由於在計算機視覺或者說人臉識別領域，我也是剛瞭解一些，以下都是我看了相關視訊和文章以後得出的個人看法和觀點． 主要有以下幾個步驟： 抽取人臉圖片的主要特徵 進行區域性特徵分析 生成特徵臉 基於彈性模型 隱馬爾可夫模型 １．用pip安裝對應的包 face_recognition,cv2

face_picture.py

# -*- coding: utf-8 -*-
import face_recognition
import cv2

# 讀取圖片
img = face_recognition.load_image_file("/home/zq/Pictures/o_neo.jpg")
# 得到人臉座標
 

face_locations = face_recognition.face_locations(img)
print(face_locations)

# 顯示原始圖片
img = cv2.imread("/home/zq/Pictures/o_neo.jpg")
cv2.namedWindow("original")
cv2.imshow("original", img)

# 遍歷每個人臉
faceNum = len(face_locations)
for i in range(0, faceNum):
    top = face_locations[i][0]
    right = face_locations[
 
i][1]
    bottom = face_locations[i][2]
    left = face_locations[i][3]

    start = (left, top)
    end = (right, bottom)
    color = (247, 230, 16)
    thickness = 2
    cv2.rectangle(img, start, end, color, thickness)

# 顯示識別後的圖片
cv2.namedWindow("recognition")
cv2.imshow("recognition", img)

cv2.waitKey(
 
0)
cv2.destroyAllWindows()

face_video.py

# -*- coding: utf-8 -*-
import face_recognition
import cv2
from gevent import os
import freetype
import copy

from numpy import unicode


class ChineseTextUtil(object):
    def __init__(self, ttf):
        self._face = freetype.Face(ttf)

    def draw_text(self, image, pos, text, text_size, text_color):
        '''
        使用ttf字型庫中的字型設定姓名
        :param image:     用於將text生成在某個image影象上
        :param pos:       畫text的位置
        :param text:      unicode編碼的text
        :param text_size: 字型大小
        :param text_color:字型顏色
        :return:          返回點陣圖
        '''
        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.string_2_bitmap(image, pos[0], pos[1], text, text_color)
        return img

    def string_2_bitmap(self, img, x_pos, y_pos, text, color):
        '''
        將字串繪製為圖片
        :param x_pos: text繪製的x起始座標
        :param y_pos: text繪製的y起始座標
        :param text:  text的unicode編碼
        :param color: text的RGB顏色編碼
        :return:      返回image點陣圖
        '''
        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: 點陣圖
        :param pen:    畫筆
        :param color:  畫筆顏色
        :return:       返回加工後的點陣圖
        '''
        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__':
    # 讀取圖片識別樣例
    face_file_list = []
    names_list = []
    face_encoding_list = []

    rootdir = '/Users/z/Desktop/group_face1/'
    list = os.listdir(rootdir)
    for i in range(0, len(list)):
        path = os.path.join(rootdir, list[i])
        if os.path.isfile(path) and ".jpg" in list[i]:
            face_file_list.append(rootdir + list[i])
            print(list[i][:-4])
            names_list.append(list[i][:-4])

    for path in face_file_list:
        print(path)
        face_image = face_recognition.load_image_file(path)
        face_encoding = face_recognition.face_encodings(face_image)[0]
        face_encoding_list.append(face_encoding)

    # 初始化一些變數用於，面部位置，編碼，姓名等
    face_locations = []
    face_encodings = []
    face_names = []
    process_this_frame = True

    video_capture = cv2.VideoCapture(0)
    while True:
        # 得到當前攝像頭拍攝的每一幀
        ret, frame = video_capture.read()

        # 縮放當前幀到4分支1大小，以加快識別程序的效率
        small_frame = cv2.resize(frame, (0, 0), fx=0.25, fy=0.25)

        # 每次只處理當前幀的視訊，以節省時間
        if process_this_frame:
            # 在當前幀中，找到所有的面部的位置以及面部的編碼
            face_locations = face_recognition.face_locations(small_frame)
            face_encodings = face_recognition.face_encodings(small_frame, face_locations)

            face_names = []
            for face_encoding in face_encodings:
                # 找到能夠與已知面部匹配的面部
                match = face_recognition.compare_faces(face_encoding_list, face_encoding, 0.6)
                name = "Unknown"

                for i in range(0, len(match)):
                    if match[i]:
                        name = names_list[i]
                        face_names.append(name)

        process_this_frame = not process_this_frame

        # 顯示結果
        for (top, right, bottom, left), name in zip(face_locations, face_names):
            # 將剛才縮放至4分支1的幀恢復到原來大小，並得到與每一個面部與姓名的對映關係
            top *= 4
            right *= 4
            bottom *= 4
            left *= 4

            # 在臉上畫一個框框
            cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)

            # 在框框的下邊畫一個label用於顯示姓名
            cv2.rectangle(frame, (left, bottom - 35), (right, bottom), (0, 0, 255), cv2.cv.CV_FILLED)
            font = cv2.FONT_HERSHEY_DUPLEX

            # 在當前幀中顯示我們識別的結果
            color_ = (255, 255, 255)
            pos = (left + 6, bottom - 6)
            text_size = 24
            # 使用自定義字型
            ft = ChineseTextUtil('wqy-zenhei.ttc')
            image = ft.draw_text(frame, pos, name, text_size, color_)

            cv2.imshow('VideoZH', image)

            # cv2.putText(frame, name, (left + 6, bottom - 6), font, 1.0, (255, 255, 255), 1)
            # cv2.imshow('Video', frame)

        # 按q退出
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    # 釋放資源
    video_capture.release()
    cv2.destroyAllWindows()

後面還需進一步研究．