[face recognition series] | realize automatic makeup

Make up

Today's project is more interesting , Make up the face in the picture [ A bad laugh ], Think about when your girlfriend said that she forgot to apply lipstick and trim her eyebrows when taking photos today , Then you say you come , Give him a boast about the operation results P It's even uglier , This doesn't make lanterns in the toilet – Looking for shit , But don't panic. I'll save you today , Cough, get to the point .
First , We still have to know what functions we need to use first , It mainly uses these two face_landmarks( As mentioned in the last article , But for better experience and faster understanding, I'd better get it for you ),ImageDraw.polygon.

Face feature extraction function ——face_landmarks

face_landmarks( face_image , face_locations=None, model=“large” ) Given an image , Extract the facial feature position of each face in the image Parameters ： face_image ： Input face image face_locations=None ： Optional parameters , The default value is None, Represents everyone's face in the default decoded picture . If input face_locations()[i] You can specify a face to decode model=“large” ： Output feature model , The default is “large”, Optional “small”. When the choice is "small" when , Only the left eye is extracted left_eye、 Right eye right_eye、 Nose nose_tip These three facial features .

ImageDraw.polygon

Construct a ImageDraw object : polygon() Method is used to draw polygons ： The first parameter is the number of polygons Composed of vertex positions list, The second parameter fill Is the face that fills the polygon color . line() The method is used to draw line segments composed of multiple points , The first parameter is Point position list, The second parameter fill Is the color of the line segment , The third reference Count width Is the width of the line segment .
By using face_landmarks To locate the characteristic face of the face , Use it Image.polygon Draw polygon , Next, the detailed code explanation

Specific code

import face_recognition
from PIL import Image, ImageDraw
def demoFunc2(pic_path):
    
     #  Load the picture as numpy Array 
    image = face_recognition.load_image_file(pic_path)
    face_landmarks_list = face_recognition.face_landmarks(image)
    print(f"I found {
      len(face_landmarks_list)} face<s> in this photograph."))
    pil_image = Image.fromarray(image)
	#  Traverse the face ,  draw 
    for face_landmarks in face_landmarks_list: 
        demo = ImageDraw.Draw(pil_image, 'RGBA')
        demo.polygon(face_landmarks['left_eyebrow'], fill=(68, 54, 39, 128))
        demo.polygon(face_landmarks['right_eyebrow'], fill=(68, 54, 39, 128))
        # demo.line(face_landmarks['left_eyebrow'], fill=(68, 54, 39, 150), width=2)
        # demo.line(face_landmarks['right_eyebrow'], fill=(68, 54, 39, 150), width=2)
        demo.polygon(face_landmarks['top_lip'], fill=(150, 0, 0, 128))
        # demo.polygon(face_landmarks['bottom_lip'], fill=(150, 0, 0, 128))
        demo.polygon(face_landmarks['bottom_lip'], fill=(150, 0, 0, 128))
        # demo.line(face_landmarks['top_lip'], fill=(150, 0, 0, 64), width=2)
        # demo.line(face_landmarks['bottom_lip'], fill=(150, 0, 0, 64), width=2)
        demo.polygon(face_landmarks['left_eye'], fill=(255, 255, 255, 30))
        demo.polygon(face_landmarks['right_eye'], fill=(255, 255, 255, 30))

        # pil_image.save("1_.jpg") # have access to save Method to save 
        pil_image.show()
demoFunc2("6.png")

I found the use of line The method is a little strange after tracing , So I made a deletion here , You can also try it yourself , The color can also follow RGBA Try to change by yourself , I continue to use Peng Yuyan here to show you haha

Result display

At the same time, I also packed it to my github In the , If you want to play, you can also download it directly .