Proceedings ArticleDOI
OGRE - open gestures recognition engine
José Miguel Salles Dias,Pedro Nande,Nuno Barata,A. Correia +3 more
- pp 33-40
Reads0
Chats0
TLDR
A hand gesture recognition engine based on computer vision (CV), as a computing platform to support gesture interaction between humans and computers, and presents experimental results, regarding the recognition of Portuguese sign language signs.Abstract:
In this paper, we describe a hand gesture recognition engine based on computer vision (CV), as a computing platform to support gesture interaction between humans and computers. Presenting a simple approach to recognizing gestures through image processing techniques and a single video camera, we address the problem of generic hand gestures recognition, especially of spelled sign language hand poses, introducing a preliminary study to its kinetic component. In our methodology, the system initially removes the background of captured images, eliminating irrelevant pixel information. The human hand is then detected, segmented and its contours localized. From these contours significant metrics are derived, allowing a search in a pre-defined hand poses' library, where each pose is previously converted into a set of metric values. We discuss several algorithmic options to support our methodology and present experimental results, regarding the recognition of Portuguese sign language signs. We discuss future directions of our work.read more
Citations
More filters
Journal ArticleDOI
Hand tracking and gesture recognition system for human-computer interaction using low-cost hardware
TL;DR: This paper proposes a simple but efficient method that allows robust and fast hand tracking despite complex background and motion blur, and enables intuitive HCI and interactive motion gaming with minimum hardware requirements.
Proceedings ArticleDOI
An intelligent gesture interface for controlling TV sets and set-top boxes
TL;DR: The data returned from a custom 3D depth camera and a customizable gesture language is used to create an intelligent gesture interface for the control of TVs and set-top boxes.
Proceedings ArticleDOI
Visual Hand Tracking Algorithms
Fariborz Mahmoudi,Mehdi Parviz +1 more
TL;DR: Most widely used methods and techniques for segmentation, tracking, modeling and recognition are reviewed and their numerical evaluation results are collected.
Patent
System for controlling light enabled devices
TL;DR: In this paper, a system for controlling IR enabled devices by projecting coded IR pulses from an active illumination depth camera is described, which can detect the performance of a particular gesture associated with a particular electronic device.
Two-Handed Gestures for Human-Computer Interaction
TL;DR: A method for HPR based on new feature extraction based on the Modified Census Transform (MCT) to extract relevant features in images is proposed and a complete survey on recent state-of-the-art techniques for both HPR and HGR is presented.
References
More filters
Proceedings ArticleDOI
An extended set of Haar-like features for rapid object detection
Rainer Lienhart,J. Maydt +1 more
TL;DR: This paper introduces a novel set of rotated Haar-like features that significantly enrich the simple features of Viola et al. scheme based on a boosted cascade of simple feature classifiers.
Journal ArticleDOI
The importance of phase in signals
Alan V. Oppenheim,Jae Lim +1 more
TL;DR: Specific conditions under which a sequence can be exactly reconstructed from phase are reviewed, both for one-dimensional and multi-dimensional sequences, and algorithms for both approximate and exact reconstruction of signals from phase information are presented.
Journal ArticleDOI
Phase-only matched filtering
TL;DR: This work examines the relationship between phase and amplitude in the case of alphanumeric characters, with and without noise, using a computer simulation and compares the phase-only and amplitude-only filters to the classical matched filter using the criteria of discrimination, correlation peak, and optical efficiency.
Proceedings Article
A Statistical Approach for Real-time Robust Background Subtraction and Shadow Detection
Proceedings ArticleDOI
Shape descriptors for non-rigid shapes with a single closed contour
TL;DR: This paper reports on the MPEG-7 Core Experiment CE-Shape, which gave a unique opportunity to compare various shape descriptors for non-rigid shapes with a single closed contour and found that a more theoretical comparison of these descriptors seems to be extremely hard.