OpenCV detectin skin colour invariant with illumination changes

Question

I have to capture skin colour independent of illumination. I used the following criteria(using hsv and rgb) but it ain't working:

int h = get_hue(...);
int s = get_saturation(...);
int r = get_red_component(...);
int g = get_green_component(...);
int b = get_blue_component(...);

if ((h<38)&&(h>6)&&(s>0.23)&&(s<0.68)){
    // skin color
}
else if ((r>95) && (g>40) && (b>20) && 
         ((maximum(r,g,b)-minimum(r,g,b))>15) && 
         (abs(r-g)>15)&&(r>g)&&(r>b)){
   // also skin color
}

It works in the morning when my skin is illuminated but by evening it does not work.

Any Help will be appreciated. Thanks in Advance. (PS -my skin ain't white.)

Answer 1

In my experience best method for this is converting it to Lab color space. L represents the light, and a and b are light independent. OpenCV supports Lab color scale conversion.

Answer 2

try this:

''' Detect human skin tone and draw a boundary around it.
Useful for gesture recognition and motion tracking.

Inspired by: http://stackoverflow.com/a/14756351/1463143

Date: 08 June 2013
'''

# Required moduls
import cv2
import numpy

# Constants for finding range of skin color in YCrCb
min_YCrCb = numpy.array([0,133,77],numpy.uint8)
max_YCrCb = numpy.array([255,173,127],numpy.uint8)

# Create a window to display the camera feed
cv2.namedWindow('Camera Output')

# Get pointer to video frames from primary device
videoFrame = cv2.VideoCapture(0)

# Process the video frames
keyPressed = -1 # -1 indicates no key pressed

while(keyPressed < 0): # any key pressed has a value >= 0

    # Grab video frame, decode it and return next video frame
    readSucsess, sourceImage = videoFrame.read()

    # Convert image to YCrCb
    imageYCrCb = cv2.cvtColor(sourceImage,cv2.COLOR_BGR2YCR_CB)

    # Find region with skin tone in YCrCb image
    skinRegion = cv2.inRange(imageYCrCb,min_YCrCb,max_YCrCb)

    # Do contour detection on skin region
    contours, hierarchy = cv2.findContours(skinRegion, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    # Draw the contour on the source image
    for i, c in enumerate(contours):
        area = cv2.contourArea(c)
        if area > 1000:
            cv2.drawContours(sourceImage, contours, i, (0, 255, 0), 3)

    # Display the source image
    cv2.imshow('Camera Output',sourceImage)

    # Check for user input to close program
    keyPressed = cv2.waitKey(1) # wait 1 milisecond in each iteration of while loop

# Close window and camera after exiting the while loop
cv2.destroyWindow('Camera Output')
videoFrame.release()

Answer 3

For this special case, I recommend reading up on LAB Color model.

And in regard to the LAB Color model, read up on Delta E. The distance between 2 colors. More details about color space can be found here: http://www.codeproject.com/Articles/613798/Colorspaces-and-Conversions

I have never attempted the LAB color model via OpenCV as it's is a hassle to convert from RGB to LAB and back(requires an immediate step).

But I have explored Delta E on MatLab to great success. You have to select the skin first, draw a small ROI on the video/picture and the program will find all the exact same color tone as the skin you selected via the ROI.

Another option is also look into the texture. A short preview here: http://books.google.com.sg/books?id=bRlk_WjfITIC&pg=PA598&lpg=PA598&dq=skin+thresholding+from+texture&source=bl&ots=28fE0livyh&sig=8EeQTLFCc-JB979_-ccyrhDJlqA&hl=en&sa=X&ei=aAuFUsHhJoWJrQfpkoCgBg&ved=0CDUQ6AEwAQ#v=onepage&q=skin%20thresholding%20from%20texture&f=false

This is basically training a image database. Comment here if you need help to training the image database or conversion of ColorSpace. A little busy, so the answer is just suggestions that you can do. Cheers.