Hand Gesture Recognition Using OpenCV: Video Capture, Skin Detection, and Contour Processing in Python

The author presents a beginner‑friendly project that implements hand‑gesture detection using Python and OpenCV. The workflow includes acquiring video frames, applying skin‑color detection, extracting hand contours, and displaying the results.

Video Capture

The video source is opened with cap = cv2.VideoCapture("C:/Users/lenovo/Videos/1.mp4") (or a webcam with cv2.VideoCapture(0) ). A loop reads frames, resizes them, draws a rectangle to define the region of interest, and extracts that ROI for further processing.

Skin Detection (Function A)

The ROI is converted from BGR to YCrCb color space to reduce the influence of illumination. The Cr channel is blurred, then Otsu’s thresholding isolates skin pixels. The mask is applied with cv2.bitwise_and to obtain a skin‑only image.

<code>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)  # Otsu
    res = cv2.bitwise_and(img, img, mask=skin)
    return res</code>

Contour Extraction (Function B)

After converting the skin‑detected image to grayscale and applying a Laplacian filter, 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.

<code>def B(img):
    h = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
    contour = h[0]
    contour = sorted(contour, key=cv2.contourArea, reverse=True)
    bg = np.ones(dst.shape, np.uint8) * 255  # white background
    ret = cv2.drawContours(bg, contour[0], -1, (0, 0, 0), 3)  # draw black contour
    return ret</code>

Main Loop

The script continuously reads frames, extracts the ROI, runs A(roi) for skin detection, converts the result to grayscale, applies a Laplacian filter, then calls B(Laplacian) to obtain the hand contour. The original ROI, skin mask, and contour image are displayed in separate windows. Pressing ‘q’ exits the loop.

<code>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]
    res = A(roi)
    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)
    cv2.imshow("2", contour)
    key = cv2.waitKey(50) & 0xFF
    if key == ord('q'):
        break
cap.release()
cv2.destroyAllWindows()</code>

The article also includes animated GIFs and images illustrating the final hand‑gesture detection result, as well as promotional material for a free Python course, which is not part of the technical content.