本项目是利用mtcnn网络和facenet网络实现了一个简单的人脸识别功能。整体流程大致如下：首先利用mtcnn网络进行人脸检测和人脸关键点（5个）提取；接着利用人脸关键点进行人脸校正（仿射变换）；然后将校正之后的人脸图片送入facenet网络进行人脸特征（128维）提取；最后将提取到的人脸特征与底库中的人脸特征进行相似度计算（特征比对），完成人脸识别功能。
☆37Feb 9, 2021Updated 5 years ago
Alternatives and similar repositories for mtcnn-align-facenet-deployment
Users that are interested in mtcnn-align-facenet-deployment are comparing it to the libraries listed below
Sorting:
- YOLOv5 Quantization Aware Training with TensorRT☆19Jan 10, 2023Updated 3 years ago
- ☆12Jan 25, 2023Updated 3 years ago
- 本项目主要功能为AI智能换发型。用户上传代换发型、目标发型图片文件至系统后，可选择两种形式实现该换发型操作：①将目标的发型换到自己脸上（N模式）；②将自己的脸型融合到他人的脸上（Y模式）。☆18Jul 21, 2022Updated 3 years ago
- 使用TensorRT部署SlowFast模型☆24Mar 2, 2022Updated 4 years ago
- 人民日报中军装照换脸的一个demo，借用大神的思路改写。☆17Oct 23, 2017Updated 8 years ago
- pytorch实现实时人脸识别，使用opencv+facenet+mtcnn+knn☆17Jul 15, 2022Updated 3 years ago
- Multi-Object-Tracking for garbage detection☆26Mar 24, 2023Updated 2 years ago
- 一个基于vue+vuex+vue-img-cutter+face-api.js+Face++Api+iview实现的web端智能证件照制作工具，实现自动矫正人脸，手动选择图片裁剪范围，自动抠出人脸并自动替换背景，vue2练手☆27Mar 29, 2022Updated 3 years ago
- ☆26Jul 7, 2021Updated 4 years ago
- 深度学习是利用卷积网络的深层结构提取的信息，卷积网络目前主要用于图像识别分类技术，其实在其中间层中包含了丰富的有用信息，而这些正是风格迁移的基础。 如果研究 CNN 的各层级结构，会发现里面的每一层神经元的激活态都对应了一种特定的信息，越是底层的就越接近画面的纹理信息，如…☆10Aug 25, 2021Updated 4 years ago
- Tekla Structures Extension using Tekla Open API☆11Dec 24, 2017Updated 8 years ago
- 自控课设，基于模糊PID,可控硅调压的温度控制系统☆10Dec 9, 2019Updated 6 years ago
- yolox人脸检测，含关键点☆28Aug 11, 2021Updated 4 years ago
- C++ implementations for various tokenizers (sentencepiece, tiktoken etc).☆49Feb 23, 2026Updated 2 weeks ago
- provide some new architecture, channel pruning and quantization methods for yolov5☆31Oct 13, 2025Updated 4 months ago
- OpenCV+Pyqt实现人脸互换、人脸融合，人脸特效、人脸生成，OpenCV结课大作业☆34Sep 12, 2020Updated 5 years ago
- Deployment of yolov3 for pedestrian detection and deeplabv3+ for human segmentation using TensorRT☆29Aug 6, 2019Updated 6 years ago
- ESP8266 based MQTT gateway for DIY Kyoto Wattson☆10Dec 29, 2020Updated 5 years ago
- 信贷申请评分☆10Apr 1, 2020Updated 5 years ago
- Use an esp32 as gateway for the Eqiva Bluetooth smart lock to integrate it in Home Assistant as MQTT lock☆10Mar 4, 2022Updated 4 years ago
- 为了了解观看热门电影的用户都有哪些特征，爬取猫眼网站热门电影的评论数据进行分析：评分统计、词云、城市评论数量与平均评分、性别分析、评论数量与时间的关系。☆10Nov 14, 2019Updated 6 years ago
- Official Code for All-in-One Medical Image Re-Identification (CVPR2025)☆18Jan 11, 2026Updated last month
- This repository contains a social real-time application for iOS devices. The app leverages Amazon IVS Real-time streaming and uses the Am…☆11Nov 19, 2025Updated 3 months ago
- matlab script and simulink model for genetic algoritm☆13Aug 18, 2017Updated 8 years ago
- Python超级玛丽游戏手把手教程及代码☆11Dec 22, 2020Updated 5 years ago
- ☆21Oct 14, 2025Updated 4 months ago
- 网盘项目☆10Mar 9, 2017Updated 9 years ago
- 单片机PID算法的恒温控制系统仿真与程序源码设计(DS18B20传感器)☆12Apr 18, 2019Updated 6 years ago
- 使用ONNXRuntime部署阿里达摩院开源DAMO-YOLO目标检测，一共包含27个onnx模型，依然是包含了C++和Python两个版本的程序☆35Dec 11, 2022Updated 3 years ago
- 适用于低压伺服电机改装成高速主轴用驱动☆11Jul 28, 2023Updated 2 years ago
- Libraries, guides, blueprints, and sample code, to enable rapidly building 0-1 applications on iOS, Android and web.☆11May 12, 2023Updated 2 years ago
- This repo consist of some experimental results on bdd100k datasets using different object detection algorithms(Faster-RCNN, FCOS, ATSS)☆11Jun 27, 2020Updated 5 years ago
- This repository presents a code to detect the rear of cars using RCNNs. The dataset consists of road images in different conditions like …☆10Apr 15, 2019Updated 6 years ago
- 针对口罩部分的人脸补全技术，为提高人脸补全算法的效果，基于现有的生成式对抗网络人脸图像补全算法做出改进，增加人脸结构信息的人脸关键点约束。☆10Oct 2, 2023Updated 2 years ago
- 最懂你的网盘搜索引擎☆11Sep 20, 2018Updated 7 years ago
- Mediola MQTT Gateway☆15Apr 18, 2023Updated 2 years ago
- 多订阅合并后, 进行本机多端口匹配分流, 适合跨境或者多ip环境的网络设置☆26Feb 28, 2026Updated last week
- Low-level Vision Model Deployment☆10May 27, 2023Updated 2 years ago
- Main control terminal of educational UAV (PID Version)☆10May 23, 2020Updated 5 years ago