mabinhao/Face_Recognition
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Compare commits

merge into: mabinhao:master
Branches Tags
mabinhao:master mabinhao:DLib_Face_recognition_loong mabinhao:2021_11_09 mabinhao:classify_from_image mabinhao:use_mysql mabinhao:patch_customize_name mabinhao:for_issue_#10 mabinhao:for_patch mabinhao:customize_name
...
pull from: mabinhao:classify_from_image
Branches Tags
mabinhao:master mabinhao:DLib_Face_recognition_loong mabinhao:2021_11_09 mabinhao:classify_from_image mabinhao:use_mysql mabinhao:patch_customize_name mabinhao:for_issue_#10 mabinhao:for_patch mabinhao:customize_name

1 Commits
master ... classify_f

Author SHA1 Message Date
Xie, Zhengtian
93b8332555 face detect and classify from image 2020-10-16 11:04:20 +08:00
2 changed files with 54 additions and 81 deletions
Expand all files Collapse all files

BIN
data/data_faces_for_test/test_faces_1.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 88 KiB

135
face_reco_from_camera.py
View File

@ -6,7 +6,7 @@
# GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera # GitHub: https://github.com/coneypo/Dlib_face_recognition_from_camera
# Mail: coneypo@foxmail.com # Mail: coneypo@foxmail.com
# 摄像头实时人脸识别 / Real-time face detection and recognition # 人脸识别 / Real-time face detection and recognition from images
import dlib import dlib
import numpy as np import numpy as np
@ -110,103 +110,76 @@ class Face_Recognizer:
# self.name_known_list[4] ='xx'.encode('utf-8').decode() # self.name_known_list[4] ='xx'.encode('utf-8').decode()
# 处理获取的视频流，进行人脸识别 / Face detection and recognition from input video stream # 处理获取的视频流，进行人脸识别 / Face detection and recognition from input video stream
def process(self, stream): def process(self):
# 1. 读取存放所有人脸特征的 csv / Get faces known from "features.all.csv" # 1. 读取存放所有人脸特征的 csv / Get faces known from "features.all.csv"
if self.get_face_database(): if self.get_face_database():
while stream.isOpened():
print(">>> Frame start")
flag, img_rd = stream.read()
faces = detector(img_rd, 0)
kk = cv2.waitKey(1)
# 按下 q 键退出 / Press 'q' to quit
if kk == ord('q'):
break
else:
self.draw_note(img_rd)
self.current_frame_feature_list = []
self.current_frame_face_cnt = 0
self.current_frame_name_position_list = []
self.current_frame_name_list = []
# 2. 检测到人脸 / Face detected in current frame print(">>> Frame start")
if len(faces) != 0: img_rd = cv2.imread("data/data_faces_for_test/test_faces_1.jpg")
# 3. 获取当前捕获到的图像的所有人脸的特征 / Compute the face descriptors for faces in current frame faces = detector(img_rd, 1)
for i in range(len(faces)): self.draw_note(img_rd)
shape = predictor(img_rd, faces[i])
self.current_frame_feature_list.append(face_reco_model.compute_face_descriptor(img_rd, shape))
# 4. 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
print(">>>>>> For face", k+1, " in camera")
# 先默认所有人不认识，是 unknown / Set the default names of faces with "unknown"
self.current_frame_name_list.append("unknown")
# 每个捕获人脸的名字坐标 / Positions of faces captured # 2. 检测到人脸 / Face detected in current frame
self.current_frame_name_position_list.append(tuple( if len(faces) != 0:
[faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)])) # 3. 获取当前捕获到的图像的所有人脸的特征 / Compute the face descriptors for faces in current frame
for i in range(len(faces)):
shape = predictor(img_rd, faces[i])
self.current_frame_feature_list.append(face_reco_model.compute_face_descriptor(img_rd, shape))
# 4. 遍历捕获到的图像中所有的人脸 / Traversal all the faces in the database
for k in range(len(faces)):
print(">>>>>> For face", k+1, " in camera")
# 先默认所有人不认识，是 unknown / Set the default names of faces with "unknown"
self.current_frame_name_list.append("unknown")
# 5. 对于某张人脸，遍历所有存储的人脸特征 # 每个捕获人脸的名字坐标 / Positions of faces captured
# For every faces detected, compare the faces in the database self.current_frame_name_position_list.append(tuple(
current_frame_e_distance_list = [] [faces[k].left(), int(faces[k].bottom() + (faces[k].bottom() - faces[k].top()) / 4)]))
for i in range(len(self.feature_known_list)):
# 如果 person_X 数据不为空
if str(self.feature_known_list[i][0]) != '0.0':
print(" >>> With person", str(i + 1), ", the e distance: ", end='')
e_distance_tmp = self.return_euclidean_distance(self.current_frame_feature_list[k],
self.feature_known_list[i])
print(e_distance_tmp)
current_frame_e_distance_list.append(e_distance_tmp)
else:
# 空数据 person_X
current_frame_e_distance_list.append(999999999)
# 6. 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
similar_person_num = current_frame_e_distance_list.index(min(current_frame_e_distance_list))
print(" >>> Minimum e distance with ", self.name_known_list[similar_person_num], ": ", min(current_frame_e_distance_list))
if min(current_frame_e_distance_list) < 0.4: # 5. 对于某张人脸，遍历所有存储的人脸特征
self.current_frame_name_list[k] = self.name_known_list[similar_person_num] # For every faces detected, compare the faces in the database
print(" >>> Face recognition result: " + str(self.name_known_list[similar_person_num])) current_frame_e_distance_list = []
else: for i in range(len(self.feature_known_list)):
print(" >>> Face recognition result: Unknown person") # 如果 person_X 数据不为空
if str(self.feature_known_list[i][0]) != '0.0':
# 矩形框 / Draw rectangle print(" >>> With person", str(i + 1), ", the e distance: ", end='')
for kk, d in enumerate(faces): e_distance_tmp = self.return_euclidean_distance(self.current_frame_feature_list[k],
# 绘制矩形框 self.feature_known_list[i])
cv2.rectangle(img_rd, tuple([d.left(), d.top()]), tuple([d.right(), d.bottom()]), print(e_distance_tmp)
(0, 255, 255), 2) current_frame_e_distance_list.append(e_distance_tmp)
else:
self.current_frame_face_cnt = len(faces) # 空数据 person_X
current_frame_e_distance_list.append(999999999)
# 7. 在这里更改显示的人名 / Modify name if needed # 6. 寻找出最小的欧式距离匹配 / Find the one with minimum e distance
# self.show_chinese_name() similar_person_num = current_frame_e_distance_list.index(min(current_frame_e_distance_list))
print(" >>> Minimum e distance with ", self.name_known_list[similar_person_num], ": ", min(current_frame_e_distance_list))
# 8. 写名字 / Draw name
img_with_name = self.draw_name(img_rd)
if min(current_frame_e_distance_list) < 0.4:
self.current_frame_name_list[k] = self.name_known_list[similar_person_num]
print(" >>> Face recognition result: " + str(self.name_known_list[similar_person_num]))
else: else:
img_with_name = img_rd print(" >>> Face recognition result: Unknown person")
# 矩形框 / Draw rectangle
for kk, d in enumerate(faces):
# 绘制矩形框
cv2.rectangle(img_rd, tuple([d.left(), d.top()]), tuple([d.right(), d.bottom()]),
(0, 255, 255), 2)
self.current_frame_face_cnt = len(faces)
img_rd = self.draw_name(img_rd)
print(">>>>>> Faces in camera now:", self.current_frame_name_list) print(">>>>>> Faces in camera now:", self.current_frame_name_list)
cv2.imshow("camera", img_with_name) cv2.imshow("camera", img_rd)
cv2.waitKey(0)
# 9. 更新 FPS / Update stream FPS
self.update_fps()
print(">>> Frame ends\n\n") print(">>> Frame ends\n\n")
# OpenCV 调用摄像头并进行 process
def run(self):
cap = cv2.VideoCapture(0)
# cap = cv2.VideoCapture("video.mp4")
cap.set(3, 480) # 640x480
self.process(cap)
cap.release()
cv2.destroyAllWindows()
def main(): def main():
Face_Recognizer_con = Face_Recognizer() Face_Recognizer_con = Face_Recognizer()
Face_Recognizer_con.run() Face_Recognizer_con.process()
if __name__ == '__main__': if __name__ == '__main__':