RGB-H-CbCr Skin Colour Model for Human Face Detection

Abstract 

RGB, HSV and YUV (YCbCr) are standard models used in various colour imaging applications, not all of their information are necessary to classify skin colour. This paper presents a novel skin colour model, RGB-H-CbCr for the detection of human faces. Skin regions are extracted using a set of bounding rules based on the skin colour distribution obtained from a training set. The segmented face regions are further classified using a parallel combination of simple morphological operations.

Introduction

This paper present a novel skin colour model RGB-H-CbCr for human face detection. This model utilises the additional hue and chrominance information of the image on top of standard RGB properties to improve the dis criminality between skin pixels and non-skin pixels. In this approach, skin regions are classified using the RGB boundary rules introduced by Peer et al. and also additional new rules for the H and CbCr subspaces. These rules are constructed based on the skin colour distribution obtained from the training images. The classification of the extracted regions is further refined using a parallel combination of morphological operations.

System Overview

In this colour-based approach to face detection, prior formulation of the proposed RGB H- CbCr skin model is done using a set of skin-cropped training images. Three commonly known colour spaces

– RGB, HSV and YCbCr are used to construct the proposed hybrid model. Bounding planes or rules for each skin colour subspace are constructed from their respective skin colour distributions.

In the first step of the detection stage, these bounding rules are used to segment the skin regions of

input test images. After that, a combination of morphological operations are applied to the extracted

skin regions to eliminate possible non-face skin regions. Finally, the last step labels all the face regions in the image and returns them as detected faces.

RGB-H-CbCr Model

The prepared skin colour samples were analysed in the RGB, HSV and YCbCr spaces, As opposed to 3-D space cluster approximation used by Garcia and Tziritas , this paper intend to examine 2-D colour subspaces in each of the mentioned colour models, i.e. H-S, S-V, H-V and so forth.

In RGB space, the skin colour region is not well distinguished in all 3 channels.

In HSV space, the H (Hue) channel shows significant discrimination of skin colour regions, as

observed from the H-V and H-S plots in where both plots exhibited very similar distribution of pixels. In the hue channel, most of the skin colour samples are concentrated around values between

0 and 0.1 and between 0.9 and 1.0 (in a normalized scale of 0 to 1).

The Cb-Cr subspace offers the best discrimination between skin and non-skin regions.

Skin colour bounding rules

From the skin colour subspace analysis, a set of bounding rules is derived from all three colour spaces, RGB, YCbCr and HSV, based on training observations. All rules are derived for intensity values between 0 and 255.

Rule A

In RGB space, use the skin colour rules introduced by Peer et al. The skin colour at

uniform daylight illumination rule is defined as

(R > 95) AND (G > 40) AND (B > 20) AND

(max{R, G, B} − min{R, G, B} > 15) AND

(|R − G| > 15) AND (R > G) AND (R > B)     

                                                                         Rule(1)

while the skin colour under flashlight or daylight lateral

illumination rule is given by

(R > 220) AND (G > 210) AND (B > 170) AND

(|R − G| ≤ 15) AND (R > B) AND (G > B) 

                                                                         Rule(2)

To consider both conditions when needed, this paper used

a logical OR to combine both rule (1) and rule (2).  Rule A: Equation(1) OR Equation(2)     

Rule B

Based on the observation that the Cb-Cr subspace is a strong discriminant of skin colour;

Cr ≤ 1.5862 × Cb + 20   (3)

Cr ≥ 0.3448 × Cb + 76.2069  (4)

Cr ≥ -4.5652 × Cb + 234.5652  (5)

Cr ≤ -1.15 × Cb + 301.75  (6)

Cr ≤ -2.2857 × Cb + 432.85  (7)

Rules (3) to (7) are combined using a logical AND to obtain the CbCr bounding rule B.

Rule B: Equation(3) AND Equation(4) AND Equation(5) AND Equation(6) AND Equation(7) 

Rule C

In the HSV space, the hue values exhibit the most noticeable separation between skin and non-skin

regions. We estimated two cut off levels as our H subspace skin boundaries,

H < 25 (9)

H > 230 (10)

where both rules are combined by a logical OR to obtain the H bounding rule C.

Rule C: Equation(9) OR Equation(10)

Thereafter, each pixel that fulfills Rule A, Rule B and Rule C is classified as a skin colour pixel,

Rule A AND Rule B AND Rule C

Skin colour segmentation

The proposed novel combination of all 3 bounding rules from the RGB, H and CbCr subspaces  is named the “RGB-H-CbCr” skin colour model. Although skin colour segmentation is normally

considered to be a low-level or “first-hand” cue extraction, it is crucial that the skin regions are

segmented precisely and accurately. Our segmentation technique, which uses all 3 colour spaces was designed to boost the face detection accuracy.

Morphological Operations

The next step of the face detection system involves the use of morphological operations to refine the skin regions extracted from the segmentation step.

Firstly, fragmented sub-regions can be easily grouped together by applying simple dilation on the

large regions. Hole and gaps within each region can also be closed by a flood fill operation.

this paper used a morphological opening to “open up” or pull apart narrow, connected regions.

Additional measures are also introduced to determine the likelihood of a skin region being a face

region. 

Two region properties – box ratio and eccentricity are used to examine and classify the shape

of each skin region.

The box ratio property is simply defined as the width to height ratio of the region bounding box. By

trial and error, the good range of values lie between 1.0 and 0.4. Ratio values above 1.0 would not suggest a face since human faces are oriented vertically with a longer height than width. Meanwhile, ratio values below 0.4 are found to misclassifying arms, legs or other elongated objects as faces.

The eccentricity property measures the ratio of the minor axis to major axis of a bounding ellipse.

Eccentricity values of between 0.3 and 0.9 are estimated to be of good range for classifying face

regions. Though this property works in a similar way as box ratio, it is more sensitive to the region shape and is able to consider various face rotations and poses.

Both the box ratio and eccentricity properties can be applied to the extracted skin regions either sequentially or parallelly, following a dilation, opening or flood fill.

Conclusion

In this paper, they have presented a novel skin colour model, RGB-H-CbCr to detect human faces. Skin region segmentation was performed using a combination of RGB, H and CbCr subspaces, which

demonstrated evident discrimination between skin and non-skin regions. The experimental results showed that this new approach in modelling skin colour was able to achieve a good detection success rate. On a similar test data set, the performance of our approach was comparable to that of the AdaBoost face classifier.