SIFT

Class: SIFTBlockV1

Source: inference.core.workflows.core_steps.classical_cv.sift.v1.SIFTBlockV1

The Scale-Invariant Feature Transform (SIFT) algorithm is a popular method in computer vision for detecting and describing features (interesting parts) in images. SIFT is used to find key points in an image and describe them in a way that allows for recognizing the same objects or features in different images, even if the images are taken from different angles, distances, or lighting conditions.

Read more: https://en.wikipedia.org/wiki/Scale-invariant_feature_transform

Type identifier

Use the following identifier in step "type" field: roboflow_core/sift@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

Check what blocks you can connect to SIFT in version v1.

• inputs: Image Convert Grayscale, Absolute Static Crop, Relative Static Crop, Label Visualization, Line Counter Visualization, Background Color Visualization, Stitch Images, Camera Focus, Image Contours, Image Preprocessing, Image Slicer, Reference Path Visualization, SIFT Comparison, Triangle Visualization, Grid Visualization, Polygon Zone Visualization, Keypoint Visualization, Depth Estimation, Bounding Box Visualization, Image Blur, Perspective Correction, Halo Visualization, Ellipse Visualization, Color Visualization, Crop Visualization, Dot Visualization, Pixelate Visualization, Model Comparison Visualization, Classification Label Visualization, Camera Calibration, Stability AI Image Generation, Polygon Visualization, Trace Visualization, Corner Visualization, Image Threshold, Blur Visualization, Image Slicer, Stability AI Inpainting, Mask Visualization, SIFT, Circle Visualization, Dynamic Crop
• outputs: LMM, Buffer, Image Convert Grayscale, VLM as Detector, Absolute Static Crop, Multi-Label Classification Model, Relative Static Crop, Line Counter Visualization, Gaze Detection, Background Color Visualization, OCR Model, Camera Focus, Image Contours, Image Slicer, Reference Path Visualization, Keypoint Detection Model, Instance Segmentation Model, SIFT Comparison, Object Detection Model, Triangle Visualization, Detections Stabilizer, Multi-Label Classification Model, Depth Estimation, Google Vision OCR, Llama 3.2 Vision, Roboflow Dataset Upload, Clip Comparison, Perspective Correction, Object Detection Model, Crop Visualization, Dot Visualization, Model Comparison Visualization, Instance Segmentation Model, Classification Label Visualization, Camera Calibration, Qwen2.5-VL, Stability AI Image Generation, Trace Visualization, Time in Zone, Corner Visualization, Image Threshold, Blur Visualization, QR Code Detection, CogVLM, Stability AI Inpainting, Keypoint Detection Model, SIFT, Circle Visualization, OpenAI, Moondream2, Florence-2 Model, Label Visualization, Stitch Images, Image Preprocessing, Detections Stitch, Template Matching, Byte Tracker, SmolVLM2, Dominant Color, Polygon Zone Visualization, Keypoint Visualization, LMM For Classification, Bounding Box Visualization, CLIP Embedding Model, OpenAI, Halo Visualization, Google Gemini, Ellipse Visualization, Image Blur, Color Visualization, Barcode Detection, Pixelate Visualization, Single-Label Classification Model, SIFT Comparison, Pixel Color Count, YOLO-World Model, VLM as Detector, Roboflow Dataset Upload, Segment Anything 2 Model, Polygon Visualization, Single-Label Classification Model, VLM as Classifier, Image Slicer, Clip Comparison, Mask Visualization, VLM as Classifier, Anthropic Claude, Florence-2 Model, Dynamic Crop

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SIFT in version v1 has.

Bindings

• input

  • image (image): The input image for this step..

• output

  • image (image): Image in workflows.
  • keypoints (image_keypoints): Image keypoints detected by classical Computer Vision method.
  • descriptors (numpy_array): Numpy array.

Example JSON definition of step SIFT in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sift@v1",
    "image": "$inputs.image"
}