Robust hand gesture recognition based on finger-earth mover's distance with a commodity depth camera

By Zhou Ren, Junsong Yuan, Zhengyou Zhang. ACM Multimedia, 2011

453 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/cf88c2f3729b1486bfbf7d82c342ee2f71fe929f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Human Action Recognition by Shape Analysis of Motion Trajectories on Riemannian Manifold (2014, background): “3 These new acquisition devices have stimulated the development of various promising applications, includ4 ing human pose reconstruction and estimation [3], scene flow estimation [4], hand gesture recognition [5], 5 and face super-resolution [6].”
LaRED: a large RGB-D extensible hand gesture dataset (2014, methodology): “The dataset in [10] contains 10 classes performed by 10 persons under cluttered background.”
Robust hand gesture recognition with kinect sensor (2011, methodology): “Therefore, we use a novel shape distance metric called Finger-Earth Mover’s Distance (FEMD) to measure the dissimilarities between different hand shapes, which is proposed in [4].”
Recent methods and databases in vision-based hand gesture recognition: A review (2015, methodology): “[88, 112] proposed a hand posture recognition system having robustness against variations in hand orientation, scale, and articulation.”
Hand gesture recognition with depth images: A review (2012, methodology): “Ren [11] uses Template Matching on features transformed by a Finger-Earth Mover’s Distance.”
A real time system for dynamic hand gesture recognition with a depth sensor (2012, methodology): “Index Terms— Gesture recognition, depth camera”
Depth-Based Hand Pose Estimation: Methods, Data, and Challenges (2015, unknown): “Recently introduced consumer depth cameras have spurred a ﬂurry of new advances [4,14,15,17,25,33,36,38,42].”
Robust Part-Based Hand Gesture Recognition Using Kinect Sensor (2013, unknown): “It should be noted that our FEMD algorithm is mainly rewritten and optimized in C++, rather than just using Matlab as in our previous work [1], which leads to the better results than [1].”
Challenges in multimodal gesture recognition (2016, background): “…of static gestures, frequently hand shape is the important differentiating feature (Cui and Weng, 2000; Freeman and Roth, 1996; Kelly et al., 2010; Ren et al., 2011b; Triesch and von der Malsburg, 2002), although the pose of the rest of the body can also be important, e.g., (Yang et al., 2010;…”
Hand gesture recognition with leap motion and kinect devices (2014, background): “[7] and [8] compare, instead, the histograms of the distance of hand edge points from the hand center in order to recognize the gestures.”
From Word Embeddings To Document Distances (2015, methodology): “The use of the EMD has been pioneered in the computer vision literature (Rubner et al., 1998; Ren et al., 2011).”
3D Gestural Interaction: The State of the Field (2013, background): “Other recent works using depth cameras for hand and finger tracking for 3D gestural interfaces can be found in [42] [43] [44].”