Hybrid face detection with HSV Color method and HAAR classifier

Niazi, Mehrnaz; Jafar, Shahram

doi:10.1109/icste.2010.5608795

Cited by 1 publication

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linear transformations include YIQ, YYUV, and YC b C r . Nonlinear transformations include NCC, HSV, and HSL [10][11][12][13]. Recent research efforts have generally used techniques that transform higher-dimensional color spaces into lower-dimensional color spaces to save computational time [14,15].…”

Section: Department Of Mechatronics Division Of Information System Ementioning

confidence: 99%

See 1 more Smart Citation

Skin Region Detection Using a Mean Shift Algorithm Based on the Histogram Approximation

Byun¹,

Nam²,

Ye³

2012

Transactions on Electrical and Electronic Materials

View full text Add to dashboard Cite

In conventional, skin detection methods using for skin color definitions is based on prior knowledge. Byexperimentation, the threshold value for dividing the background from the skin region is determined subjectively. Adrawback of such techniques is that their performance is dependent on a threshold value which is estimated fromrepeated experiments. To overcome this, the present paper introduces a skin region detection method. This methoduses a histogram approximation based on the mean shift algorithm. This proposed method applies the mean shiftprocedure to a histogram of a skin map of the input image. It is generated by comparing with the standard skin colorsin the CbCr color space. It divides the background from the skin region by selecting the maximum value accordingto the brightness level. As the histogram has the form of a discontinuous function. It is accumulated according tothe brightness values of the pixels. It is then, approximated by a Gaussian mixture model (GMM) using the Beziercurve technique. Thus, the proposed method detects the skin region using the mean shift procedure to determine amaximum value. Rather than using a manually selected threshold value, as in existing techniques this becomes thedividing point. Experiments confirm that the new procedure effectively detects the skin region

show abstract

Section: Department Of Mechatronics Division Of Information System Ementioning

confidence: 99%

“…Equation 11is the Bezier curve formula using the De Castelli algorithm. (11) The control point P S (x) indicates the frequency at each brightness level of the histogram, and t is a distance control variable calculated via Equation (12) (smaller values of t corresponding to shorter curves).…”

Section: Histogram Approximation Using Bezier Curvementioning

confidence: 99%