opencv 48 googleNet face detection

code link: https://github.com/chuanshuoge6/googleNet-face

#googleNet_face.py

import os

import numpy as np

import argparse

import cv2

# construct the argument parse and parse the arguments

ap = argparse.ArgumentParser()

ap.add_argument("-p", "--prototxt", default="googleNet\\deploy.prototxt",

                help="path to Caffe 'deploy' prototxt file")

ap.add_argument("-m", "--model",

                default="googleNet\\res10_300x300_ssd_iter_140000.caffemodel",

                help="path to Caffe pre-trained model")

ap.add_argument("-c", "--confidence", type=float, default=0.5,

                help="minimum probability to filter weak detections")

args = vars(ap.parse_args())

# load our serialized model from disk

print("[INFO] loading model...")

net = cv2.dnn.readNetFromCaffe(args["prototxt"], args["model"])

cap = cv2.VideoCapture("assets/fashion.mp4")

j = 0

while True:

    ret, frame = cap.read()

    w = int(cap.get(3))

    h = int(cap.get(4))

    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0,

                                 (300, 300), (104.0, 177.0, 123.0))

    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

        # prediction

        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")

            # draw the bounding box of the face along with the associated

            # probability

            text = "{:.2f}%".format(confidence * 100)

            y = startY - 10 if startY - 10 > 10 else startY + 10

            cv2.rectangle(frame, (startX, startY), (endX, endY),

                          (0, 0, 255), 2)

            cv2.putText(frame, text, (startX, y),

                        cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)

    cv2.imshow('frame', frame)

    path = 'C:/Users/zchen/PycharmProjects/opencv/googleNet/record'

    name = str(j) + ".jpg"

    cv2.imwrite(os.path.join(path , name), frame)

    j += 1

    if cv2.waitKey(1) == ord('q'):

        break

    if cv2.waitKey(1) == ord('p'):

        cv2.waitKey(-1)  # wait until any key is pressed

cap.release()

cv2.destroyAllWindows()

-------------------

#video_writer.py

import os

import cv2

import glob

img_dict = {}

for filename in glob.glob('C:/Users/zchen/PycharmProjects/opencv/googleNet/record/*.jpg'):

    img = cv2.imread(filename)

    height, width, layers = img.shape

    size = (width, height)

    img_dict[filename.split("\\")[1]] = img

    #print(img_dict)

    print("loading image " + str(len(img_dict)))

path = 'C:/Users/zchen/PycharmProjects/opencv/googleNet'

out = cv2.VideoWriter(os.path.join(path , "fashion_face_detection.avi"), cv2.VideoWriter_fourcc(*'DIVX'), 60, size)

for i in range(len(img_dict)):

    key = str(i) + ".jpg"

    out.write(img_dict[key])

    print("processing image " + str(i))

out.release()

reference:

https://github.com/sr6033/face-detection-with-OpenCV-and-DNN

video writer

https://theailearner.com/2018/10/15/creating-video-from-images-using-opencv-python/

googleNet

http://chuanshuoge2.blogspot.com/2021/05/opencv-47-googlenet.html