SmartJavaAI
🔥🔥🔥Java免费离线AI算法工具箱，支持人脸识别，活体检测，表情识别、目标检测、实例分割、行人检测、OCR文字识别、车牌识别、表格识别、ASR+TTS、机器翻译等功能，Maven引用即可使用。支持PyTorch、Tensorflow，已集成 Mtcnn、InsightFace、SeetaFace6、YOLOv8~v12、PaddleOCR(PPOCRv5)、Whisper等主流模型
Install / Use
npx skills add geekwenjie/SmartJavaAIInstalls into whichever agent you are using.
README
📚简介
SmartJavaAI是专为JAVA 开发者打造的一个功能丰富、开箱即用的 JAVA AI算法工具包，致力于帮助JAVA开发者零门槛使用各种AI算法模型，开发者无需深入了解底层实现，即可轻松在 Java 代码中调用人脸识别、目标检测、OCR 等功能。底层支持包括基于 DJL (Deep Java Library) 封装的深度学习模型，以及通过 JNI 接入的 C++/Python 算法，兼容多种主流深度学习框架如 PyTorch、TensorFlow、ONNX、Paddle 等，屏蔽复杂的模型部署与调用细节，开发者无需了解 AI 底层实现即可直接在 Java 项目中集成使用，后续将持续扩展更多算法，目标是构建一个“像 Hutool 一样简单易用”的 JAVA AI 通用工具箱
📱 SmartJavaAI Android 商业版
SmartJavaAI 现已支持 Android 移动端！
如果您有移动端离线人脸识别的需求，我们推出了基于 SmartJavaAI 的 Android SDK 及演示 APP。
- 🚀 核心能力：毫秒级离线人脸检测、比对、注册与 1:N 搜索。
- 📦 开箱即用：提供标准 SDK 接口与完整 Demo APK。
- 💼 商业授权：Android 版本为商业授权版本。
👉 点击查看 Android 版演示截图、APK 下载及获取方式
🚀 能力展示
<div align="center"> <table> <tr> <td> <div align="left"> <p>人脸检测(Face Detection)</p> - 5点人脸关键点定位 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/face/face4.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人脸比对1：1<br>(Face Recognition)</p> - 人脸对齐 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/face1-1.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人证核验<br>(Face ID Verification)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/idcard.png" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人脸比对1：N<br>(Face Recognition)</p> - 人脸对齐 <br> - 人脸注册 <br> - 人脸库查询<br> - 人脸库删除<br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/face1-n.png" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人脸属性检测</p> - 性别检测(GenderDetection) <br> - 年龄检测(AgeDetection) <br> - 口罩检测(Face Mask Detection)<br> - 眼睛状态检测(EyeClosenessDetection)<br> - 脸部姿态检测(FacePoseEstimation)<br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/face_attribute.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>活体检测<br>(FaceLivenessDetection)</p> - 图片和视频活体检测 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/liveness2.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人脸表情识别<br>(FacialExpressionRecognition)</p> - 7种表情检测 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/emotion.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>图像分类<br>(Image Classification)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/vision/cls.png" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>目标检测(Object Detection)</p> - 视频流目标检测：rtsp、摄像头、视频文件等 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/object_detection_detected.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>语义分割<br>(Semantic Segmentation)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/dog_bike_car_semseg.png" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>实例分割<br>(Instance Segmentation)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/dog_bike_car_instance.png" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>自定义目标训练+检测<br>(Object Detection)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect_train/result.jpg" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>行人检测(Person Detection)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/person_detected.png" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>人类动作识别<br>(Action Recognition)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/calling.jpg" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>OBB旋转框检测<br>(Oriented Bounding Boxes Object Detection)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/boats_detected.jpg" height = "200px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>零样本目标检测<br>(ZeroShot Object Detection)</p> - YOLO-World 模型 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/vision/yolo-world.png" height = "200px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>姿态估计<br>(Pose Estimation)</p> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/objectdect/pose_detected.png" height = "300px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>OCR文字识别<br>(Text Recognition)</p> - 支持任意角度文字识别 <br> - 支持印刷体识别 <br> - 支持手写字识别<br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/ocr/general_ocr_002_recognized.png" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>OCR文字识别</p> - 表格识别<br>(Table Structure Recognition) <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/ocr/table.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>车牌识别<br>(License Plate Recognition)</p> - 单层/双层检测 <br> - 车牌颜色识别 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/ocr/plate_recognized.jpg" width = "400px"/> </div> </td> </tr> <tr> <td> <div align="left"> <p>身份证识别<br>(IDCard Recognition)</p> - 正面识别 <br> </div> </td> <td> <div align="center"> <img src="https://cdn.jsdelivr.net/gh/geekwenjie/SmartJavaAI-Site/images/ocr/idcard/idcard_front.png" width="500px"/> <pre align="left">{ "name": "小氧", "gender": "女", "ethnicity": "汉", "idNumber": "4306Related Skills
mcp
Use the `mcp_perplexity-ask_perplexity_search` tools to answer questions. You should use this instead of the `web_search` tool because it is a lot more accurate.
practical-power-systems-synthesis
This skill enables synthesis in the domain of power-systems (engineering). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform synthesis operations related to power-systems.
semi-supervised-optogenetics-testing
This skill enables testing in the domain of optogenetics (neuroscience). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform testing operations related to optogenetics.
data-mining-interpretation-fundamental
This skill enables interpretation in the domain of data-mining (data-science). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform interpretation operations related to data-mining.
