app.py

from fastapi import FastAPI
import os
from typing import Any, Union,Dict, List
import numpy as np
import io
import base64
import requests

import cv2
from PIL import Image
 
# Create a new FastAPI app instance
app = FastAPI()
 
# Initialize the text generation pipeline
# This function will be able to generate text
# given an input.
prototxtPath = os.path.sep.join(["face_detector", "deploy.prototxt"])
weightsPath = os.path.sep.join(["face_detector",
    "res10_300x300_ssd_iter_140000.caffemodel"])
net = cv2.dnn.readNet(prototxtPath, weightsPath)

# Define a function to handle the GET request at `/generate`
# The generate() function is defined as a FastAPI route that takes a 
# string parameter called text. The function generates text based on the # input using the pipeline() object, and returns a JSON response 
# containing the generated text under the key "output"
args = {
    "method": "simple",
    "blocks": 20,
    "confidence": 0.5
}
def anonymize_face_simple(image, factor=3.0):
    # automatically determine the size of the blurring kernel based
    # on the spatial dimensions of the input image
    (h, w) = image.shape[:2]
    kW = int(w / factor)
    kH = int(h / factor)

    # ensure the width of the kernel is odd
    if kW % 2 == 0:
        kW -= 1

    # ensure the height of the kernel is odd
    if kH % 2 == 0:
        kH -= 1

    # apply a Gaussian blur to the input image using our computed
    # kernel size
    return cv2.GaussianBlur(image, (kW, kH), 0)

def anonymize_face_pixelate(image, blocks=3):
    # divide the input image into NxN blocks
    (h, w) = image.shape[:2]
    xSteps = np.linspace(0, w, blocks + 1, dtype="int")
    ySteps = np.linspace(0, h, blocks + 1, dtype="int")

    # loop over the blocks in both the x and y direction
    for i in range(1, len(ySteps)):
        for j in range(1, len(xSteps)):
            # compute the starting and ending (x, y)-coordinates
            # for the current block
            startX = xSteps[j - 1]
            startY = ySteps[i - 1]
            endX = xSteps[j]
            endY = ySteps[i]

            # extract the ROI using NumPy array slicing, compute the
            # mean of the ROI, and then draw a rectangle with the
            # mean RGB values over the ROI in the original image
            roi = image[startY:endY, startX:endX]
            (B, G, R) = [int(x) for x in cv2.mean(roi)[:3]]
            cv2.rectangle(image, (startX, startY), (endX, endY),
                (B, G, R), -1)

    # return the pixelated blurred image
    return image
        
@app.get("/generate")
def generate(path: str):
    """
    Using the text summarization pipeline from `transformers`, summerize text
    from the given input text. The model used is `philschmid/bart-large-cnn-samsum`, which
    can be found [here](<https://huggingface.co/philschmid/bart-large-cnn-samsum>).
    """
    r = requests.get(path, stream=True)
    img = Image.open(io.BytesIO(r.content)).convert('RGB') 
    open_cv_image = np.array(img) 
    # Convert RGB to BGR 
    open_cv_image = open_cv_image[:, :, ::-1].copy()  # numpy array (width, hight, 3)
    image = open_cv_image # numpy array (width, hight, 3)
    orig = image.copy()
    (h, w) = image.shape[:2]

    # construct a blob from the image
    blob = cv2.dnn.blobFromImage(image, 1.0, (300, 300),(104.0, 177.0, 123.0))

    # pass the blob through the network and obtain the face detections
    logger.info("computing face detections...")
    net.setInput(blob)
    detections = net.forward()

    # loop over the detections
    for i in range(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with the
        # detection
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the confidence is greater
        # than the minimum confidence
        if confidence > args["confidence"]:
            # compute the (x, y)-coordinates of the bounding box for the
            # object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # extract the face ROI
            face = image[startY:endY, startX:endX]

            # check to see if we are applying the "simple" face blurring
            # method
            if args["method"] == "simple":
                face = anonymize_face_simple(face, factor=3.0)

            # otherwise, we must be applying the "pixelated" face
            # anonymization method
            else:
                face = anonymize_face_pixelate(face,blocks=args["blocks"])

            # store the blurred face in the output image
            image[startY:endY, startX:endX] = face

    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
    img = Image.fromarray(image)

    im_file = io.BytesIO()
    img.save(im_file, format="PNG")
    im_bytes = base64.b64encode(im_file.getvalue()).decode("utf-8") 
     
    # Return the generated text in a JSON response
    return {"output": im_bytes}