Using opencv to parse frames for Amazon Rekognition to analyze. This example uses Rekognition's celebrity recognition feature as an example.

opencv-python_rekognition.py

# With help from https://aws.amazon.com/blogs/ai/build-your-own-face-recognition-service-using-amazon-rekognition/

frame_skip = 100 # analyze every 100 frames to cut down on Rekognition API calls

import boto3
import cv2
from PIL import Image
import io

rekog = boto3.client('rekognition')

vidcap = cv2.VideoCapture('./video_clip.mp4') # Load clip from storage. Can modify this to input from camera.
cur_frame = 0
success = True

while success:

    success, frame = vidcap.read() # get next frame from video

    if cur_frame % frame_skip == 0: # only analyze every n frames
        print('frame: {}'.format(cur_frame)) 

        pil_img = Image.fromarray(frame) # convert opencv frame (with type()==numpy) into PIL Image
        stream = io.BytesIO()
        pil_img.save(stream, format='JPEG') # convert PIL Image to Bytes
        bin_img = stream.getvalue()

        response = rekog.recognize_celebrities(Image={'Bytes': bin_img}) # call Rekognition
        if response['CelebrityFaces']: # print celebrity name if a celebrity is detected
            for face in response['CelebrityFaces']:
                print('Celebrity is {} with confidence of {}'.format(face['Name'], face['MatchConfidence']))

    cur_frame += 1

kudos for the awesome code!! but how to redisplay the image after recognition with all the celebrity info.

kudos for the awesome code!! but how to redisplay the image after recognition with all the celebrity info.

Not sure I 100% understand your question, but if you're talking about plotting the bounding boxes on top of the faces, then:

1. Grab the bounding box info from the API response. If you check out boto3's rekognition API for recognize_celebrities(), this would be `face['Face']['BoundingBox'] if using my variable above.
2. Plot the bounding box on top of the image using PIL by using the rectangle method in PIL's ImageDraw class.