Hand Gesture Detection Using OpenCV and Python: Skin Color and Contour Processing

The author describes a beginner‑friendly project that implements hand‑gesture detection using Python and OpenCV, leveraging basic image‑processing techniques such as video capture, skin‑color detection in the YCrCb color space, and contour extraction to isolate the hand region.

Video Capture

cap = cv2.VideoCapture("C:/Users/lenovo/Videos/1.mp4")  # read video file
#cap = cv2.VideoCapture(0)  # use webcam
while True:
    ret, frame = cap.read()
    key = cv2.waitKey(50) & 0xFF
    if key == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

The loop reads each frame, displays it, and exits when the user presses q .

Skin Color Detection

The method converts the frame from BGR to YCrCb, applies Gaussian blur to the Cr channel, and uses Otsu’s thresholding to obtain a binary skin mask, which is then applied to the original image.

def A(img):
    YCrCb = cv2.cvtColor(img, cv2.COLOR_BGR2YCR_CB)  # convert to YCrCb
    (y, cr, cb) = cv2.split(YCrCb)                 # split channels
    cr1 = cv2.GaussianBlur(cr, (5, 5), 0)
    _, skin = cv2.threshold(cr1, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
    res = cv2.bitwise_and(img, img, mask=skin)
    return res

Contour Processing

After obtaining a binary skin image, contours are found with cv2.findContours . The contours are sorted by area, and the largest one (assumed to be the hand) is drawn on a white canvas.

def B(img):
    h = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)  # find contours
    contour = h[0]
    contour = sorted(contour, key=cv2.contourArea, reverse=True)  # sort by area
    bg = np.ones(dst.shape, np.uint8) * 255  # white background
    ret = cv2.drawContours(bg, contour[0], -1, (0, 0, 0), 3)  # draw largest contour
    return ret

Full Processing Loop

while True:
    ret, frame = cap.read()
    src = cv2.resize(frame, (400, 350), interpolation=cv2.INTER_CUBIC)
    cv2.rectangle(src, (90, 60), (300, 300), (0, 255, 0))
    roi = src[60:300, 90:300]  # region of interest
    res = A(roi)  # skin detection
    cv2.imshow("0", roi)
    gray = cv2.cvtColor(res, cv2.COLOR_BGR2GRAY)
    dst = cv2.Laplacian(gray, cv2.CV_16S, ksize=3)
    Laplacian = cv2.convertScaleAbs(dst)
    contour = B(Laplacian)  # contour processing
    cv2.imshow("2", contour)
    key = cv2.waitKey(50) & 0xFF
    if key == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

The complete script captures video frames, extracts a hand region, performs skin detection, applies Laplacian filtering, extracts the largest contour, and displays both the original ROI and the processed contour image.

Overall, the tutorial demonstrates how to combine basic OpenCV functions to achieve real‑time hand‑gesture detection, providing all necessary code snippets and explanations for beginners.