12강 얼굴 인식

Pyhton을 통해 얼굴인식 해보자

여기서 핵심은 의 이해가 필요하다 net = cv2.dnn.readNetFromCaffe(“deploy.prototxt”, “res10_300x300_ssd_iter_140000_fp16.caffemodel”) blob = cv2.dnn.blobFromImage(frame, 1.0, (in_width, in_height), mean, swapRB = False, crop = False

1. 함수 모듈 호출

   import cv2
   import sys
   

2. 변수 값 받아오기 만약 python에서 변수가 없으면 카메라 영상 데이터를 가져온다.

s = 0
if len(sys.argv) > 1:
    s = sys.argv[1]

source = cv2.VideoCapture(s)

참고 사항

참고로 컴퓨터로 동작하고 싶은데 나는 USB 카메라가 없어요 하는 경우 휴대폰에서 Ip webCam을 다운받아 사용하는데 python 파일명 http://XXX.XXX.XX.XX:8080/video 실행하면된다.

1. 딥러닝 자료 가져오기 추후 내가 caffemodel 자료 만드는 방법을 알고 싶은데 우선 만들어진 자료를 가져와 사용한다. ```python win_name = ‘Camera Preview’ cv2.namedWindow(win_name, cv2.WINDOW_NORMAL)

net = cv2.dnn.readNetFromCaffe(“deploy.prototxt”, “res10_300x300_ssd_iter_140000_fp16.caffemodel”)

4. 모델 변수 적용

```python
# Model parameters
in_width = 300
in_height = 300
mean = [104, 117, 123]
conf_threshold = 0.7

while cv2.waitKey(1) != 27:
    has_frame, frame = source.read()
    if not has_frame:
        break
    frame = cv2.flip(frame,1)
    frame_height = frame.shape[0]
    frame_width = frame.shape[1]

    # Create a 4D blob from a frame.
    blob = cv2.dnn.blobFromImage(frame, 1.0, (in_width, in_height), mean, swapRB = False, crop = False)
    # Run a model
    net.setInput(blob)
    detections = net.forward()

    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > conf_threshold:
            x_left_bottom = int(detections[0, 0, i, 3] * frame_width)
            y_left_bottom = int(detections[0, 0, i, 4] * frame_height)
            x_right_top = int(detections[0, 0, i, 5] * frame_width)
            y_right_top = int(detections[0, 0, i, 6] * frame_height)

            cv2.rectangle(frame, (x_left_bottom, y_left_bottom), (x_right_top, y_right_top), (0, 255, 0))
            label = "Confidence: %.4f" % confidence
            label_size, base_line = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)

            cv2.rectangle(frame, (x_left_bottom, y_left_bottom - label_size[1]),
                                (x_left_bottom + label_size[0], y_left_bottom + base_line),
                                (255, 255, 255), cv2.FILLED)
            cv2.putText(frame, label, (x_left_bottom, y_left_bottom),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    t, _ = net.getPerfProfile()
    label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
    cv2.putText(frame, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
    cv2.imshow(win_name, frame)

source.release()
cv2.destroyWindow(win_name)

전체 소스코드

import cv2
import sys

s = 0
if len(sys.argv) > 1:
    s = sys.argv[1]

source = cv2.VideoCapture(s)

win_name = 'Camera Preview'
cv2.namedWindow(win_name, cv2.WINDOW_NORMAL)

net = cv2.dnn.readNetFromCaffe("deploy.prototxt",
                               "res10_300x300_ssd_iter_140000_fp16.caffemodel")
# Model parameters
in_width = 300
in_height = 300
mean = [104, 117, 123]
conf_threshold = 0.7

while cv2.waitKey(1) != 27:
    has_frame, frame = source.read()
    if not has_frame:
        break
    frame = cv2.flip(frame,1)
    frame_height = frame.shape[0]
    frame_width = frame.shape[1]

    # Create a 4D blob from a frame.
    blob = cv2.dnn.blobFromImage(frame, 1.0, (in_width, in_height), mean, swapRB = False, crop = False)
    # Run a model
    net.setInput(blob)
    detections = net.forward()

    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > conf_threshold:
            x_left_bottom = int(detections[0, 0, i, 3] * frame_width)
            y_left_bottom = int(detections[0, 0, i, 4] * frame_height)
            x_right_top = int(detections[0, 0, i, 5] * frame_width)
            y_right_top = int(detections[0, 0, i, 6] * frame_height)

            cv2.rectangle(frame, (x_left_bottom, y_left_bottom), (x_right_top, y_right_top), (0, 255, 0))
            label = "Confidence: %.4f" % confidence
            label_size, base_line = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)

            cv2.rectangle(frame, (x_left_bottom, y_left_bottom - label_size[1]),
                                (x_left_bottom + label_size[0], y_left_bottom + base_line),
                                (255, 255, 255), cv2.FILLED)
            cv2.putText(frame, label, (x_left_bottom, y_left_bottom),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    t, _ = net.getPerfProfile()
    label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
    cv2.putText(frame, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
    cv2.imshow(win_name, frame)

source.release()
cv2.destroyWindow(win_name)