Human. Robot.

View full text Add to dashboard Cite

Gesture recognition plays an important role in human–computer interaction. However, most existing methods are complex and time-consuming, which limit the use of gesture recognition in real-time environments. In this paper, we propose a static gesture recognition system that combines depth information and skeleton data to classify gestures. Through feature fusion, hand digit gestures of 0–9 can be recognized accurately and efficiently. According to the experimental results, the proposed gesture recognition system is effective and robust, which is invariant to complex background, illumination changes, reversal, structural distortion, rotation, etc. We have tested the system both online and offline which proved that our system is satisfactory to real-time requirements, and therefore it can be applied to gesture recognition in real-world human–computer interaction systems.

show abstract

Section: Gesture Classificationmentioning

confidence: 99%

Section: Research Progressmentioning

confidence: 99%

A Novel Hand Gesture Recognition Based on High-Level Features

Wang

2018

Int. J. Human. Robot.

View full text Add to dashboard Cite

show abstract

“…The past few years have seen a rapid improvement in the design and development of advanced and sophisticated means of Human Computer Interaction (HCI). Though the range of HCI techniques for basic tasks is still dominated by traditional input methods like the keyboard and mouse, or touch based systems like touch pads, Hand Gesture Interaction (HGI) is gaining popularity [1] as an attractive alternative-especially in gaming, virtual reality and medical applications. With the advance of Vision based Hand Gesture Recognition (HGR), users can communicate with computers without physically touching them, just as one would communicate naturally with another.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of segmentation algorithms for hand gesture recognition

Subramaniam

2018

IJET

View full text Add to dashboard Cite

The gestures presented in diverse backgrounds have to be accurately processed and segmented, for it to be classified precisely by the hand gesture recognition system. This study compares performance of the proposed Image Segmentation Algorithm with a standard Canny Edge Detection Algorithm by comparing the statistical values of the features obtained from the feature extraction stage, thus validating the importance of having a robust preprocessing stage for the hand gestures. The proposed algorithm uses Non-local Mean filter for noise removal and then an improved Global Swarm Optimization based Canny edge detection for extracting the edges. Features are extracted using two dimensional Multi-resolution Discrete Wavelet Transform (2D-DWT) combined with Gray-level Co-occurrence Matrix. The efficiency of the proposed Image Segmentation Algorithm is evaluated using Radial Basis Function Neural Network as the classifier.

show abstract

“…Target classification algorithms include Dynamic Time Warping, Hidden Markov model (HMM), Random Forest, Adaptive Boosting (AdaBoost), and so on [ 19 , 20 , 21 , 22 , 23 ]. The Dynamic Time Warping (DTW) algorithm allows two temporal sequences to be aligned in terms of length, and also allows similarities between them to be measured.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Gesture Recognition with a Terahertz Radar Based on Range Profile Sequences and Doppler Signatures

Zhi

Cao

2017

Sensors

View full text Add to dashboard Cite

The frequency of terahertz radar ranges from 0.1 THz to 10 THz, which is higher than that of microwaves. Multi-modal signals, including high-resolution range profile (HRRP) and Doppler signatures, can be acquired by the terahertz radar system. These two kinds of information are commonly used in automatic target recognition; however, dynamic gesture recognition is rarely discussed in the terahertz regime. In this paper, a dynamic gesture recognition system using a terahertz radar is proposed, based on multi-modal signals. The HRRP sequences and Doppler signatures were first achieved from the radar echoes. Considering the electromagnetic scattering characteristics, a feature extraction model is designed using location parameter estimation of scattering centers. Dynamic Time Warping (DTW) extended to multi-modal signals is used to accomplish the classifications. Ten types of gesture signals, collected from a terahertz radar, are applied to validate the analysis and the recognition system. The results of the experiment indicate that the recognition rate reaches more than 91%. This research verifies the potential applications of dynamic gesture recognition using a terahertz radar.

show abstract

A novel finger and hand pose estimation technique for real-time hand gesture recognition

Cited by 133 publications

References 32 publications

A Novel Hand Gesture Recognition Based on High-Level Features

A Novel Hand Gesture Recognition Based on High-Level Features

Performance comparison of segmentation algorithms for hand gesture recognition

Dynamic Gesture Recognition with a Terahertz Radar Based on Range Profile Sequences and Doppler Signatures

Contact Info

Product

Resources

About