Implementing an HTTP endpoint to perform face detection on a single image
Before working with WebSockets, we'll start simple and implement, using FastAPI, a classic HTTP endpoint for accepting image uploads and performing face detection on them. As you'll see, the main difference from the previous example is in how we acquire the image: instead of streaming it from the webcam, we get it from a file upload that we have to convert into an OpenCV image object.
You can see the whole implementation in the following code:
chapter14_api.py
from typing import List, Tuple
import cv2
import numpy as np
from fastapi import FastAPI, File, UploadFile
from pydantic import BaseModel
app = FastAPI()
cascade_classifier = cv2.CascadeClassifier()
class Faces(BaseModel):
faces: List[Tuple[int, int, int, int]]
@app.post("/face-detection", response_model=Faces)
async def face_detection(image: UploadFile = File(...)) -> Faces:
...
