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: Blur Visualization, Dot Visualization, Image Contours, Perspective Correction, Polygon Zone Visualization, Bounding Box Visualization, QR Code Generator, Pixelate Visualization, Reference Path Visualization, Morphological Transformation, Trace Visualization, Image Threshold, Polygon Visualization, Dynamic Crop, Icon Visualization, Image Slicer, Stability AI Outpainting, Model Comparison Visualization, Contrast Equalization, Classification Label Visualization, Camera Focus, Stitch Images, Mask Visualization, Stability AI Inpainting, Relative Static Crop, Absolute Static Crop, Line Counter Visualization, SIFT Comparison, Circle Visualization, Ellipse Visualization, Image Convert Grayscale, Crop Visualization, Grid Visualization, Color Visualization, Image Blur, Image Preprocessing, Stability AI Image Generation, Keypoint Visualization, Camera Calibration, SIFT, Image Slicer, Depth Estimation, Background Subtraction, Label Visualization, Background Color Visualization, Triangle Visualization, Halo Visualization, Corner Visualization
• outputs: Llama 3.2 Vision, Blur Visualization, Perception Encoder Embedding Model, SAM 3, Perspective Correction, Polygon Zone Visualization, Bounding Box Visualization, Pixelate Visualization, Trace Visualization, QR Code Detection, Segment Anything 2 Model, Image Threshold, Image Slicer, Icon Visualization, Polygon Visualization, Dynamic Crop, Stability AI Outpainting, Model Comparison Visualization, Clip Comparison, Single-Label Classification Model, LMM, OpenAI, Stitch Images, Classification Label Visualization, Florence-2 Model, Mask Visualization, Single-Label Classification Model, Relative Static Crop, SIFT Comparison, Absolute Static Crop, SAM 3, Moondream2, Google Gemini, Circle Visualization, Florence-2 Model, LMM For Classification, Time in Zone, Ellipse Visualization, Image Convert Grayscale, Object Detection Model, OCR Model, SmolVLM2, Anthropic Claude, Image Preprocessing, Image Blur, Stability AI Image Generation, Google Vision OCR, Color Visualization, Keypoint Visualization, Camera Calibration, VLM as Detector, Keypoint Detection Model, EasyOCR, Image Slicer, VLM as Detector, Byte Tracker, Roboflow Dataset Upload, Gaze Detection, Background Color Visualization, Triangle Visualization, Keypoint Detection Model, Multi-Label Classification Model, Object Detection Model, Detections Stabilizer, Halo Visualization, Google Gemini, Corner Visualization, Roboflow Dataset Upload, Dot Visualization, Image Contours, Multi-Label Classification Model, Instance Segmentation Model, VLM as Classifier, Seg Preview, Reference Path Visualization, Morphological Transformation, Motion Detection, OpenAI, Instance Segmentation Model, Barcode Detection, Detections Stitch, Contrast Equalization, YOLO-World Model, Camera Focus, Stability AI Inpainting, Clip Comparison, CogVLM, Line Counter Visualization, Template Matching, CLIP Embedding Model, Email Notification, Crop Visualization, VLM as Classifier, Buffer, OpenAI, SIFT, Background Subtraction, Depth Estimation, SAM 3, Anthropic Claude, Pixel Color Count, Label Visualization, Qwen2.5-VL, SIFT Comparison, OpenAI, Dominant Color

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"
}