上海网站制作公司是什么,WordPress整合phpems,全国建设部网站,房地产公司基本介绍文章目录前言原理项目结构编码配置主控函数人脸采集模块特征提取识别测试前言
2023-3-18 天小雨#xff0c;午觉舒适程度5颗星。任务完成指数2颗星。续接上文#xff1a;《MidiaPipe stgcn#xff08;时空图卷积网络#xff09;实现人体姿态判断#xff08;单目标#x…
文章目录前言原理项目结构编码配置主控函数人脸采集模块特征提取识别测试前言
2023-3-18 天小雨午觉舒适程度5颗星。任务完成指数2颗星。续接上文《MidiaPipe stgcn时空图卷积网络实现人体姿态判断单目标》我们这边需要实现的是一个多目标的检测并且我们期望能够适用在家庭这里领域因此在前者算法改进的基础上我们还需要加入这个人脸识别模块。调某度这些现成的开发的API当然可以但是自己搭建价更高能装13还不用小钱钱数据牢牢在手主打的就是一个安全。
同样的我们还是按照以前的习惯一个模块一个模块来进行说明写完之后的话再进行完整版本的开源但是每一个独立的模块都是开源直接使用的这个可以放心也就是说按照本文给到项目结构和代码是可以直接复现运行的。但是这里声明一下这个项目是一个综合项目有算法有前端有后端技术体系覆盖vue , pythonfastapijava(SpringBoot)开发这里开源的模块是算法模块。其他的模块不开源因为这个也是我们技术团队做的一个大创项目同时这个项目也不算是个小项目里面覆盖的技术不少需要同时具备Python和Java开发能力以及以Python为体现的人工智能应用开发能力所以就算开源全部模块对于读者的要求是比较高的。
之后我要说明的一点是本篇文章中的相当一部分代码其实是通过NewBing和ChatGPT生成的使用的第三方库是dlib我的工作是负责将这些代码进行整合修改测试调整。
原理
首先这个人脸识别的原理的话这个说实话相关的博文已经烂大街了所以这里就简简单单的过一下。这里的话就主要说到我们这个自己用到的这个方法因为相关的方法其实挺多了。那么原理的话首先是这个样子的
首先这个是一张图片 然后我们识别出它的脸部也就是这样 然后呢我们提取出脸部的68个关键点 然后呢我们在这个基础上提取出长度为128的特征向量
之后呢我们进行对比的时候呢先识别出一个人A按照同样的流程拿到A的128的特征向量然后呢我们把这个向量和我们已经存起来了的向量给进行一个对比也就是计算一下欧氏距离然后呢得到一个组距离然后我们得到距离最小的那个对应的名字就好了。
流程呢大概就是这样的 项目结构
都说了是个大工厂哈所以项目结构是这样的 这里的话有三个文件注意一下 然后这个依赖模型的话可以在这里拿到也可以自己去下载 链接https://pan.baidu.com/s/1PQOj_gPkTN9Od1PQDbeCtw 提取码6666
其他的自己按照结构去创建就好了。
编码
okey, 现在流程搞清楚了那么就开始组装代码了。
配置
首先是我们的这个配置项。
import dlib
import os
人脸识别配置class FACE_FILE(object):shape_predictor_pathalg/faceRec/data/data_dlib/shape_predictor_68_face_landmarks.datrecognition_model_pathalg/faceRec/data/data_dlib/dlib_face_recognition_resnet_model_v1.datcsv_base_pathalg/faceRec/data/csv/features.csvfaceData_pathalg/faceRec/data/faceData/points_faceData_pathalg/faceRec/data/faceData_points/faceName_pathalg/faceRec/data/faceName.txtimgs_folder_pathos.listdir(alg/faceRec/data/faceData/)FACE_CONFIG{max_collection_image: 50,get_points_faceData_flag: True,import_all_features_flag:True,face_needTo_update:[x for x in range(1, 2)], #选择更新脸部的编号从0开始num_of_person_in_lib:len(FACE_FILE.imgs_folder_path),recognition_threshold:0.43,predictor: dlib.shape_predictor(FACE_FILE.shape_predictor_path),recognition_model: dlib.face_recognition_model_v1(FACE_FILE.recognition_model_path),detector:dlib.get_frontal_face_detector(),
}目标检测配置DECTION_CONFIG{}主控函数
之后的我们先来看到我们的这个主控函数是如何操作的。 我们这边的任何操作都只能在主控文件同级目录下进行调用原因无他这个路径的问题必须要进行一个统一。 import cv2 as cvfrom client.server.alg.faceRec.buildFace import BuildFace
from client.server.alg.faceRec.collection import Collection
from client.server.alg.faceRec.detectFace import DetectFacedef collection_face():cam cv.VideoCapture(0)Collection().collection_cramer(cam)cam.release()cv.destroyAllWindows()print(采集完毕,程序退出!!)def build_face():build BuildFace()build.building_all()def detect_face():cam cv.VideoCapture(0)process DetectFace()process.detect_from_cam(cam)
if __name__ __main__:# collection_face()# build_face()detect_face()调用的话其实非常简单所以非常容易就可以做整合用在具体的功能模块当中。
人脸采集模块
接下来就是我们的这个采集模块作用很简单就是读取到视频流然后呢去识别到头像然后裁剪然后保存在目录下 负责收集人脸关键点位import cv2 as cv
import time
import os
from client.server.config import FACE_FILE,FACE_CONFIGclass Collection(object):提供两种解析方式1. 通过opencv的VideoCapture 进行读取然后得到图像2. 通过图像进行解析读取同时得到框出头像之后的图像def __init__(self):self.start_time 0self.fps 0self.image Noneself.face_img Noneself.face_num 0self.last_face_num 0self.face_num_change_flag Falseself.quit_flag Falseself.buildNewFolder False # 按下n新建文件夹标志位self.save_flag False # 按下“s”保存人脸数据标志位self.face_flag Falseself.img_num 0self.collect_face_data Truedef get_fps(self):now time.time()time_period now - self.start_timeself.fps 1.0 / time_periodself.start_time nowcolor (0,255,0)if self.fps 15:color (0,0,255)cv.putText(self.image, str(self.fps.__round__(2)), (20, 50), cv.FONT_HERSHEY_DUPLEX, 1, color)def save_face_image(self,build_path):buildFile build_pathif(not build_path):buildFile FACE_FILE.faceData_path person_{}.format(FACE_CONFIG.get(num_of_person_in_lib))if(os.path.exists(buildFile)):self.buildNewFolder Trueelse:os.makedirs(buildFile)FACE_CONFIG[num_of_person_in_lib] FACE_CONFIG.get(num_of_person_in_lib) 1print(存放人脸数据的文件夹创建成功)self.buildNewFolder Trueif (self.collect_face_data True and self.buildNewFolder True):if (self.face_img.size 0):cv.imwrite(FACE_FILE.faceData_path person_{}/{}.png.format(FACE_CONFIG.get(num_of_person_in_lib) - 1, self.img_num),self.face_img)self.img_num 1def key_scan(self, key):if self.collect_face_data True:if self.save_flag True and self.buildNewFolder True:if self.face_img.size 0:cv.imwrite(FACE_FILE.faceData_path person_{}/{}.png.format(FACE_CONFIG.get(num_of_person_in_lib) - 1, self.img_num),self.face_img)self.img_num 1if key ord(s):self.save_flag not self.save_flagif key ord(n):os.makedirs(FACE_FILE.faceData_path person_{}.format(FACE_CONFIG.get(num_of_person_in_lib)))FACE_CONFIG[num_of_person_in_lib] FACE_CONFIG.get(num_of_person_in_lib)1print(新文件夹建立成功!!)self.buildNewFolder Trueif key ord(q): self.quit_flag Truedef face_detecting(self):face_location []all_face_location []faces FACE_CONFIG.get(detector)(self.image, 0)self.face_num len(faces)if self.face_num ! self.last_face_num:self.face_num_change_flag True# print(脸数改变由{}张变为{}张.format(self.last_face_num, self.face_num))self.check_times 0self.last_face_num self.face_numelse:self.face_num_change_flag Falseif len(faces) ! 0:self.face_flag Truefor i, face in enumerate(faces):face_location.append(face)w, h (face.right() - face.left()), (face.bottom() - face.top())left, right, top, bottom face.left() - w//4, face.right() w//4, face.top() - h//2, face.bottom() h//4all_face_location.append([left, right, top, bottom])return face_location, all_face_locationelse:self.face_flag Falsereturn Nonedef collection_cramer(self, camera,showTrue)::param camera: 摄像头视频/读取视频:param show: 是否要展示框选出头像:return:当处理完毕之后将保持到好识别出来的头像while camera.isOpened() and not self.quit_flag:val, self.image camera.read()if val False: continuekey cv.waitKey(1)res self.face_detecting()if res is not None:_, all_face_location resfor i in range(self.face_num):[left, right, top, bottom] all_face_location[i]self.face_img self.image[top:bottom, left:right]cv.rectangle(self.image, (left, top), (right, bottom), (0, 0, 255))if self.collect_face_data True:cv.putText(self.image, Face, (int((left right) / 2) - 50, bottom 20), cv.FONT_HERSHEY_COMPLEX, 1,(255, 255, 255))self.key_scan(key)self.get_fps()cv.namedWindow(camera, 0)if(show):cv.imshow(camera, self.image)if(self.img_numFACE_CONFIG.get(max_collection_image)):print(采集完毕)breakcamera.release()cv.destroyAllWindows()def collection_images(self,images,save_pathNone)::param images: 图片类型是图片数组并且对象是opencv读取的图像对象:param save_path: 图片保存的路径:return:如果传入的图像路径为None的话那么这里就执行默认的策略也就是增量修改人物模型如果传入的图像有路径的话那么就直接保存到那里面去for image in images:self.image imageres self.face_detecting()if res is not None:_, all_face_location resfor i in range(self.face_num):[left, right, top, bottom] all_face_location[i]self.face_img self.image[top:bottom, left:right]cv.rectangle(self.image, (left, top), (right, bottom), (0, 0, 255))if self.collect_face_data True:cv.putText(self.image, Face, (int((left right) / 2) - 50, bottom 20), cv.FONT_HERSHEY_COMPLEX, 1,(255, 255, 255))self.save_face_image(save_path)
特征提取
这个特征向量的获取的话其实是分两个部分的当然最后我们暴露出来就只是一个方法罢了。这个特征提取就是建立连接的过程也就是存储这个特征。 负责读取采集到的人脸图像然后去构建人脸对应的信息import cv2 as cv
import os
import numpy as np
import csvfrom tqdm import tqdm
import shutil
from client.server.config import FACE_FILE,FACE_CONFIGclass BuildFace():def write2csv(self,data, mode):更新csv文件当中的数据这里面存储的是我们人脸的特征:param data::param mode::return:with open(FACE_FILE.csv_base_path, mode, newline) as wf:csv_writer csv.writer(wf)csv_writer.writerow(data)def get_features_from_csv(self):features_in_csv []with open(FACE_FILE.csv_base_path, r) as rf:csv_reader csv.reader(rf)for row in csv_reader:for i in range(0, 128):row[i] float(row[i])features_in_csv.append(row)return features_in_csvdef save_select_in_csv(self,data):选择性更新人脸数据:param data::return:features_in_csv self.get_features_from_csv()with open(FACE_FILE.csv_base_path, w, newline) as wf:csv_writer csv.writer(wf)for index, i in enumerate(FACE_CONFIG.get(face_needTo_update)):features_in_csv[i] data[index]csv_writer.writerow(features_in_csv[0])with open(FACE_FILE.csv_base_path, a, newline) as af:csv_writer csv.writer(af)for j in range(1, len(features_in_csv)):csv_writer.writerow(features_in_csv[j])print(csv文件更新完成!!)def get_128_features(self,person_index)::param person_index: person_index代表第几个人脸数据文件夹:return:num 0features []imgs_folder FACE_FILE.imgs_folder_path[person_index]points_faceImage_path FACE_FILE.points_faceData_path imgs_folderimgs_path FACE_FILE.faceData_path imgs_folder /list_imgs os.listdir(imgs_path)imgs_num len(list_imgs)if os.path.exists(FACE_FILE.points_faceData_path imgs_folder):shutil.rmtree(points_faceImage_path)os.makedirs(points_faceImage_path)print(人脸点图文件夹建立成功!!)with tqdm(totalimgs_num) as pbar:pbar.set_description(str(imgs_folder))for j in range(imgs_num):image cv.imread(os.path.join(imgs_path, list_imgs[j]))faces FACE_CONFIG.get(detector)(image, 1)if len(faces) ! 0:for z, face in enumerate(faces):shape FACE_CONFIG.get(predictor)(image, face)w, h (face.right() - face.left()), (face.bottom() - face.top())left, right, top, bottom face.left() - w // 4, face.right() w // 4, face.top() - h // 2, face.bottom() h // 4im imagecv.rectangle(im, (left, top), (right, bottom), (0, 0, 255))cv.imwrite(points_faceImage_path /{}.png.format(j), im)if (FACE_CONFIG.get(get_points_faceData_flag) True):for p in range(0, 68):cv.circle(image, (shape.part(p).x, shape.part(p).y), 2, (0,0,255))cv.imwrite(points_faceImage_path /{}.png.format(j), image)the_features list(FACE_CONFIG.get(recognition_model).compute_face_descriptor(image, shape)) # 获取128维特征向量features.append(the_features)num 1pbar.update(1)np_f np.array(features)res np.median(np_f, axis0)return resdef building_form_config(self):if (FACE_CONFIG.get(import_all_features_flag) True):self.building_all()else:peoples FACE_CONFIG.get(face_needTo_update)self.building_select(peoples)def building_all(self):res self.get_128_features(person_index0)self.write2csv(res, w)for i in range(1, FACE_CONFIG.get(num_of_person_in_lib)):res self.get_128_features(person_indexi)self.write2csv(res, a)def building_select(self,peoples):更新某几个人脸传入对应的下标编号,例如[0,2,4]:param peoples::return:select_res []for i in peoples:res self.get_128_features(person_indexi)select_res.append(res)self.save_select_in_csv(select_res)
识别
识别的话这里也是有两个方法一个是直接给你一张图片然后返回到里面的人脸名称还有一个就是视频直接显示读取这个看你怎么用如果你是做QT桌面开发或者web开发并且需要持续显示视频的话用这个方法不错但是算力就上去了我这边还需要跑别的算法只有当那个算法执行完毕之后并且被出发了机制我才会进行人脸识别。 负责
import numpy as np
import csvimport cv2 as cvfrom client.server.config import FACE_CONFIG,FACE_FILE
from client.server.alg.faceRec.collection import Collectionclass DetectFace(Collection):def __init__(self):super(DetectFace, self).__init__()self.available_max_face_num 50self.collect_face_data False# 人脸识别过程不采集数据固定为Falseself.all_features []# 存储库中所有特征向量self.check_features_from_cam []# 存储五次检测过程每次得到的特征向量self.person_name []# 存储的人名映射self.all_name []# 存储预测到的所有人名self.all_face_location None# 存储一帧中所有人脸的坐标self.middle_point None# 存储一张人脸的中心点坐标self.last_frame_middle_point []# 存储上一帧所有人脸的中心点坐标self.all_e_distance []# 存储当前人脸与库中所有人脸特征的欧氏距离self.last_now_middlePoint_eDistance [66666] * (self.available_max_face_num 10)# 存储这帧与上一帧每张人脸中心点的欧氏距离self.init_process()for i in range(self.available_max_face_num):self.all_e_distance.append([])self.person_name.append([])self.check_features_from_cam.append([])self.last_frame_middle_point.append([])def get_feature_in_csv(self):# 获得库内所有特征向量datas csv.reader(open(FACE_FILE.csv_base_path, r))for row in datas:for i in range(128):row[i] float(row[i])self.all_features.append(row)def get_faceName(self):# 所有对应的人名with open(FACE_FILE.faceName_path, r, encodingutf-8) as f:datas f.readlines()for line in datas:self.all_name.append(line[:-1])print(已经录入的人名有{}.format(self.all_name))def calculate_EuclideanDistance(self, feature1, feature2): # 计算欧氏距离np_feature1 np.array(feature1)np_feature2 np.array(feature2)EuclideanDistance np.sqrt(np.sum(np.square(np_feature1 - np_feature2)))return EuclideanDistancedef meadian_filter(self, the_list, num_of_data):np_list np.array(the_list)feature_max np.max(np_list, axis0)feature_min np.min(np_list, axis0)res (np.sum(np_list, axis0) - feature_max - feature_min) / (num_of_data - 2)res.tolist()return resdef middle_filter(self, the_list):np_list np.array(the_list)return np.median(np_list, axis0)def init_process(self):self.get_feature_in_csv()self.get_faceName()def track_link(self):# 让后续帧的序号与初始帧的序号对应for index in range(self.face_num):self.last_now_middlePoint_eDistance[index] self.calculate_EuclideanDistance(self.middle_point,self.last_frame_middle_point[index])this_face_index self.last_now_middlePoint_eDistance.index(min(self.last_now_middlePoint_eDistance))self.last_frame_middle_point[this_face_index] self.middle_pointreturn this_face_indexdef detect_from_image(self,image):直接识别一张图片当中的人脸这个开销是最小的当然这个精确度嘛没有直接读取视频好一点因为那个的话确定了好几帧的情况这个的话只是单张图像的。返回的是一个图像的人名列表但是实际上的话我们其实送入的图像其实只会有一个人头像多目标检测我们也是把一张图像对多个目标进行截取然后进行识别因为需要确定每个人物的序。:param image::param show::return:self.image image# self.image cv.imread(.test_1.jpg)res self.face_detecting()names []if res is not None:face, self.all_face_location resmax_it self.face_num if self.face_num len(res) else len(res)for i in range(max_it):[left, right, top, bottom] self.all_face_location[i]self.middle_point [(left right) / 2, (top bottom) / 2]self.face_img self.image[top:bottom, left:right]cv.rectangle(self.image, (left, top), (right, bottom), (0, 0, 255))shape FACE_CONFIG.get(predictor)(self.image, face[i])the_features_from_image list(FACE_CONFIG.get(recognition_model).compute_face_descriptor(self.image, shape))e_distance []for features in self.all_features:e_distance.append(self.calculate_EuclideanDistance(the_features_from_image,features))if(min(e_distance)FACE_CONFIG.get(recognition_threshold)):max_index int(np.argmin(e_distance))names.append(self.all_name[max_index])return namesdef detect_from_cam(self,camera):这里的话和我们采集是一样的就是传入这个camera对象就好了:return:while camera.isOpened() and not self.quit_flag:val, self.image camera.read()if val False: continuekey cv.waitKey(1)res self.face_detecting() # 0.038sif res is not None:face, self.all_face_location resfor i in range(self.face_num):[left, right, top, bottom] self.all_face_location[i]self.middle_point [(left right) / 2, (top bottom) / 2]self.face_img self.image[top:bottom, left:right]cv.rectangle(self.image, (left, top), (right, bottom), (0, 0, 255))shape FACE_CONFIG.get(predictor)(self.image, face[i]) # 0.002sif self.face_num_change_flag True or self.check_times 5:if self.face_num_change_flag True: # 人脸数量有变化重新进行五次检测self.check_times 0self.last_now_middlePoint_eDistance [66666 for _ in range(self.available_max_face_num)]for z in range(self.available_max_face_num):self.check_features_from_cam[z] []if self.check_times 5:the_features_from_cam list(FACE_CONFIG.get(recognition_model).compute_face_descriptor(self.image, shape))if self.check_times 0: # 初始帧self.check_features_from_cam[i].append(the_features_from_cam)self.last_frame_middle_point[i] self.middle_pointelse:this_face_index self.track_link() # 后续帧需要与初始帧的人脸序号对应self.check_features_from_cam[this_face_index].append(the_features_from_cam)elif self.check_times 5:features_after_filter self.middle_filter(self.check_features_from_cam[i])self.check_features_from_cam[i] []for person in range(FACE_CONFIG.get(num_of_person_in_lib)):e_distance self.calculate_EuclideanDistance(self.all_features[person],features_after_filter)self.all_e_distance[i].append(e_distance)if min(self.all_e_distance[i]) FACE_CONFIG.get(recognition_threshold):self.person_name[i] self.all_name[self.all_e_distance[i].index(min(self.all_e_distance[i]))]cv.putText(self.image, self.person_name[i],(int((left right) / 2) - 50, bottom 20),cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)else:self.person_name[i] Unknownelse:this_face_index self.track_link()cv.putText(self.image, self.person_name[this_face_index],(int((left right) / 2) - 50, bottom 20),cv.FONT_HERSHEY_SIMPLEX, 0.75, (0, 0, 255), 2)self.check_times 1for j in range(self.available_max_face_num):self.all_e_distance[j] []在这里的话n,s是不会触发的这里只是用一下这个q而已也就是退出self.key_scan(key)self.get_fps()cv.namedWindow(camera, 0)cv.imshow(camera, self.image)camera.release()cv.destroyAllWindows()
测试
最后的话就是这个测试。
