tencentcloud-faceid-detectface：在 Agent 中调用腾讯云 DetectFace 人脸检测
tencentcloud-faceid-detectface 是腾讯云慧眼人脸核身团队在 SkillHub 发布的 Agent Skill（v1.0.0），封装 IAI DetectFace：人脸框坐标、最多 120 人、可选属性与质量分，支持 Base64/URL 与本地图转码。需配置 TENCENTCLOUD_SECRET_ID/KEY 与 tencentcloud-sdk-python，通过 skillhub install 装入 Cursor 等 skills 目录后运行 scripts/main.py。适合在对话中做人脸有无、定位与质量评估的开发者。
Read Morexby-head-person-detection: Head and Person Detection
xby-head-person-detection is a DeepSeek Harness (DSH) plugin maintained by xby-skill for detecting heads or human bodies in images. It must be installed via the official command-line interface. Before use, users need to obtain and configure an API key from the xiaobenyang official website. The plugin provides four core features, including API key setup and three detection modes, supporting image URLs, Base64 encoding, or local file paths. It is released under the MIT license.
Read MoreAge and Gender Recognition Based on MXNET
This project is a deep learning-based face age and gender recognition system. It uses OpenCV and MTCNN (Multi-Task Cascaded Convolutional Network) for face detection, along with a pretrained model for age and gender prediction. Below, I will briefly introduce how to run and understand these scripts. ### 1. Environment Preparation Ensure you have installed the necessary Python libraries: ```bash pip install numpy opencv-python dlib mtcnn ```
Read MoreFace Landmark Detection Model MTCNN Implemented with PaddlePaddle
The article introduces the process of using MTCNN (Multi-Task Convolutional Neural Network) for face detection, which includes three hierarchical networks: P-Net, R-Net, and O-Net. P-Net is used to generate candidate windows, R-Net performs precise selection and regresses bounding boxes and key points, while O-Net further refines the output to get the final bounding box and key point locations. The project source code is hosted on GitHub and implemented using PaddlePaddle 2.0.1. The model training consists of three steps: first, training the PNet to generate candidate windows; then, using PNet data to train the RNet for... (Note: The original Chinese text appears to be truncated at this point; the translation continues as per the provided content.)
Read More