A boosted classifier tree for hand shape detection

By Eng-Jon Ong, Richard Bowden. Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004. Proceedings., 2004

303 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/4625c6c0d45fdc19e21ceb43f12e2f7d3278f498

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Contextual Attention for Hand Detection in the Wild (2019, background): “Early works mostly used skin color to detect hands [5, 34, 35], or boosted classiﬁers based on shape features [19, 25].”
Multi-layered gesture recognition with Kinect (2015, background): “The well known features used for gesture recognition are color (Awad et al., 2006; Maraqa and Abu-Zaiter, 2008), shapes (Ramamoorthy et al., 2003; Ong and Bowden, 2004) and motion (Cutler and Turk, 1998; Mahbub et al., 2013).”
Automatic Sign Language Analysis: A Survey and the Future beyond Lexical Meaning (2005, methodology): “Ong and Bowden [101] detected hands with 99.8 percent accuracy in grey scale images with shape information alone, using a boosted cascade of classifiers [140].”
Hand detection using multiple proposals (2011, methodology): “Methods based on detecting hands independently using skin detection [27, 28, 30] or Viola & Jones like cascade detectors built from Harr features [23, 25, 26] have had limited success and impact on unconstrained images, perhaps due to lack of sufficient training data.”
Sign Language Recognition (2011, methodology): “Ong and Bowden presented a combined hand detector and shape classifier using a boosted cascade classifier [79].”
American sign language recognition with the kinect (2011, background): “Many researchers choose to use the sign as a base unit of modeling [4, 20], while others attempt to use a structure similar to phonemes to create models [8, 17].”
A Unified Framework for Gesture Recognition and Spatiotemporal Gesture Segmentation (2009, background): “Despite advances in hand detection [9], [10] and hand tracking [11], [12], [13], [14], [15], hand detection remains a challenging task in many real-life settings.”
Hand gesture recognition with depth images: A review (2012, methodology): “Without the use of depth information the most common methods for hand segmentation are skin-color maps [2, 3] and cascaded classifiers on Haar-like features [43, 44].”
Spelling it out: Real-time ASL fingerspelling recognition (2011, methodology): “Ong & Bowden [10] proposed a hand shape classifier based on boosted classifiers and shape context features, claiming 97.4% recognition rate on 300 artificial hand shapes.”
Vision-based hand pose estimation: A review (2007, methodology): “[97] employed clustering methods to cluster the training data into similar shapes and build a tree of classifiers for detection.”
Challenges in multimodal gesture recognition (2016, background): “…be achieved by placing additional constraints on the scene and the relative position of the subject and the hands with respect to the camera (Cui and Weng, 2000; Isard and Blake, 1998; Kolsch and Turk, 2004; Ong and Bowden, 2004; Stefanov et al., 2005; Stenger et al., 2003; Sudderth et al., 2004).”