Statistical Color Models with Application to Skin Detection

By Michael J. Jones, James M. Rehg. 1999

Subfields: Computer Vision and Pattern Recognition, Statistics and Probability

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Statistics and Probability

Citations in the corpus

Fine-Grained Egocentric Hand-Object Segmentation: Dataset, Model, and Applications (2022, methodology): “[22] used a color statistics–based approach to separate the skin region and the background.”
Skin segmentation using color pixel classification: analysis and comparison (2005, methodology): “Jones and Rehg [4] created the first large skin database—the Compaq database—and used the Bayesian classifier with the histogram technique for skin detection.”
Background and foreground modeling using nonparametric kernel density estimation for visual surveillance (2002, methodology): “Color histograms have also been used in [31] for tracking hands, in [26] for color region tracking and in [33] for skin detection.”
Human Pose Estimation Using Body Parts Dependent Joint Regressors (2013, methodology): “Additionally to the color and HOG features, we added the output of a skin detector [19] as feature.”
Face verification across age progression (2005, methodology): “Next, given a nonfrontal color image of an individual, we extract the face region using statistical color models for skin detection [35].”
Automatic analysis of multimodal group actions in meetings (2005, methodology): “used to extract head and hand/forearm blobs [59].”
Discovering important people and objects for egocentric video summarization (2012, methodology): “Given a frame in the test video, we first classify each pixel as (non-)skin using color likelihoods and a Naive Bayes classifier [14] trained with ground-truth hand annotations on disjoint data.”
Robust hand detection (2004, background): “For example, skin color is surprisingly uniform [9, 6], so color-based hand detection is possible [13].”
Body Parts Dependent Joint Regressors for Human Pose Estimation in Still Images (2014, background): “For classifying body parts, the parameter space is the set of class labels or body parts.”
Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images (2000, methodology): “It is argued in [7] that the performance of skin pixel detection depends entirely on the amount of overlap, and that the transformation between 3-D color spaces such as from RGB into HSV will not improve skin detection performance, because the amount of overlap is not affected.”
A Framework for content-adaptive photo manipulation macros: Application to face, landscape, and global manipulations (2011, unknown): “2003], a skin recognizer [Jones and Rehg 2002], and an outdoor scene recognizer [Hoiem et al.”
A survey of skin-color modeling and detection methods (2007, methodology): “Brand and Mason [47] have evaluated the performance of color ratios with other algorithms on the Compaq data set [48].”
Personal object discovery in first-person videos (2015, unknown): “Since personal objects cannot be fully described by appearance, we turn to object discovery in an unsupervised way.”
Human Ear Recognition in 3D (2007, methodology): “In the first step, a skin color classifier is used to isolate the side face in an image by modeling the skin color and nonskin color distributions as a mixture of Gaussians [21].”
Face recognition with image sets using manifold density divergence (2005, methodology): “The classifier is based on 3-dimensional colour histograms built for two classes: skin and non-skin pixels [17].”
Pixel-Level Hand Detection with Shape-Aware Structured Forests (2014, background): “Heuristic skin-color detection methods [3] may also fail in practice when skin color is not discriminative enough from the background.”