take-pics.py

from imutils.video import VideoStream
import numpy as np
import imutils
import time
import cv2
import os

# load model from disk
print('Loading model..')
net = cv2.dnn.readNetFromCaffe('model_weights/deploy.prototxt.txt',
        'model_architecture/res10_300x300_ssd_iter_140000.caffemodel')

confidence_d = 0.5

# Initialize video stream
print('Starting video stream')
vs = VideoStream(src=0).start()
time.sleep(1.0)
total = 0

name = input('What is your name: ')

destination = f"./dataset/{name}"

#check existence of folder 
def does_folder_exist():
    pass

# Keep frame open to capture images
while True:
    #Grab frame and resize
    frame = vs.read()

    orig = frame.copy()

    frame = imutils.resize(frame,width=400)

    #grab frame dimensions and convert it to a blob
    (h,w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(cv2.resize(frame,(300,300)),1.0,
    (300,300),(104.0,177.0,123.0))

    #pass the blob through the network and obtain predictions
    net.setInput(blob)
    detections = net.forward()

    print(detections)

    #loop over the detections
    for i in range(0, detections.shape[2]):
        #extract confidence

        confidence = detections[0,0,i,2]

        #filter out weak detections by ensuring the confidence 
        #greater than minimum confidence
        if confidence < confidence_d:
            continue

        box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
        (startX, startY, endX, endY) = box.astype("int")

        text = f"{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)

    #show output frame
    cv2.imshow("Frame",frame)
    key = cv2.waitKey(1) & 0xFF

    #if the q key was pressed, break from the loop
    if key == ord(' '):
        # if os.path.isdir("dataset"):
        #     pass
        # else: 
        #     os.mkdir('dataset')
        p = os.path.sep.join([destination,f"{name}_{str(total).zfill(5)}.png"])
        cv2.imwrite(p, orig)
        total += 1
        print(f"Captured {total} image(s)")

    elif key == ord("q"):
        print("quiting program")
        break

# do a bit of cleanup
cv2.destroyAllWindows()
vs.stop()