In this post we will walk through the solution to apply eyeliner

We are using dlib to detect the face and extract facial landmark. We will use OpenCV capabilities to do image processing.

These are the steps needed

1. Image with face
2. Detect face on the image
3. Find both eyes landmark using dlib.
4. Apply eye liner on eyes
5. Display image with applied eyeliner

Step 1 and 3 we have discussed in our previous post Apply Lipstick Effect

Step 3: Find both eyes landmark using dlib

consider points array contains all the landmarks

Left eye represented by indcies 36 to 42 in points

Right eye represented by indcies 42 to 48 in points

left_eye =  np.array(points[36:42])
right_eye = np.array(points[42:48])

Step 4: Apply eyeliner on eyes

To apply eyeliner on eyes we will use cv2.polylines() this method accept color of the eyeliner and thickness of the eyeliner and the points (i.e eye contours)

color = (0,0,0) # Eyeliner color
thickness = 3 # Eyeliner thickness
cv2.polylines(im_eyeliner,[left_eye], True, color=color, thickness = thickness)
cv2.polylines(im_eyeliner,[right_eye],  True, color=color, thickness = thickness)

Step 5: Display image with applied eyeliner

In step 4 we have drawn the polylines on im_eyelineron each eyes

plt.imshow(im_eyeliner)

as we have seen with simple image processing we can get this Eyeliner effect on any face.

This is the complete code

# Apply Eyeliner
im_eyeliner = imDlib.copy()
left_eye =  np.array(points[36:42])
right_eye = np.array(points[42:48])


color = (0,0,0) # Eyeliner color
thickness = 3 # Eyeliner thickness
cv2.polylines(im_eyeliner,[left_eye], True, color=color, thickness = thickness)
cv2.polylines(im_eyeliner,[right_eye],  True, color=color, thickness = thickness)

plt.imshow(im_eyeliner)

References:

• https://opencv.org/university/computer-vision-and-deep-learning-applications/