智慧教室—基于人脸表情识别的考试防作弊系统

简介: 智慧教室—基于人脸表情识别的考试防作弊系统

需要源码的朋友请私信我!!!!

课堂专注度及考试作弊系统、课堂动态点名,情绪识别、表情识别和人脸识别结合

课堂专注度分析

课堂专注度+表情识别

作弊检测

关键点计算方法

转头(probe)+低头(peep)+传递物品(passing)

侧面的传递物品识别

逻辑回归关键点

下载权重

1、Halpe dataset (136 keypoints)

  • 放到detection_system/checkpoints

2、Human-ReID based tracking (Recommended)

Currently the best performance tracking model. Paper coming soon.

Getting started

Download human reid model and place it into AlphaPose/trackers/weights/.

Then simply run alphapose with additional flag --pose_track

You can try different person reid model by modifing cfg.arch and cfg.loadmodel in ./trackers/tracker_cfg.py.

If you want to train your own reid model, please refer to this project

3. Yolo Detector

Download the object detection model manually: yolov3-spp.weights(Google Drive | Baidu pan). Place it into detector/yolo/data.

4. face boxes 预训练权重

google drive

放到face_recog/weights文件夹下

5. 其他

人脸识别:dlib_face_recognition_resnet_model_v1.dat

  • detection_system/face_recog/weights
    人脸对齐:shape_predictor_68_face_landmarks.dat
  • detection_system/face_recog/weights
    作弊动作分类器:cheating_detector_rfc_kp.pkl
  • detection_system/weights

使用

运行setup.py安装必要内容

python setup.py build develop

运行demo_inference.py

将detection_system设置为source root

使用摄像头运行程序

python demo_inference.py --vis --webcam 0

部分源码

import os
import platform
import subprocess
import time
import numpy as np
from Cython.Build import cythonize
from setuptools import Extension, find_packages, setup
from torch.utils.cpp_extension import BuildExtension, CUDAExtension
MAJOR = 0
MINOR = 3
PATCH = 0
SUFFIX = ''
SHORT_VERSION = '{}.{}.{}{}'.format(MAJOR, MINOR, PATCH, SUFFIX)
version_file = 'alphapose/version.py'
def readme():
    with open('README.md') as f:
        content = f.read()
    return content
def get_git_hash():
    def _minimal_ext_cmd(cmd):
        # construct minimal environment
        env = {}
        for k in ['SYSTEMROOT', 'PATH', 'HOME']:
            v = os.environ.get(k)
            if v is not None:
                env[k] = v
        # LANGUAGE is used on win32
        env['LANGUAGE'] = 'C'
        env['LANG'] = 'C'
        env['LC_ALL'] = 'C'
        out = subprocess.Popen(
            cmd, stdout=subprocess.PIPE, env=env).communicate()[0]
        return out
    try:
        out = _minimal_ext_cmd(['git', 'rev-parse', 'HEAD'])
        sha = out.strip().decode('ascii')
    except OSError:
        sha = 'unknown'
    return sha
def get_hash():
    if os.path.exists('.git'):
        sha = get_git_hash()[:7]
    elif os.path.exists(version_file):
        try:
            from alphapose.version import __version__
            sha = __version__.split('+')[-1]
        except ImportError:
            raise ImportError('Unable to get git version')
    else:
        sha = 'unknown'
    return sha
def write_version_py():
    content = """# GENERATED VERSION FILE
# TIME: {}
__version__ = '{}'
short_version = '{}'
"""
    sha = get_hash()
    VERSION = SHORT_VERSION + '+' + sha
    with open(version_file, 'w') as f:
        f.write(content.format(time.asctime(), VERSION, SHORT_VERSION))
def get_version():
    with open(version_file, 'r') as f:
        exec(compile(f.read(), version_file, 'exec'))
    return locals()['__version__']
def make_cython_ext(name, module, sources):
    extra_compile_args = None
    if platform.system() != 'Windows':
        extra_compile_args = {
            'cxx': ['-Wno-unused-function', '-Wno-write-strings']
        }
    extension = Extension(
        '{}.{}'.format(module, name),
        [os.path.join(*module.split('.'), p) for p in sources],
        include_dirs=[np.get_include()],
        language='c++',
        extra_compile_args=extra_compile_args)
    extension, = cythonize(extension)
    return extension
def make_cuda_ext(name, module, sources):
    return CUDAExtension(
        name='{}.{}'.format(module, name),
        sources=[os.path.join(*module.split('.'), p) for p in sources],
        extra_compile_args={
            'cxx': [],
            'nvcc': [
                '-D__CUDA_NO_HALF_OPERATORS__',
                '-D__CUDA_NO_HALF_CONVERSIONS__',
                '-D__CUDA_NO_HALF2_OPERATORS__',
            ]
        })
def get_ext_modules():
    ext_modules = []
    # only windows visual studio 2013+ support compile c/cuda extensions
    # If you force to compile extension on Windows and ensure appropriate visual studio
    # is intalled, you can try to use these ext_modules.
    force_compile = False
    if platform.system() != 'Windows' or force_compile:
        ext_modules = [
            make_cython_ext(
                name='soft_nms_cpu',
                module='detector.nms',
                sources=['src/soft_nms_cpu.pyx']),
            make_cuda_ext(
                name='nms_cpu',
                module='detector.nms',
                sources=['src/nms_cpu.cpp']),
            make_cuda_ext(
                name='nms_cuda',
                module='detector.nms',
                sources=['src/nms_cuda.cpp', 'src/nms_kernel.cu']),
            make_cuda_ext(
                name='roi_align_cuda',
                module='alphapose.utils.roi_align',
                sources=['src/roi_align_cuda.cpp', 'src/roi_align_kernel.cu']),
            make_cuda_ext(
                name='deform_conv_cuda',
                module='alphapose.models.layers.dcn',
                sources=[
                    'src/deform_conv_cuda.cpp',
                    'src/deform_conv_cuda_kernel.cu'
                ]),
            make_cuda_ext(
                name='deform_pool_cuda',
                module='alphapose.models.layers.dcn',
                sources=[
                    'src/deform_pool_cuda.cpp',
                    'src/deform_pool_cuda_kernel.cu'
                ]),
        ]
    return ext_modules
def get_install_requires():
    install_requires = [
        'six', 'terminaltables', 'scipy==1.1.0',
        'opencv-python', 'matplotlib', 'visdom',
        'tqdm', 'tensorboardx', 'easydict',
        'pyyaml',
        'torch>=1.1.0', 'torchvision>=0.3.0',
        'munkres', 'timm==0.1.20', 'natsort'
    ]
    # official pycocotools doesn't support Windows, we will install it by third-party git repository later
    if platform.system() != 'Windows':
        install_requires.append('pycocotools==2.0.0')
    return install_requires
def is_installed(package_name):
    from pip._internal.utils.misc import get_installed_distributions
    for p in get_installed_distributions():
        if package_name in p.egg_name():
            return True
    return False
if __name__ == '__main__':
    write_version_py()
    setup(
        name='alphapose',
        version=get_version(),
        description='Code for AlphaPose',
        long_description=readme(),
        keywords='computer vision, human pose estimation',
        url='https://github.com/MVIG-SJTU/AlphaPose',
        packages=find_packages(exclude=('data', 'exp',)),
        package_data={'': ['*.json', '*.txt']},
        classifiers=[
            'Development Status :: 4 - Beta',
            'License :: OSI Approved :: Apache Software License',
            'Operating System :: OS Independent',
            'Programming Language :: Python :: 2',
            'Programming Language :: Python :: 2.7',
            'Programming Language :: Python :: 3',
            'Programming Language :: Python :: 3.4',
            'Programming Language :: Python :: 3.5',
            'Programming Language :: Python :: 3.6',
        ],
        license='GPLv3',
        python_requires=">=3",
        setup_requires=['pytest-runner', 'numpy', 'cython'],
        tests_require=['pytest'],
        install_requires=get_install_requires(),
        ext_modules=get_ext_modules(),
        cmdclass={'build_ext': BuildExtension},
        zip_safe=False)
    # Windows need pycocotools here: https://github.com/philferriere/cocoapi#subdirectory=PythonAPI
    if platform.system() == 'Windows' and not is_installed('pycocotools'):
        print("\nInstall third-party pycocotools for Windows...")
        cmd = 'python -m pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI'
        os.system(cmd)
    if not is_installed('cython_bbox'):
        print("\nInstall `cython_bbox`...")
        cmd = 'python -m pip install git+https://github.com/yanfengliu/cython_bbox.git'
        os.system(cmd)



目录
相关文章
|
JavaScript 前端开发 小程序
Vue 3的高颜值UI组件库
Vue 3的高颜值UI组件库
627 1
|
机器学习/深度学习 固态存储 安全
表情识别-情感分析-人脸识别(代码+教程)
表情识别-情感分析-人脸识别(代码+教程)
|
机器学习/深度学习 传感器 计算机视觉
MotionBert论文解读及详细复现教程
MotionBert提出了一个统一视角来学习人体运动表示,并使用双流时空Transformer(DSTformer)网络作为运动编码器,能够全面、自适应地捕获骨骼关节之间的远程时空关系,实现在多个下游任务上的性能提升。
499 1
MotionBert论文解读及详细复现教程
|
11月前
|
Java 关系型数据库 MySQL
基于Java的学生成绩管理系统/学生信息管理系统
基于Java的学生成绩管理系统/学生信息管理系统
241 2
|
机器学习/深度学习 人机交互 计算机视觉
基于YOLOv8深度学习的人脸面部表情识别系统【python源码+Pyqt5界面+数据集+训练代码】深度学习实战
基于YOLOv8深度学习的人脸面部表情识别系统【python源码+Pyqt5界面+数据集+训练代码】深度学习实战
基于YOLOv8深度学习的人脸面部表情识别系统【python源码+Pyqt5界面+数据集+训练代码】深度学习实战
|
11月前
信号与系统:拉式变换(s域)求解电路的零输入、零状态响应
信号与系统:拉式变换(s域)求解电路的零输入、零状态响应
797 6
|
9月前
|
机器学习/深度学习 人工智能 自然语言处理
Manga Image Translator:开源的漫画文字翻译工具,支持多语言翻译并嵌入原图,保持漫画的原始风格和布局
Manga Image Translator 是一款开源的漫画图片文字翻译工具,支持多语言翻译并能将翻译后的文本无缝嵌入原图,保持漫画的原始风格和布局。该工具基于OCR技术和深度学习模型,提供批量处理和在线/离线翻译功能。
504 15
Manga Image Translator:开源的漫画文字翻译工具,支持多语言翻译并嵌入原图,保持漫画的原始风格和布局
|
11月前
|
传感器 Web App开发 编解码
基于51单片机的智能热水器设计
基于51单片机的智能热水器设计
228 0
|
11月前
|
机器学习/深度学习 监控 机器人
人体姿态估计技术的理解(Human Pose Estimination)
人体姿态估计技术的理解(Human Pose Estimination)
531 0
|
敏捷开发 安全 测试技术
软件工程:从概念到实践
【8月更文第20天】随着信息技术的快速发展,软件在现代社会中扮演着越来越重要的角色。从简单的移动应用到复杂的操作系统,软件已经成为连接人与数字世界的桥梁。为了有效地开发和维护这些软件系统,软件工程应运而生。本文将探讨软件工程的基本概念、目标、原则以及常用的生命周期模型。
575 0