1.pip install opencv
2.pip install face_recognition
3.通过摄像头实时在获取的帧上进行人脸识别(较卡顿)
facerecognition.py
# -*- coding: UTF-8 -*-
import face_recognition
import cv2
import os
import ft2
#中文支持,加载微软雅黑字体
ft = ft2.put_chinese_text('msyh.ttf')
# 获取摄像头# 0(默认)
video_capture = cv2.VideoCapture(0)
# 加载待识别人脸图像并识别。
basefacefilespath ="images"#faces文件夹中放待识别任务正面图,文件名为人名,将显示于结果中
baseface_titles=[] #图片名字列表
baseface_face_encodings=[] #识别所需人脸编码结构集
#读取人脸资源
for fn in os.listdir(basefacefilespath): #fn 人脸文件名
baseface_face_encodings.append(face_recognition.face_encodings(face_recognition.load_image_file(basefacefilespath+"/"+fn))[0])
fn=fn[:(len(fn)-4)]
baseface_titles.append(fn)#
while True:
# 获取一帧视频
ret, frame = video_capture.read()
# 人脸检测,并获取帧中所有人脸编码
face_locations = face_recognition.face_locations(frame)
face_encodings = face_recognition.face_encodings(frame, face_locations)
# 遍历帧中所有人脸编码
for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
# 与baseface_face_encodings匹配否?
for i,v in enumerate(baseface_face_encodings):
match = face_recognition.compare_faces([v], face_encoding,tolerance=0.5)
name = "?"
if match[0]:
name = baseface_titles[i]
break
name=unicode(name,'gb2312')#gbk is also ok.
print(name)
# 围绕脸的框
cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
# 框下的名字(即,匹配的图片文件名)
cv2.rectangle(frame, (left, bottom), (right, bottom+35), (0, 0, 255), cv2.FILLED)
frame = ft.draw_text(frame, (left + 2, bottom + 12), name, 16, (255, 255, 255))
# show结果图像
cv2.imshow('Video', frame)
# 按q退出
if cv2.waitKey(1) & 0xFF == ord('q'):
break
# 释放摄像头中的流
video_capture.release()
cv2.destroyAllWindows()
ft2.py
# -*- coding: utf-8 -*-
import numpy as np
import freetype
import copy
import pdb
class put_chinese_text(object):
def __init__(self, ttf):
self._face = freetype.Face(ttf)
def draw_text(self, image, pos, text, text_size, text_color):
'''
draw chinese(or not) text with ttf
:param image: image(numpy.ndarray) to draw text
:param pos: where to draw text
:param text: the context, for chinese should be unicode type
:param text_size: text size
:param text_color:text color
:return: image
'''
self._face.set_char_size(text_size * 64)
metrics = self._face.size
ascender = metrics.ascender/64.0
#descender = metrics.descender/64.0
#height = metrics.height/64.0
#linegap = height - ascender + descender
ypos = int(ascender)
if not isinstance(text, unicode):
text = text.decode('utf-8')
img = self.draw_string(image, pos[0], pos[1]+ypos, text, text_color)
return img
def draw_string(self, img, x_pos, y_pos, text, color):
'''
draw string
:param x_pos: text x-postion on img
:param y_pos: text y-postion on img
:param text: text (unicode)
:param color: text color
:return: image
'''
prev_char = 0
pen = freetype.Vector()
pen.x = x_pos << 6 # div 64
pen.y = y_pos << 6
hscale = 1.0
matrix = freetype.Matrix(int(hscale)*0x10000L, int(0.2*0x10000L),\
int(0.0*0x10000L), int(1.1*0x10000L))
cur_pen = freetype.Vector()
pen_translate = freetype.Vector()
image = copy.deepcopy(img)
for cur_char in text:
self._face.set_transform(matrix, pen_translate)
self._face.load_char(cur_char)
kerning = self._face.get_kerning(prev_char, cur_char)
pen.x += kerning.x
slot = self._face.glyph
bitmap = slot.bitmap
cur_pen.x = pen.x
cur_pen.y = pen.y - slot.bitmap_top * 64
self.draw_ft_bitmap(image, bitmap, cur_pen, color)
pen.x += slot.advance.x
prev_char = cur_char
return image
def draw_ft_bitmap(self, img, bitmap, pen, color):
'''
draw each char
:param bitmap: bitmap
:param pen: pen
:param color: pen color e.g.(0,0,255) - red
:return: image
'''
x_pos = pen.x >> 6
y_pos = pen.y >> 6
cols = bitmap.width
rows = bitmap.rows
glyph_pixels = bitmap.buffer
for row in range(rows):
for col in range(cols):
if glyph_pixels[row*cols + col] != 0:
img[y_pos + row][x_pos + col][0] = color[0]
img[y_pos + row][x_pos + col][1] = color[1]
img[y_pos + row][x_pos + col][2] = color[2]
if __name__ == '__main__':
# just for test
import cv2
line = '你好'
img = np.zeros([300,300,3])
color_ = (0,255,0) # Green
pos = (3, 3)
text_size = 24
#ft = put_chinese_text('wqy-zenhei.ttc')
ft = put_chinese_text('msyh.ttf')
image = ft.draw_text(img, pos, line, text_size, color_)
cv2.imshow('ss', image)
cv2.waitKey(0)
将msyh.ttf 微软雅黑字体文件copy到同级目录,在同级images文件夹下,以人名命名正面脸图.
运行, python facerecognition.py
卡顿,跳帧,
结果如图:
base faces
识别: