Real-time fingertip localization conditioned on hand gesture classification

Suau, Xavier; Alcoverro, Marcel; Lopez-Mendez, Adolfo; Ruiz-Hidalgo, Javier; Casas, Josep R.

doi:10.1016/j.imavis.2014.04.015

Cited by 29 publications

(11 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

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%

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

“…2. Each gesture varies in orientation and translation with complexity and challenging factor depending on the amount of intragesture variability [26]. EMG sEMG signals are captured from human forearms by placing electrodes on the subjects as shown in Fig.…”

Section: Color Tip Datasetmentioning

confidence: 99%

Study of Hand Gesture Recognition and Classification

Srinivas

Rajagopal

2017

Asian J Pharm Clin Res

View full text Add to dashboard Cite

To recognize different hand gestures and achieve efficient classification to understand static and dynamic hand movements used for communications. Static and dynamic hand movements are first captured using gesture recognition devices including Kinect device, hand movement sensors, connecting electrodes, and accelerometers. These gestures are processed using hand gesture recognition algorithms such as multivariate fuzzy decision tree, hidden Markov models (HMM), dynamic time warping framework, latent regression forest, support vector machine, and surface electromyogram. Hand movements made by both single and double hands are captured by gesture capture devices with proper illumination conditions. These captured gestures are processed for occlusions and fingers close interactions for identification of right gesture and to classify the gesture and ignore the intermittent gestures. Real-time hand gestures recognition needs robust algorithms like HMM to detect only the intended gesture. Classified gestures are then compared for the effectiveness with training and tested standard datasets like sign language alphabets and KTH datasets. Hand gesture recognition plays a very important role in some of the applications such as sign language recognition, robotics, television control, rehabilitation, and music orchestration.

show abstract

“…Kinematic hand model [7,31] tries to emulate the DoF of the human hand through fingers, joints, and their relative distances and angles primarily for robotic hands [10,33]. The vision based kinematic posture recognition approaches which are mostly contour-based adopt mechanisms like palm comprising of connected spheres [30], oriented radial distribution [40], Semi-supervised Transductive Regression Forest [41], and curve fitting [45] to implement DoFs. Skeleton-based techniques which employ structural representations like graphs [1,35] utilize heuristics like junction points (intersection of multiple branches) and end points (branch points which are not connected to any other branch) in skeleton matching.…”

Section: Literature Reviewmentioning

confidence: 99%

Real-time recognition of medial structures within hand postures through Eigen-space and geometric skeletal shape features

Kane

Khanna

2016

Multimed Tools Appl

View full text Add to dashboard Cite

Skeletons provide landmark points that preserve implicit strokes or medial structure within a shape for compact representation. Though, hand posture shapes are usually recognized by region or contour representations, some applications may only be interested in the recognition of medial structures within the postures rather than their exact outlines and regions. Proposed work identifies several unique medial structures formed by a set of both one and two-handed postures and demonstrates their pure skeletal recognition in real-time. Existing skeleton-based recognition schemes apply the complex segmental processing on underlying skeleton and rely on contour information which is not suitable for fast recognition of medial structures. Presented work applies intuitive Eigen-space based Principal Components of Symbolic Structure (PCSS) and geometric Equi-Polar Signature (EPS) features to accomplish the recognition task. Both PCV and EPS process the skeleton globally without sections without associating contour information. Recognition accuracy up to 94% is obtained on a 22 posture dataset comprising of 10,560 depth frames with 480 samples for each posture. Depth sensor based acquisition is employed to meet the real-time requirements.

show abstract

Real-time fingertip localization conditioned on hand gesture classification

Cited by 29 publications

References 24 publications

A Novel Hand Gesture Recognition Based on High-Level Features

A Novel Hand Gesture Recognition Based on High-Level Features

Study of Hand Gesture Recognition and Classification

Real-time recognition of medial structures within hand postures through Eigen-space and geometric skeletal shape features

Contact Info

Product

Resources

About