调用笔记本的摄像头实现基于opencv的视频人脸识别（中文显示和英文显示）以及 index 480 is out of bounds for axis 0 with size 480错误的解决

@人脸识别代码和一些常见错误

基于opencv的视频人脸识别（中文显示）以及 index 480 is out of bounds for axis 0 with size 480错误的解决

参考了
https://github.com/niehen6174/face-recognition-and-put-in-chinese
上述代码中采用的是海康的摄像头，这里我用的是自己笔记本的摄像头。
直接使用会显示数组溢出，这里会有一些修改的部分
报错 index 480 is out of bounds for axis 0 with size 480的解决见代码后面的修改部分
直接运行下述代码应该不会报错

ft2（处理中文识别）

# -*- coding: utf-8 -*-
# http://blog.csdn.net/zizi7/article/details/70145150

'''
##################################################
# tools                                          #
#------------------------------------------------#
# draw chinese text using freetype on python2.x  #                  #
# 2017.4.12                                      #
##################################################
'''
                                                              
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, x, y,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, str):
            #对于Python 2中的unicode和Python 3中的str，对于Python 2中的str/bytes和Python 3中的bytes的二进制文件
            text = text.decode('utf-8')
        img = self.draw_string(image,x,y+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)*0x10000), int(0.2*0x10000),\
                                 int(0.0*0x10000), int(1.1*0x10000))
        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('diplay', image)
    cv2.waitKey(0)

修改的部分是第44行的，就是这里的数组出现了问题。

img = self.draw_string(image,x,y+ypos, text, text_color)

face_mobilevideo实现人脸识别，按下S键可拍照并保存。

# -*- coding: utf-8 -*-
# 摄像头头像识别
import face_recognition
import cv2
import ft2
from PIL import Image, ImageDraw, ImageFont
import numpy as np

cam = cv2.VideoCapture(0)
# 本地图像
kxs_image = face_recognition.load_image_file("kxs.jpg")
kxs_face_encoding = face_recognition.face_encodings(kxs_image)[0]

# 本地图像二
wsp_image = face_recognition.load_image_file("wsp.jpg")
wsp_face_encoding = face_recognition.face_encodings(wsp_image)[0]

# 本地图片三2
pr_image = face_recognition.load_image_file("pr.jpg")
pr_face_encoding = face_recognition.face_encodings(pr_image)[0]

# Create arrays of known face encodings and their names
# 脸部特征数据的集合
known_face_encodings = [
    kxs_face_encoding,
    wsp_face_encoding,
    pr_face_encoding
]

# 人物名称的集合
"""""
known_face_names = [
    "kxs",
    "wsp",
    "panrui"
]
"""""
known_face_names = [
    "匡",
    "王",
    "潘"
]
face_locations = []
face_encodings = []
face_names = []
process_this_frame = True


while(cam.isOpened()):
    # 读取摄像头画面
    ret, frame = cam.read()
    if not ret:
        #等同于 if ret is not none
        break
    sucess, img = cam.read()
    k = cv2.waitKey(1)
    if k == 27:
        # 通过esc键退出摄像
        cv2.destroyAllWindows()
        break
    elif k == ord("s"):
        # 通过s键保存图片，并退出。
        num = 1
        cv2.imwrite("image%s.jpg" % num, img)
        num+=1;
        print("ok")
        #cv2.destroyAllWindows()
        break
    # 改变摄像头图像的大小，图像小，所做的计算就少
    small_frame = cv2.resize(frame, (0, 0), fx=0.33, fy=0.33)

    # opencv的图像是BGR格式的，而我们需要是的RGB格式的，因此需要进行一个转换。
    rgb_small_frame = small_frame[:, :, ::-1]

    # Only process every other frame of video to save time
    if process_this_frame:
        # 根据encoding来判断是不是同一个人，是就输出true，不是为flase
        face_locations = face_recognition.face_locations(rgb_small_frame)
        face_encodings = face_recognition.face_encodings(rgb_small_frame, face_locations)

        face_names = []
        for face_encoding in face_encodings:
            # 默认为unknown
            matches = face_recognition.compare_faces(known_face_encodings, face_encoding,tolerance=0.48)
            #阈值太低容易造成无法成功识别人脸，太高容易造成人脸识别混淆 默认阈值tolerance为0.6
            #print(matches)
            name = "Unknown"

            # if match[0]:
            #     name = "michong"
            # If a match was found in known_face_encodings, just use the first one.
            if True in matches:
                first_match_index = matches.index(True)
                name = known_face_names[first_match_index]

            face_names.append(name)

    process_this_frame = not process_this_frame

    # 将捕捉到的人脸显示出来
    for (top, right, bottom, left), name in zip(face_locations, face_names):
        # Scale back up face locations since the frame we detected in was scaled to 1/4 size
        #由于我们检测到的帧被缩放到1/4大小，所以要缩小面位置
        top *= 3
        right *= 3
        bottom *= 3
        left *= 3

        cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 3)
        print(name)
        ft = ft2.put_chinese_text('msyh.ttf')
        #引入ft2中的字体
        #加上标签
        xpos=left+10
        ypos=bottom
        frame = ft.draw_text(frame,xpos,ypos,name, 20, (255, 255, 255))
       


    cv2.imshow('monitor', frame)
    if cv2.waitKey(1) & 0xFF == 27:
        break

cam.release()
cv2.destroyAllWindows()

修改的部分是120行左右的

		xpos=left+10
        ypos=bottom
        frame = ft.draw_text(frame,xpos,ypos,name, 20, (255, 255, 255))

只输出英文（把上面的输出文字改为下面的代码即可）

cv2.putText(frame, name, (left + 6, bottom - 6), 000, 0.8, (255, 255, 255), 1)  # 这是不输入汉字时可以用的代码

报错

** index 480 is out of bounds for axis 0 with size 480**
就按我上面的修改就不会出错了。

代码文件下载

https://github.com/horsein/-python_face_recognition–/tree/main