SeasonOCR for EasyOCR Models. Cross-platform OCR library for ONNX models converted from EasyOCR.
Pure C# implementation of the StrongSORT multi-object tracker (DeepSORT with NSA Kalman filter, EMA appearance embedding and combined appearance/motion matching). No native or ML dependencies — bring your own detector and ReID embeddings.
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.
Unofficial C# (.NET 8) port of the ByteTrack (FoundationVision/ByteTrack) multi-object tracker core. Not affiliated with the original authors.
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.
GPU-accelerated deterministic SIFT, descriptor matching and homography RANSAC for .NET using Vulkan.
Runtime native DepthAI.Net untuk Linux ARM64 (Raspberry Pi 4/5, Jetson Orin): shim depthai-c di atas depthai-core 3.11, agar DepthAI.Net berbicara dengan kamera OAK sungguhan.
.NET bindings for NVIDIA's LocateAnything-3B — text-prompted, open-vocabulary object detection that runs fully local, from single images to live camera streams. Requires a native backend package: Mori.LocateAnythingSharp.Runtime.Cpu or Mori.LocateAnythingSharp.Runtime.Cuda.
Face stylizer model for MediaPipe.NET: BlazeFaceStylizer color sketch (256x256) and the 192x192 face mesh it aligns faces with. Converted from Google MediaPipe (Apache-2.0) and cross-validated against TFLite. Created by Gravicode Studios, led by Kang Fadhil.
Computer vision: 2D FFT, Sobel, HOG, histogram equalization, color processing.
Computer vision for aquaculture: YOLO/ONNX detection with NMS, shrimp and fish disease detection (WSSV, EMS, EHP, gill disease, fin rot, ulcer), counting and length/weight estimation, OpenCvSharp interop.
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.
.NET wrapper for OpenALPR license plate recognition. Provides P/Invoke bindings to the native OpenALPR C API.
Fish and shrimp length and weight from photos and video with MediaPipe's MagicTouch interactive segmenter (MediaPipeNet): one tap per animal, principal-axis length, measuring-board scale, species length–weight.