大数据毕设选题 - 深度学习口罩佩戴检测系统（python OpenCV YOLO）

文章目录

0 前言

🔥 Hi，大家好，这里是丹成学长的毕设系列文章！

🔥 对毕设有任何疑问都可以问学长哦!

这两年开始，各个学校对毕设的要求越来越高，难度也越来越大… 毕业设计耗费时间，耗费精力，甚至有些题目即使是专业的老师或者硕士生也需要很长时间，所以一旦发现问题，一定要提前准备，避免到后面措手不及，草草了事。

为了大家能够顺利以及最少的精力通过毕设，学长分享优质毕业设计项目，今天要分享的新项目是

🚩 基于YOLO实现的口罩佩戴检测

🥇学长这里给一个题目综合评分(每项满分5分)

• 难度系数：4分
• 工作量：4分
• 创新点：3分

🧿 选题指导, 项目分享：

https://gitee.com/yaa-dc/BJH/blob/master/gg/cc/README.md

1 课题介绍

受全球新冠肺炎疫情影响，虽然目前中国疫情防控取 得了良好效果，绝大多数地区处于疫情低风险，但个别地 区仍有零星散发病例和局部聚集性疫情。在机场、地 铁 站、医院等公共服务和重点机构场所规定必须佩戴口罩， 口罩佩戴检查已成为疫情防控的必备操作。目前，口罩 佩戴检查多为人工检查方式，如高铁上会有乘务人员一节 节车厢巡逻检查提醒乘客佩戴口罩，在医院等高危场所也 会有医务人员提醒时刻戴好口罩。人工检查方式存在检 查效率低下、难以及时发现错误佩戴口罩以及未佩戴口罩 行为等弊端。采用深度学习目标检测方法设计一个具有口罩识别功能的防疫系统，可以大大提高检测效率。

2 算法原理

2.1 算法简介

YOLOv5是一种单阶段目标检测算法，该算法在YOLOv4的基础上添加了一些新的改进思路，使其速度与精度都得到了极大的性能提升。主要的改进思路如下所示：

输入端：在模型训练阶段，提出了一些改进思路，主要包括Mosaic数据增强、自适应锚框计算、自适应图片缩放；
基准网络：融合其它检测算法中的一些新思路，主要包括：Focus结构与CSP结构；
Neck网络：目标检测网络在BackBone与最后的Head输出层之间往往会插入一些层，Yolov5中添加了FPN+PAN结构；
Head输出层：输出层的锚框机制与YOLOv4相同，主要改进的是训练时的损失函数GIOU_Loss，以及预测框筛选的DIOU_nms。

2.2 网络架构

上图展示了YOLOv5目标检测算法的整体框图。对于一个目标检测算法而言，我们通常可以将其划分为4个通用的模块，具体包括：输入端、基准网络、Neck网络与Head输出端，对应于上图中的4个红色模块。YOLOv5算法具有4个版本，具体包括：YOLOv5s、YOLOv5m、YOLOv5l、YOLOv5x四种，本文重点讲解YOLOv5s，其它的版本都在该版本的基础上对网络进行加深与加宽。

• 输入端-输入端表示输入的图片。该网络的输入图像大小为608*608，该阶段通常包含一个图像预处理阶段，即将输入图像缩放到网络的输入大小，并进行归一化等操作。在网络训练阶段，YOLOv5使用Mosaic数据增强操作提升模型的训练速度和网络的精度；并提出了一种自适应锚框计算与自适应图片缩放方法。
• 基准网络-基准网络通常是一些性能优异的分类器种的网络，该模块用来提取一些通用的特征表示。YOLOv5中不仅使用了CSPDarknet53结构，而且使用了Focus结构作为基准网络。
• Neck网络-Neck网络通常位于基准网络和头网络的中间位置，利用它可以进一步提升特征的多样性及鲁棒性。虽然YOLOv5同样用到了SPP模块、FPN+PAN模块，但是实现的细节有些不同。
• Head输出端-Head用来完成目标检测结果的输出。针对不同的检测算法，输出端的分支个数不尽相同，通常包含一个分类分支和一个回归分支。YOLOv4利用GIOU_Loss来代替Smooth L1 Loss函数，从而进一步提升算法的检测精度。

3 关键代码

classDetect(nn.Module):
    stride =None# strides computed during build
    onnx_dynamic =False# ONNX export parameterdef__init__(self, nc=80, anchors=(), ch=(), inplace=True):# detection layersuper().__init__()
        self.nc = nc  # number of classes
        self.no = nc +5# number of outputs per anchor
        self.nl =len(anchors)# number of detection layers
        self.na =len(anchors[0])//2# number of anchors
        self.grid =[torch.zeros(1)]* self.nl  # init grid
        self.anchor_grid =[torch.zeros(1)]* self.nl  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl,-1,2))# shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na,1)for x in ch)# output conv
        self.inplace = inplace  # use in-place ops (e.g. slice assignment)defforward(self, x):
        z =[]# inference outputfor i inrange(self.nl):
            x[i]= self.m[i](x[i])# conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i]= x[i].view(bs, self.na, self.no, ny, nx).permute(0,1,3,4,2).contiguous()ifnot self.training:# inferenceif self.onnx_dynamic or self.grid[i].shape[2:4]!= x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i]= self._make_grid(nx, ny, i)

                y = x[i].sigmoid()if self.inplace:
                    y[...,0:2]=(y[...,0:2]*2-0.5+ self.grid[i])* self.stride[i]# xy
                    y[...,2:4]=(y[...,2:4]*2)**2* self.anchor_grid[i]# whelse:# for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
                    xy =(y[...,0:2]*2-0.5+ self.grid[i])* self.stride[i]# xy
                    wh =(y[...,2:4]*2)**2* self.anchor_grid[i]# wh
                    y = torch.cat((xy, wh, y[...,4:]),-1)
                z.append(y.view(bs,-1, self.no))return x if self.training else(torch.cat(z,1), x)def_make_grid(self, nx=20, ny=20, i=0):
        d = self.anchors[i].device
        if check_version(torch.__version__,'1.10.0'):# torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')else:
            yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
        grid = torch.stack((xv, yv),2).expand((1, self.na, ny, nx,2)).float()
        anchor_grid =(self.anchors[i].clone()* self.stride[i]) \
            .view((1, self.na,1,1,2)).expand((1, self.na, ny, nx,2)).float()return grid, anchor_grid

classModel(nn.Module):def__init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):# model, input channels, number of classessuper().__init__()ifisinstance(cfg,dict):
            self.yaml = cfg  # model dictelse:# is *.yamlimport yaml  # for torch hub
            self.yaml_file = Path(cfg).name
            withopen(cfg, encoding='ascii', errors='ignore')as f:
                self.yaml = yaml.safe_load(f)# model dict# Define model
        ch = self.yaml['ch']= self.yaml.get('ch', ch)# input channelsif nc and nc != self.yaml['nc']:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml['nc']= nc  # override yaml valueif anchors:
            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
            self.yaml['anchors']=round(anchors)# override yaml value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])# model, savelist
        self.names =[str(i)for i inrange(self.yaml['nc'])]# default names
        self.inplace = self.yaml.get('inplace',True)# Build strides, anchors
        m = self.model[-1]# Detect()ifisinstance(m, Detect):
            s =256# 2x min stride
            m.inplace = self.inplace
            m.stride = torch.tensor([s / x.shape[-2]for x in self.forward(torch.zeros(1, ch, s, s))])# forward
            m.anchors /= m.stride.view(-1,1,1)
            check_anchor_order(m)
            self.stride = m.stride
            self._initialize_biases()# only run once# Init weights, biases
        initialize_weights(self)
        self.info()
        LOGGER.info('')defforward(self, x, augment=False, profile=False, visualize=False):if augment:return self._forward_augment(x)# augmented inference, Nonereturn self._forward_once(x, profile, visualize)# single-scale inference, traindef_forward_augment(self, x):
        img_size = x.shape[-2:]# height, width
        s =[1,0.83,0.67]# scales
        f =[None,3,None]# flips (2-ud, 3-lr)
        y =[]# outputsfor si, fi inzip(s, f):
            xi = scale_img(x.flip(fi)if fi else x, si, gs=int(self.stride.max()))
            yi = self._forward_once(xi)[0]# forward# cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
            yi = self._descale_pred(yi, fi, si, img_size)
            y.append(yi)
        y = self._clip_augmented(y)# clip augmented tailsreturn torch.cat(y,1),None# augmented inference, traindef_forward_once(self, x, profile=False, visualize=False):
        y, dt =[],[]# outputsfor m in self.model:if m.f !=-1:# if not from previous layer
                x = y[m.f]ifisinstance(m.f,int)else[x if j ==-1else y[j]for j in m.f]# from earlier layersif profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)# run
            y.append(x if m.i in self.save elseNone)# save outputif visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)return x

    def_descale_pred(self, p, flips, scale, img_size):# de-scale predictions following augmented inference (inverse operation)if self.inplace:
            p[...,:4]/= scale  # de-scaleif flips ==2:
                p[...,1]= img_size[0]- p[...,1]# de-flip udelif flips ==3:
                p[...,0]= img_size[1]- p[...,0]# de-flip lrelse:
            x, y, wh = p[...,0:1]/ scale, p[...,1:2]/ scale, p[...,2:4]/ scale  # de-scaleif flips ==2:
                y = img_size[0]- y  # de-flip udelif flips ==3:
                x = img_size[1]- x  # de-flip lr
            p = torch.cat((x, y, wh, p[...,4:]),-1)return p

    def_clip_augmented(self, y):# Clip YOLOv5 augmented inference tails
        nl = self.model[-1].nl  # number of detection layers (P3-P5)
        g =sum(4** x for x inrange(nl))# grid points
        e =1# exclude layer count
        i =(y[0].shape[1]// g)*sum(4** x for x inrange(e))# indices
        y[0]= y[0][:,:-i]# large
        i =(y[-1].shape[1]// g)*sum(4**(nl -1- x)for x inrange(e))# indices
        y[-1]= y[-1][:, i:]# smallreturn y

    def_profile_one_layer(self, m, x, dt):
        c =isinstance(m, Detect)# is final layer, copy input as inplace fix
        o = thop.profile(m, inputs=(x.copy()if c else x,), verbose=False)[0]/1E9*2if thop else0# FLOPs
        t = time_sync()for _ inrange(10):
            m(x.copy()if c else x)
        dt.append((time_sync()- t)*100)if m == self.model[0]:
            LOGGER.info(f"{'time (ms)':>10s}{'GFLOPs':>10s}{'params':>10s}{'module'}")
        LOGGER.info(f'{dt[-1]:10.2f}{o:10.2f}{m.np:10.0f}{m.type}')if c:
            LOGGER.info(f"{sum(dt):10.2f}{'-':>10s}{'-':>10s}  Total")def_initialize_biases(self, cf=None):# initialize biases into Detect(), cf is class frequency# https://arxiv.org/abs/1708.02002 section 3.3# cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
        m = self.model[-1]# Detect() modulefor mi, s inzip(m.m, m.stride):# from
            b = mi.bias.view(m.na,-1)# conv.bias(255) to (3,85)
            b.data[:,4]+= math.log(8/(640/ s)**2)# obj (8 objects per 640 image)
            b.data[:,5:]+= math.log(0.6/(m.nc -0.999999))if cf isNoneelse torch.log(cf / cf.sum())# cls
            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)def_print_biases(self):
        m = self.model[-1]# Detect() modulefor mi in m.m:# from
            b = mi.bias.detach().view(m.na,-1).T  # conv.bias(255) to (3,85)
            LOGGER.info(('%6g Conv2d.bias:'+'%10.3g'*6)%(mi.weight.shape[1],*b[:5].mean(1).tolist(), b[5:].mean()))# def _print_weights(self):#     for m in self.model.modules():#         if type(m) is Bottleneck:#             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weightsdeffuse(self):# fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')for m in self.model.modules():ifisinstance(m,(Conv, DWConv))andhasattr(m,'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)# update convdelattr(m,'bn')# remove batchnorm
                m.forward = m.forward_fuse  # update forward
        self.info()return self

    defautoshape(self):# add AutoShape module
        LOGGER.info('Adding AutoShape... ')
        m = AutoShape(self)# wrap model
        copy_attr(m, self, include=('yaml','nc','hyp','names','stride'), exclude=())# copy attributesreturn m

    definfo(self, verbose=False, img_size=640):# print model information
        model_info(self, verbose, img_size)def_apply(self, fn):# Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self =super()._apply(fn)
        m = self.model[-1]# Detect()ifisinstance(m, Detect):
            m.stride = fn(m.stride)
            m.grid =list(map(fn, m.grid))ifisinstance(m.anchor_grid,list):
                m.anchor_grid =list(map(fn, m.anchor_grid))return self

defparse_model(d, ch):# model_dict, input_channels(3)
    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}{'module':<40}{'arguments':<30}")
    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
    na =(len(anchors[0])//2)ifisinstance(anchors,list)else anchors  # number of anchors
    no = na *(nc +5)# number of outputs = anchors * (classes + 5)

    layers, save, c2 =[],[], ch[-1]# layers, savelist, ch outfor i,(f, n, m, args)inenumerate(d['backbone']+ d['head']):# from, number, module, args
        m =eval(m)ifisinstance(m,str)else m  # eval stringsfor j, a inenumerate(args):try:
                args[j]=eval(a)ifisinstance(a,str)else a  # eval stringsexcept NameError:pass

        n = n_ =max(round(n * gd),1)if n >1else n  # depth gainif m in[Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
            c1, c2 = ch[f], args[0]if c2 != no:# if not output
                c2 = make_divisible(c2 * gw,8)

            args =[c1, c2,*args[1:]]if m in[BottleneckCSP, C3, C3TR, C3Ghost]:
                args.insert(2, n)# number of repeats
                n =1elif m is nn.BatchNorm2d:
            args =[ch[f]]elif m is Concat:
            c2 =sum(ch[x]for x in f)elif m is Detect:
            args.append([ch[x]for x in f])ifisinstance(args[1],int):# number of anchors
                args[1]=[list(range(args[1]*2))]*len(f)elif m is Contract:
            c2 = ch[f]* args[0]**2elif m is Expand:
            c2 = ch[f]// args[0]**2else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args)for _ inrange(n)))if n >1else m(*args)# module
        t =str(m)[8:-2].replace('__main__.','')# module type
        np =sum(x.numel()for x in m_.parameters())# number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}{t:<40}{str(args):<30}')# print
        save.extend(x % i for x in([f]ifisinstance(f,int)else f)if x !=-1)# append to savelist
        layers.append(m_)if i ==0:
            ch =[]
        ch.append(c2)return nn.Sequential(*layers),sorted(save)

4 数据集

大家可采用公开标注好的数据集。如果为了更深入的学习也可自己标注，但过程相对比较繁琐，麻烦。

以下简单介绍数据标注的相关方法，数据标注这里推荐的软件是labelimg，学长以火灾数据集为例！

4.1 安装

通过pip指令即可安装

pip install labelimg

4.2 打开

在命令行中输入labelimg即可打开

打开你所需要进行标注的文件夹

4.3 选择yolo标注格式

点击红色框区域进行标注格式切换，我们需要yolo格式，因此切换到yolo。

4.4 打标签

点击Create RectBo -> 拖拽鼠标框选目标 -> 给上标签 -> 点击ok。

注：若要删除目标，右键目标区域，delete即可

4.5 保存

点击save，保存txt。

打开具体的标注文件，你将会看到下面的内容，txt文件中每一行表示一个目标，以空格进行区分，分别表示目标的类别id，归一化处理之后的中心点x坐标、y坐标、目标框的w和h。

5 训练

修改train.py中的weights、cfg、data、epochs、batch_size、imgsz、device、workers等参数

训练代码成功执行之后会在命令行中输出下列信息，接下来就是安心等待模型训练结束即可。

6 实现效果

6.1 pyqt实现简单GUI

from PyQt5 import QtCore, QtGui, QtWidgets

classUi_Win_mask(object):defsetupUi(self, Win_mask):
        Win_mask.setObjectName("Win_mask")
        Win_mask.resize(1107,868)
        Win_mask.setStyleSheet("QString qstrStylesheet = \"background-color:rgb(43, 43, 255)\";\n""ui.pushButton->setStyleSheet(qstrStylesheet);")
        self.frame = QtWidgets.QFrame(Win_mask)
        self.frame.setGeometry(QtCore.QRect(10,140,201,701))
        self.frame.setFrameShape(QtWidgets.QFrame.StyledPanel)
        self.frame.setFrameShadow(QtWidgets.QFrame.Raised)
        self.frame.setObjectName("frame")
        self.pushButton = QtWidgets.QPushButton(self.frame)
        self.pushButton.setGeometry(QtCore.QRect(10,40,161,51))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.pushButton.setFont(font)
        self.pushButton.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
        self.pushButton.setObjectName("pushButton")
        self.pushButton_2 = QtWidgets.QPushButton(self.frame)
        self.pushButton_2.setGeometry(QtCore.QRect(10,280,161,51))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.pushButton_2.setFont(font)
        self.pushButton_2.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
        self.pushButton_2.setObjectName("pushButton_2")
        self.pushButton_3 = QtWidgets.QPushButton(self.frame)
        self.pushButton_3.setGeometry(QtCore.QRect(10,500,161,51))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        font.setStrikeOut(False)
        self.pushButton_3.setFont(font)
        self.pushButton_3.setStyleSheet("QPushButton{background-color:rgb(151, 191, 255);}")
        self.pushButton_3.setObjectName("pushButton_3")
        self.frame_2 = QtWidgets.QFrame(Win_mask)
        self.frame_2.setGeometry(QtCore.QRect(230,110,1031,861))
        self.frame_2.setStyleSheet("")
        self.frame_2.setFrameShape(QtWidgets.QFrame.StyledPanel)
        self.frame_2.setFrameShadow(QtWidgets.QFrame.Raised)
        self.frame_2.setObjectName("frame_2")
        self.show_picture_page = QtWidgets.QStackedWidget(self.frame_2)
        self.show_picture_page.setGeometry(QtCore.QRect(-10,0,871,731))
        font = QtGui.QFont()
        font.setBold(True)
        font.setWeight(75)
        self.show_picture_page.setFont(font)
        self.show_picture_page.setObjectName("show_picture_page")
        self.photo = QtWidgets.QWidget()
        self.photo.setObjectName("photo")
        self.label = QtWidgets.QLabel(self.photo)
        self.label.setGeometry(QtCore.QRect(10,30,641,641))
        font = QtGui.QFont()
        font.setFamily("Arial")
        font.setPointSize(36)
        self.label.setFont(font)
        self.label.setText("")
        self.label.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
        self.label.setObjectName("label")
        self.pushButton_4 = QtWidgets.QPushButton(self.photo)
        self.pushButton_4.setGeometry(QtCore.QRect(680,220,171,61))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.pushButton_4.setFont(font)
        self.pushButton_4.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.pushButton_4.setObjectName("pushButton_4")
        self.pushButton_5 = QtWidgets.QPushButton(self.photo)
        self.pushButton_5.setGeometry(QtCore.QRect(680,400,171,61))
        font = QtGui.QFont()
        font.setUnderline(True)
        self.pushButton_5.setFont(font)
        self.pushButton_5.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.pushButton_5.setObjectName("pushButton_5")
        self.show_picture_page.addWidget(self.photo)
        self.videos = QtWidgets.QWidget()
        self.videos.setObjectName("videos")
        self.vid_img = QtWidgets.QLabel(self.videos)
        self.vid_img.setGeometry(QtCore.QRect(10,30,640,640))
        font = QtGui.QFont()
        font.setFamily("Arial")
        font.setPointSize(36)
        self.vid_img.setFont(font)
        self.vid_img.setText("")
        self.vid_img.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
        self.vid_img.setObjectName("vid_img")
        self.mp4_detection_btn = QtWidgets.QPushButton(self.videos)
        self.mp4_detection_btn.setGeometry(QtCore.QRect(680,220,171,61))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.mp4_detection_btn.setFont(font)
        self.mp4_detection_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.mp4_detection_btn.setObjectName("mp4_detection_btn")
        self.vid_stop_btn = QtWidgets.QPushButton(self.videos)
        self.vid_stop_btn.setGeometry(QtCore.QRect(680,400,171,61))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.vid_stop_btn.setFont(font)
        self.vid_stop_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.vid_stop_btn.setObjectName("vid_stop_btn")
        self.show_picture_page.addWidget(self.videos)
        self.camera = QtWidgets.QWidget()
        self.camera.setObjectName("camera")
        self.webcam_detection_btn = QtWidgets.QPushButton(self.camera)
        self.webcam_detection_btn.setGeometry(QtCore.QRect(680,220,171,61))
        self.webcam_detection_btn.setBaseSize(QtCore.QSize(2,2))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.webcam_detection_btn.setFont(font)
        self.webcam_detection_btn.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.webcam_detection_btn.setObjectName("webcam_detection_btn")
        self.cam_img = QtWidgets.QLabel(self.camera)
        self.cam_img.setGeometry(QtCore.QRect(10,30,640,640))
        font = QtGui.QFont()
        font.setFamily("Arial")
        font.setPointSize(36)
        self.cam_img.setFont(font)
        self.cam_img.setText("")
        self.cam_img.setPixmap(QtGui.QPixmap("./images/UI/up.jpeg"))
        self.cam_img.setObjectName("cam_img")
        self.vid_stop_btn_cma = QtWidgets.QPushButton(self.camera)
        self.vid_stop_btn_cma.setGeometry(QtCore.QRect(680,400,171,61))
        font = QtGui.QFont()
        font.setBold(True)
        font.setUnderline(True)
        font.setWeight(75)
        self.vid_stop_btn_cma.setFont(font)
        self.vid_stop_btn_cma.setStyleSheet("QPushButton{background-color:rgb(85, 170, 255);}")
        self.vid_stop_btn_cma.setObjectName("vid_stop_btn_cma")
        self.show_picture_page.addWidget(self.camera)
        self.label_2 = QtWidgets.QLabel(Win_mask)
        self.label_2.setGeometry(QtCore.QRect(430,40,251,71))
        font = QtGui.QFont()
        font.setPointSize(24)
        font.setBold(True)
        font.setItalic(False)
        font.setUnderline(True)
        font.setWeight(75)
        self.label_2.setFont(font)
        self.label_2.setStyleSheet("Font{background-color:rgb(85, 170, 255);}")
        self.label_2.setObjectName("label_2")
        self.listView = QtWidgets.QListView(Win_mask)
        self.listView.setGeometry(QtCore.QRect(-5,1,1121,871))
        self.listView.setStyleSheet(" \n""background-image: url(:/bg.png);")
        self.listView.setObjectName("listView")
        self.listView.raise_()
        self.frame.raise_()
        self.frame_2.raise_()
        self.label_2.raise_()

        self.retranslateUi(Win_mask)
        self.show_picture_page.setCurrentIndex(0)
        QtCore.QMetaObject.connectSlotsByName(Win_mask)

6.2 图片识别效果

6.3 视频识别效果

6.4 摄像头实时识别

7 最后