SIFT Comparison

v2

Class: SIFTComparisonBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.classical_cv.sift_comparison.v2.SIFTComparisonBlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Compare SIFT descriptors from multiple images using FLANN-based matcher.

This block is useful for determining if multiple images match based on their SIFT descriptors.

Type identifier

Use the following identifier in step "type" field: roboflow_core/sift_comparison@v2to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
good_matches_threshold	int	Threshold for the number of good matches to consider the images as matching.	✅
ratio_threshold	float	Ratio threshold for the ratio test, which is used to filter out poor matches by comparing the distance of the closest match to the distance of the second closest match. A lower ratio indicates stricter filtering..	✅
matcher	str	Matcher to use for comparing the SIFT descriptors.	✅
visualize	bool	Whether to visualize the keypoints and matches between the two images.	✅

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 Comparison in version v2.

• inputs: LMM For Classification, Single-Label Classification Model, Florence-2 Model, Background Color Visualization, Identify Changes, Anthropic Claude, Llama 3.2 Vision, Webhook Sink, Halo Visualization, OpenAI, Reference Path Visualization, Camera Calibration, JSON Parser, Triangle Visualization, Mask Visualization, Dynamic Crop, SIFT Comparison, Stability AI Outpainting, Ellipse Visualization, Image Threshold, Identify Outliers, Relative Static Crop, Twilio SMS Notification, Google Vision OCR, VLM as Classifier, Depth Estimation, Line Counter, Roboflow Dataset Upload, Email Notification, Bounding Box Visualization, Roboflow Custom Metadata, VLM as Classifier, LMM, Color Visualization, Classification Label Visualization, PTZ Tracking (ONVIF).md), Local File Sink, Distance Measurement, Polygon Zone Visualization, CogVLM, Multi-Label Classification Model, Trace Visualization, Perspective Correction, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Stitch OCR Detections, Label Visualization, Model Comparison Visualization, Stability AI Image Generation, CSV Formatter, Slack Notification, Model Monitoring Inference Aggregator, Keypoint Detection Model, Pixelate Visualization, Absolute Static Crop, Object Detection Model, Dynamic Zone, Line Counter, Camera Focus, Detections Consensus, Keypoint Visualization, OpenAI, Image Contours, Blur Visualization, Image Blur, Clip Comparison, Grid Visualization, Image Convert Grayscale, OpenAI, Corner Visualization, SIFT, VLM as Detector, Pixel Color Count, Crop Visualization, Dot Visualization, Image Slicer, Google Gemini, Image Slicer, Circle Visualization, Florence-2 Model, OCR Model, VLM as Detector, Template Matching, Roboflow Dataset Upload, Image Preprocessing, Line Counter Visualization, Instance Segmentation Model, Stitch Images
• outputs: Detection Offset, Florence-2 Model, Identify Changes, Llama 3.2 Vision, Reference Path Visualization, Segment Anything 2 Model, SIFT Comparison, Stability AI Outpainting, Ellipse Visualization, Identify Outliers, Relative Static Crop, Twilio SMS Notification, Email Notification, QR Code Detection, Detections Classes Replacement, Roboflow Custom Metadata, Color Visualization, Classification Label Visualization, Multi-Label Classification Model, Perspective Correction, YOLO-World Model, Detections Stabilizer, SIFT Comparison, Model Comparison Visualization, Time in Zone, Stability AI Image Generation, Slack Notification, Model Monitoring Inference Aggregator, Pixelate Visualization, Object Detection Model, Detections Consensus, Image Blur, Keypoint Detection Model, Pixel Color Count, Image Slicer, Image Slicer, Circle Visualization, SmolVLM2, Template Matching, Multi-Label Classification Model, Perception Encoder Embedding Model, Instance Segmentation Model, Google Vision OCR, Stitch Images, Clip Comparison, LMM For Classification, Single-Label Classification Model, Moondream2, Background Color Visualization, Anthropic Claude, Webhook Sink, Halo Visualization, OpenAI, Camera Calibration, Triangle Visualization, Mask Visualization, Dynamic Crop, Byte Tracker, Image Threshold, Qwen2.5-VL, VLM as Classifier, Dominant Color, Object Detection Model, Depth Estimation, Time in Zone, Roboflow Dataset Upload, Bounding Box Visualization, VLM as Classifier, LMM, Instance Segmentation Model, PTZ Tracking (ONVIF).md), Polygon Zone Visualization, CogVLM, Trace Visualization, Byte Tracker, Polygon Visualization, Byte Tracker, Stability AI Inpainting, Stitch OCR Detections, Label Visualization, Detections Stitch, Keypoint Detection Model, Absolute Static Crop, Dynamic Zone, Camera Focus, Keypoint Visualization, OpenAI, Image Contours, Blur Visualization, Clip Comparison, OpenAI, Grid Visualization, VLM as Detector, Image Convert Grayscale, Corner Visualization, SIFT, Crop Visualization, Dot Visualization, Google Gemini, Single-Label Classification Model, Barcode Detection, Buffer, Florence-2 Model, CLIP Embedding Model, OCR Model, VLM as Detector, Roboflow Dataset Upload, Gaze Detection, Line Counter Visualization, Image Preprocessing

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SIFT Comparison in version v2 has.

Bindings

• input

  • input_1 (Union[image, numpy_array]): Reference to Image or SIFT descriptors from the first image to compare.
  • input_2 (Union[image, numpy_array]): Reference to Image or SIFT descriptors from the second image to compare.
  • good_matches_threshold (integer): Threshold for the number of good matches to consider the images as matching.
  • ratio_threshold (float_zero_to_one): Ratio threshold for the ratio test, which is used to filter out poor matches by comparing the distance of the closest match to the distance of the second closest match. A lower ratio indicates stricter filtering..
  • matcher (string): Matcher to use for comparing the SIFT descriptors.
  • visualize (boolean): Whether to visualize the keypoints and matches between the two images.

• output

  • images_match (boolean): Boolean flag.
  • good_matches_count (integer): Integer value.
  • keypoints_1 (image_keypoints): Image keypoints detected by classical Computer Vision method.
  • descriptors_1 (numpy_array): Numpy array.
  • keypoints_2 (image_keypoints): Image keypoints detected by classical Computer Vision method.
  • descriptors_2 (numpy_array): Numpy array.
  • visualization_1 (image): Image in workflows.
  • visualization_2 (image): Image in workflows.
  • visualization_matches (image): Image in workflows.

Example JSON definition of step SIFT Comparison in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sift_comparison@v2",
    "input_1": "$inputs.image1",
    "input_2": "$inputs.image2",
    "good_matches_threshold": 50,
    "ratio_threshold": 0.7,
    "matcher": "FlannBasedMatcher",
    "visualize": true
}

v1

Class: SIFTComparisonBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.classical_cv.sift_comparison.v1.SIFTComparisonBlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Compare SIFT descriptors from multiple images using FLANN-based matcher.

This block is useful for determining if multiple images match based on their SIFT descriptors.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
good_matches_threshold	int	Threshold for the number of good matches to consider the images as matching.	✅
ratio_threshold	float	Ratio threshold for the ratio test, which is used to filter out poor matches by comparing the distance of the closest match to the distance of the second closest match. A lower ratio indicates stricter filtering..	✅

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 Comparison in version v1.

• inputs: SIFT, Pixel Color Count, Perspective Correction, Depth Estimation, SIFT Comparison, Line Counter, Template Matching, Line Counter, SIFT Comparison, Image Contours, Distance Measurement
• outputs: Single-Label Classification Model, Detection Offset, Background Color Visualization, Anthropic Claude, Identify Changes, Webhook Sink, Halo Visualization, Reference Path Visualization, Segment Anything 2 Model, Triangle Visualization, Mask Visualization, SIFT Comparison, Stability AI Outpainting, Ellipse Visualization, Identify Outliers, Image Threshold, Byte Tracker, Twilio SMS Notification, Dominant Color, Object Detection Model, Time in Zone, Email Notification, Roboflow Dataset Upload, Bounding Box Visualization, Detections Classes Replacement, Roboflow Custom Metadata, Color Visualization, Instance Segmentation Model, PTZ Tracking (ONVIF).md), Classification Label Visualization, Polygon Zone Visualization, Multi-Label Classification Model, Trace Visualization, Byte Tracker, Perspective Correction, Detections Stabilizer, Polygon Visualization, SIFT Comparison, Byte Tracker, Stitch OCR Detections, Stability AI Inpainting, Label Visualization, Model Comparison Visualization, Time in Zone, Slack Notification, Model Monitoring Inference Aggregator, Keypoint Detection Model, Pixelate Visualization, Absolute Static Crop, Object Detection Model, Dynamic Zone, Detections Consensus, Keypoint Visualization, Image Contours, Blur Visualization, Image Blur, Keypoint Detection Model, Grid Visualization, Corner Visualization, Pixel Color Count, Image Slicer, Dot Visualization, Crop Visualization, Single-Label Classification Model, Image Slicer, Circle Visualization, Template Matching, Multi-Label Classification Model, Roboflow Dataset Upload, Gaze Detection, Line Counter Visualization, Instance Segmentation Model, Image Preprocessing, Stitch Images

Input and Output Bindings

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

Bindings

• input

  • descriptor_1 (numpy_array): Reference to SIFT descriptors from the first image to compare.
  • descriptor_2 (numpy_array): Reference to SIFT descriptors from the second image to compare.
  • good_matches_threshold (integer): Threshold for the number of good matches to consider the images as matching.
  • ratio_threshold (integer): Ratio threshold for the ratio test, which is used to filter out poor matches by comparing the distance of the closest match to the distance of the second closest match. A lower ratio indicates stricter filtering..

• output

  • good_matches_count (integer): Integer value.
  • images_match (boolean): Boolean flag.

Example JSON definition of step SIFT Comparison in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sift_comparison@v1",
    "descriptor_1": "$steps.sift.descriptors",
    "descriptor_2": "$steps.sift.descriptors",
    "good_matches_threshold": 50,
    "ratio_threshold": 0.7
}