A fully managed .NET binding for OpenCV 5, covering image processing, video analysis, camera calibration, object detection, and machine learning. Includes built-in code analysis rules that catch common mistakes when working with image data. This package is the managed API only; a small platform-specific add-on package is also required for the native OpenCV binaries to load.
LDVisionCamera 工业相机 .NET SDK 的 **Windows 7 兼容版**:API 与 LDVisionCamera.Net 完全一致,仅内含的原生库改为 Win7 兼容构建(不依赖 Win8+ 系统 DLL)。仅在需要支持 Windows 7 时使用,其余场景请用 LDVisionCamera.Net。两者不可同时安装。
Industrial Concrete Pipeline Nodes: Machine Vision, Metrology, Barcode/QR Decoders, AI Inference, Modbus PLC, and Gorilla TimeSeries Logging for ZeroPlatform.
Local PIV facial-image preparation with bounded JPEG 2000 encoding and explicit verification evidence.
A lightweight, zero-configuration object detector for .NET. Supports RT-DETR models with automatic download, GPU acceleration, and HuggingFace caching. NMS-free architecture for fast inference.
Reads a DeepSharp pipeline's rows out of a folder of pictures, a folder to each class: .ReadImages(path, shape) in the chain, read.images in a pipeline file, replayed like any other file the pipeline reads. PNG, JPEG, BMP, GIF and TGA, each file a row whose pixels are one cell of a fixed size and a fixed number of channels that the step says — a picture of another size is refused and never resized — and the class the name of its folder, with a column of nought and one for each class a learner is handed the answer by.
GraviTransformers.Vision - ViT image classification, CLIP zero-shot classification and TrOCR text recognition on .NET, with PIL's resize reproduced to the byte so results match torch. Split from GraviTransformers so that text-only users do not depend on an image library. Part of HF.Net. Dibuat oleh Gravicode Studios, dipimpin oleh Kang Fadhil.
ImageSharp-based image pre/post-processing adapter for ModelSharp — resize/normalize tensor preprocessing and classification/detection postprocessing.
A .NET library for running Segment Anything Model (SAM) and SAM2 using ONNX Runtime. Provides high-performance image segmentation capabilities with support for both SAM and MobileSAM models. Features include point-based prompting, bounding box prompts, and video frame tracking with temporal memory for SAM2.
OPC 40100-1 Machine Vision control and management contracts and the Perception model in independent generated namespaces. Part 2 asset models are supplied by Opc.Ua.MachineVision.
Typed clients for OPC 40100-1 Machine Vision control and management and the Perception model. Discover systems, manage jobs and documents, transfer files and observe events. Part 2 asset clients are supplied by Opc.Ua.MachineVision.Client.
Headless .NET vision library (HALCON-style operators, single managed assembly) with the native x64 core runtime bundled for Windows.
Server hosting for OPC 40100-1 Machine Vision control and management and the Perception model, with asynchronous providers, bounded and persistent stores, file transfer and fluent builders. Part 2 asset hosting is supplied by Opc.Ua.MachineVision.Server.
OPC UA MCP tools for OPC 40100-1/-2 Machine Vision control, management, file transfer, assets and health, and Perception discovery, image capture, inference, feedback and frame graphs. Embed one bounded catalog for all Vision models in any MCP server host.
.NET 8/9 implementation of the GenICam GenApi standard for industrial camera integration.
.NET 8/9 implementation of the GigE Vision protocol (GVCP and GVSP) for industrial camera control and image streaming.
GenICam standard support package for VisioForge .NET SDKs. Provides support for GenICam-compliant industrial cameras and machine vision devices.
HalconDotNet 22.11.0 - A .NET wrapper for the HALCON machine vision library. Provides easy access to powerful image processing and machine vision functionality.
YoloDotNet is a modular, lightweight C# library for high-performance, real-time computer vision and YOLO-based inference in .NET. Built on .NET 8 and powered by ONNX Runtime, YoloDotNet provides explicit, production-ready inference for modern YOLO model families, including YOLOv5u through YOLOv26, YOLO-World, YOLO-E, RT-DETR and D-Fine. Support AOT. The library features a fully modular execution architecture with pluggable execution providers for CPU, CUDA / TensorRT, Intel OpenVINO, Apple CoreML, and DirectML, enabling predictable deployment across Windows, Linux, and macOS. YoloDotNet intentionally avoids heavy computer vision frameworks such as OpenCV. Image handling and preprocessing are performed using SkiaSharp, with no Python runtime, no hidden preprocessing, and no implicit behavior. Designed for low-latency inference and long-running workloads, YoloDotNet gives developers full control over execution, memory usage, and preprocessing — allowing you to choose the hardware, platform, and execution backend without unnecessary abstraction or overhead.
基于 Avalonia 的图像显示控件:支持缩放/平移、鼠标位置与像素值实时显示,以及矩形、圆形、椭圆、圆环扇形、多边形、可旋转矩形、直线等 ROI 的绘制与属性获取。
The Z-Vision engine for Zork Nemesis and Zork: Grand Inquisitor, ported from ScummVM.
Computer vision for Idrak (no dependencies beyond Idrak and Idrak.Imaging): image model families (classifiers, detectors, segmenters from checkpoints), region classification in batches, content framing for classifiers of single objects (also as a training transform), per-channel image statistics for normalization, and detection and segmentation over any network.
OpenCV computer vision libraries package for VisioForge .NET SDKs. Enables advanced image processing, computer vision, and machine learning capabilities.
YoloDotNet.ExecutionProvider.DirectML enables hardware-accelerated inference on Windows using Microsoft’s DirectML framework. This execution provider integrates ONNX Runtime’s DirectML backend and runs on top of DirectX 12, allowing inference to be accelerated on a wide range of GPUs using the Windows graphics driver stack. DirectML is a Windows-only technology and is supported on Windows 10 and Windows 11 with a DirectX 12–capable GPU. No vendor-specific SDKs or external runtimes are required beyond the standard Windows graphics drivers. This makes the DirectML execution provider a low-friction option for GPU acceleration on Windows systems. Designed for YoloDotNet’s modular, execution-provider-agnostic architecture, the DirectML provider integrates cleanly with the core library and exposes explicit, predictable inference behavior. It is well-suited for Windows applications that require GPU acceleration without locking into a specific hardware vendor or proprietary ML stack.
Avalonia display and shape-editing controls for the CvInspect machine-vision toolkit — Mat image display with zoom/pan/pixel probe, renderer-neutral overlay drawing, and draggable teaching shapes that write back to tool option POCOs. For Windows and Linux, checked by a headless test suite in CI on both and in one consumer's real window on Windows (no Linux desktop run yet; macOS is not verified). Based on OpenCvSharp; the native OpenCV runtime is chosen by the consumer.
The vision model families for Idrak, as plug-ins on the library's public API (one namespace per family): reference it and call VisionPlugins.RegisterAll(), or register one family with its own Register().
Windows WPF camera viewer for discovering GigE Vision cameras, browsing GenICam features, and streaming GVSP frames.
Hikrobot MVS industrial camera wrapper for .NET with OpenCvSharp frame output on Windows and macOS.
Rotation- and scale-invariant shape matching for machine vision. .NET binding over the native geofit core; loads a recipe exported from the dashboard and finds parts by pose.
Computer vision: 2D FFT, Sobel, HOG, histogram equalization, color processing.
Image processing module for AIScript.
Real-time computer-vision components for Blazor on MediaPipe.NET (native .NET MediaPipe Tasks on ONNX Runtime): camera viewer and overlays, face detection, 478-point face mesh and blendshapes, attendance and verification, hand tracking and gestures, sign language, pose and exercise analytics, holistic tracking and motion capture, background removal, object detection, image classification, vision copilot, 3D avatars and industry, health, agritech and analytics dashboards.
OpenCV computer vision libraries package for VisioForge .NET SDKs. Enables advanced image processing, computer vision, and machine learning capabilities.
Source-generated OPC 40100-2 Machine Vision asset management and condition monitoring models, independent of the Part 1 control and Perception models.
Typed OPC 40100-2 Machine Vision asset discovery, identification, condition-monitoring snapshots and relationship clients.
OPC 40100-2 Machine Vision asset management and condition monitoring, with generated fluent accessors, transactional telemetry updates and shared DI/Machinery hosting.
YoloDotNet.ExecutionProvider.DirectML enables hardware-accelerated inference on Windows using Microsoft’s DirectML framework. This execution provider integrates ONNX Runtime’s DirectML backend and runs on top of DirectX 12, allowing inference to be accelerated on a wide range of GPUs using the Windows graphics driver stack. DirectML is a Windows-only technology and is supported on Windows 10 and Windows 11 with a DirectX 12–capable GPU. No vendor-specific SDKs or external runtimes are required beyond the standard Windows graphics drivers. This makes the DirectML execution provider a low-friction option for GPU acceleration on Windows systems. Designed for YoloDotNet’s modular, execution-provider-agnostic architecture, the DirectML provider integrates cleanly with the core library and exposes explicit, predictable inference behavior. It is well-suited for Windows applications that require GPU acceleration without locking into a specific hardware vendor or proprietary ML stack.
YoloDotNet is a modular, lightweight C# library for high-performance, real-time computer vision and YOLO-based inference in .NET. Built on .NET 8 and powered by ONNX Runtime, YoloDotNet provides explicit, production-ready inference for modern YOLO model families, including YOLOv5u through YOLOv26, YOLO-World, YOLO-E, RT-DETR and D-Fine. The library features a fully modular execution architecture with pluggable execution providers for CPU, CUDA / TensorRT, Intel OpenVINO, Apple CoreML, and DirectML, enabling predictable deployment across Windows, Linux, and macOS. YoloDotNet intentionally avoids heavy computer vision frameworks such as OpenCV. Image handling and preprocessing are performed using SkiaSharp, with no Python runtime, no hidden preprocessing, and no implicit behavior. Designed for low-latency inference and long-running workloads, YoloDotNet gives developers full control over execution, memory usage, and preprocessing — allowing you to choose the hardware, platform, and execution backend without unnecessary abstraction or overhead.
YoloDotNet.ExecutionProvider.DirectML enables hardware-accelerated inference on Windows using Microsoft’s DirectML framework. This execution provider integrates ONNX Runtime’s DirectML backend and runs on top of DirectX 12, allowing inference to be accelerated on a wide range of GPUs using the Windows graphics driver stack. DirectML is a Windows-only technology and is supported on Windows 10 and Windows 11 with a DirectX 12–capable GPU. No vendor-specific SDKs or external runtimes are required beyond the standard Windows graphics drivers. This makes the DirectML execution provider a low-friction option for GPU acceleration on Windows systems. Designed for YoloDotNet’s modular, execution-provider-agnostic architecture, the DirectML provider integrates cleanly with the core library and exposes explicit, predictable inference behavior. It is well-suited for Windows applications that require GPU acceleration without locking into a specific hardware vendor or proprietary ML stack.
OpenCV computer vision libraries package for VisioForge .NET SDKs. Enables advanced image processing, computer vision, and machine learning capabilities.
OpenCV computer vision libraries package for VisioForge .NET SDKs. Enables advanced image processing, computer vision, and machine learning capabilities.