A Comparative Study of Skin-Color Models

Lu, Juwei; Gu, Qian; Plataniotis, K.N.; Wang, Jie

doi:10.1007/11559573_89

Cited by 6 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diverse approaches for skin detection have been developed which could be classified into parametric [1,4,9,12], statistical, such as [15] and adaptive methods [7,11,17] as described in [16,20,23]. The parametric and statistical methods are quite effective for skin detection, but they are highly sensitive to changes in lighting conditions and they also produce high false-positive errors in case of objects with colour similar to human skin exist in the environment.…”

Section: Research Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic approach for real-time skin detection

Bilal

Akmeliawati

Salami

et al. 2012

J Real-Time Image Proc

View full text Add to dashboard Cite

Human face and hand detection, recognition and tracking are important research areas for many computer interaction applications. Face and hand are considered as human skin blobs, which fall in a compact region of colour spaces. Limitations arise from the fact that human skin has common properties and can be defined in various colour spaces after applying colour normalization. The model therefore, has to accept a wide range of colours, making it more susceptible to noise. We have addressed this problem and propose that the skin colour could be defined separately for every person. This is expected to reduce the errors. To detect human skin colour pixels and to decrease the number of false alarms, a prior face or hand detection model has been developed using Haar-like and AdaBoost technique. To decrease the cost of computational time, a fast search algorithm for skin detection is proposed. The level of performance reached in terms of detection accuracy and processing time allows this approach to be an adequate choice for real-time skin blob tracking.

show abstract

Section: Research Backgroundmentioning

confidence: 99%

“…Many of the adaptive skin detectors are mainly employed to achieve high detection accuracy. Neural network-based methods support vector machines and other kernel methods have been proposed [16,20,23], where in the vast majority of cases, lighting conditions are constant within an image.…”

Section: Research Backgroundmentioning

confidence: 99%

Dynamic approach for real-time skin detection

Bilal

Akmeliawati

Salami

et al. 2012

J Real-Time Image Proc

View full text Add to dashboard Cite

show abstract

“…In that sense, the pixels with intensity values between either two closest local minima are labeled as a cluster. To this end, other clustering algorithms like watershed 16 and meanshift 17 could be used as alternatives.…”

Section: Split-merge Skin Detectionmentioning

confidence: 99%

Unsupervised tattoo segmentation combining bottom-up and top-down cues

et al. 2011

View full text Add to dashboard Cite

Tattoo segmentation is challenging due to the complexity and large variance in tattoo structures. We have developed a segmentation algorithm for finding tattoos in an image. Our basic idea is split-merge: split each tattoo image into clusters through a bottom-up process, learn to merge the clusters containing skin and then distinguish tattoo from the other skin via top-down prior in the image itself. Tattoo segmentation with unknown number of clusters is transferred to a figureground segmentation. We have applied our segmentation algorithm on a tattoo dataset and the results have shown that our tattoo segmentation system is efficient and suitable for further tattoo classification and retrieval purposes.

show abstract

“…Assuming the frame rate is adequate, the sizes of the objects should not change dramatically between adjacent frames. The distance of an object between adjacent frames defined as: dis = (exc px Y + (c yc py y (12) if dis ::;; r (r is a threshold), we consider that the two objects in two different but adjacent frames are the same object.…”

Section: Vl-160mentioning

confidence: 99%

“…It is necessary to introduce the mean shift algorithm prior to the CAMSHIFT since the CAM SHIFT is derived from the mean shift which is climbs the gradient of a procedure to a probability distribution to find the nearest dominant dome (peak) [12]. The procedure to calculate the mean shift algorithm is given as follows:…”

Section: B the Camshift Algorithmmentioning

confidence: 99%

Video object tracking based on position prediction guide CAMSHIFT

Ling

Zhang

Xing

2010

2010 3rd International Conference on Advanced Computer Theory and Engineering(ICACTE)

View full text Add to dashboard Cite

In this article, a novel algorithm-position prediction guide continuously adaptive mean shift procedure (CAMSHIFT)-is proposed for tracking objects in video sequences. CAMSHIFT is incorporated with the position prediction algorithm makes the scale adaptation of CAMSHIFT is improved, tracking efficiency increased and the computation complexity is reduced. Preliminary experimental results show the algorithm performs well. Meanwhile, the algorithm success in indicating new objects appeared; objects disappeared; objects collisions and the consistency of the objects in consecutive sequences.

show abstract

A Comparative Study of Skin-Color Models

Abstract: Abstract. In this paper, we report the results of a comparative study on skin-color models generally used for facial region location. These include two 2D Gaussian models developed in normalized RGB and HSV color spaces respectively, a 1D lookup

Cited by 6 publications

References 15 publications

Dynamic approach for real-time skin detection

Dynamic approach for real-time skin detection

Unsupervised tattoo segmentation combining bottom-up and top-down cues

Video object tracking based on position prediction guide CAMSHIFT

Contact Info

Product

Resources

About