Absolute Static Crop

Class: AbsoluteStaticCropBlockV1

Source: inference.core.workflows.core_steps.transformations.absolute_static_crop.v1.AbsoluteStaticCropBlockV1

Extract a fixed rectangular region from input images using absolute pixel coordinates specified by center point and dimensions, creating consistent crops from the same image location across all inputs for region-of-interest extraction and fixed-area analysis workflows.

How This Block Works

This block crops a fixed rectangular region from input images using absolute pixel coordinates, unlike dynamic cropping which uses detection bounding boxes. The block:

1. Receives input images and absolute coordinate specifications (x_center, y_center, width, height)
2. Calculates the crop boundaries from the center point and dimensions:
3. Computes x_min and y_min by subtracting half the width/height from the center coordinates
4. Computes x_max and y_max by adding the width/height to the minimum coordinates
5. Rounds coordinate values to integer pixel positions
6. Extracts the rectangular region from the image using array slicing (from y_min to y_max, x_min to x_max)
7. Validates that the cropped region has content (returns None if the crop would be empty, such as when coordinates are outside image bounds)
8. Creates a cropped image object with metadata tracking the crop's origin (original image, offset coordinates, unique crop identifier)
9. Preserves video metadata if the input is from video (maintains frame information and temporal context)
10. Returns the cropped image for each input image

The block uses fixed coordinates, so the same region is extracted from all images in a batch, making it suitable for extracting consistent regions across multiple images (e.g., always cropping the top-right corner, extracting a fixed area of interest, or focusing on a specific image section). The center-based coordinate system allows specifying crops by their center point rather than corner coordinates, which can be more intuitive for defining regions. The block handles edge cases gracefully by returning None for invalid crops (coordinates outside image bounds or resulting in empty regions).

Common Use Cases

• Fixed Region Extraction: Extract the same image region from multiple images for consistent analysis (e.g., crop a specific area of interest like a logo zone, extract a fixed region for watermark detection, crop a consistent area for pattern matching), enabling standardized region analysis across image batches
• Region-of-Interest Focus: Isolate specific areas of images for detailed processing (e.g., crop a specific quadrant of surveillance frames, extract a fixed region for text recognition, focus on a known area of interest), enabling focused analysis of predetermined image regions
• Multi-Stage Workflow Preparation: Extract fixed regions for secondary processing steps (e.g., crop a specific area from full images, then run OCR or classification on the cropped region), enabling hierarchical workflows with fixed region focus
• Standardized Crop Generation: Create consistent crops from images for training or analysis (e.g., extract a fixed region from all images for dataset creation, crop a standard area for comparison, generate uniform crops for feature extraction), enabling standardized data preparation workflows
• Fixed-Area Monitoring: Monitor specific image regions across time or batches (e.g., crop the same area from video frames for change detection, extract a fixed region for tracking analysis, focus on a consistent monitoring zone), enabling temporal analysis of fixed regions
• Pre-Processing for Specialized Blocks: Extract fixed regions before processing with specialized models (e.g., crop a specific area before running OCR, extract a fixed region for fine-grained classification, isolate a region for specialized analysis), enabling optimized processing of known image regions

Connecting to Other Blocks

This block receives images and produces cropped images from fixed regions:

• After image loading blocks to extract a fixed region of interest before processing, enabling focused analysis of predetermined image areas without processing entire images
• Before classification or analysis blocks that need region-focused inputs (e.g., OCR for text in a fixed area, fine-grained classification for cropped regions, specialized models for specific image areas), enabling optimized processing of consistent regions
• In video processing workflows to extract the same region from multiple frames (e.g., crop a fixed area from each video frame for temporal analysis, extract a consistent monitoring zone for tracking, focus on a specific region across frames), enabling temporal analysis of fixed regions
• After detection blocks where you know the approximate location and want to extract a fixed-size region around it (e.g., detect objects in a general area, then crop a fixed region around that area for detailed analysis), enabling region-focused multi-stage workflows
• Before visualization blocks that display specific regions (e.g., display only the cropped region, visualize a fixed area of interest, show isolated region annotations), enabling focused visualization of extracted regions
• In batch processing workflows where the same region needs to be extracted from all images for consistent analysis or comparison, enabling standardized region extraction across image sets

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
x_center	int	X coordinate of the center point of the crop region in absolute pixel coordinates. Must be a positive integer. The crop region is centered at this X coordinate. The actual crop boundaries are calculated as x_min = x_center - width/2 and x_max = x_min + width. If the calculated crop extends beyond image bounds, the crop will be clipped or may return None if the crop would be empty..	✅
y_center	int	Y coordinate of the center point of the crop region in absolute pixel coordinates. Must be a positive integer. The crop region is centered at this Y coordinate. The actual crop boundaries are calculated as y_min = y_center - height/2 and y_max = y_min + height. If the calculated crop extends beyond image bounds, the crop will be clipped or may return None if the crop would be empty..	✅
width	int	Width of the crop region in pixels. Must be a positive integer. Defines the horizontal extent of the crop. The crop extends width/2 pixels to the left and right of the x_center coordinate. Total crop width equals this value. If the calculated crop extends beyond the image's width, it will be clipped to image boundaries..	✅
height	int	Height of the crop region in pixels. Must be a positive integer. Defines the vertical extent of the crop. The crop extends height/2 pixels above and below the y_center coordinate. Total crop height equals this value. If the calculated crop extends beyond the image's height, it will be clipped to image boundaries..	✅

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 Absolute Static Crop in version v1.

• inputs: QR Code Generator, Pixelate Visualization, Morphological Transformation, Camera Calibration, Polygon Zone Visualization, Keypoint Visualization, Camera Focus, Background Subtraction, Text Display, SIFT Comparison, Pixel Color Count, Bounding Box Visualization, Image Threshold, Contrast Equalization, Halo Visualization, Model Comparison Visualization, Label Visualization, Circle Visualization, Reference Path Visualization, Camera Focus, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, Image Slicer, Stability AI Image Generation, Stability AI Outpainting, Stitch Images, Color Visualization, Corner Visualization, Classification Label Visualization, Detection Event Log, Depth Estimation, Image Preprocessing, Line Counter, Template Matching, Image Convert Grayscale, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Dynamic Crop, Line Counter, Image Slicer, Dot Visualization, Absolute Static Crop, Triangle Visualization, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Crop Visualization, Perspective Correction, Distance Measurement, Relative Static Crop, SIFT, Grid Visualization, Blur Visualization, Trace Visualization
• outputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Morphological Transformation, Google Gemini, LMM, Instance Segmentation Model, Motion Detection, Email Notification, Detections Stitch, Polygon Zone Visualization, Keypoint Visualization, Camera Focus, Anthropic Claude, Multi-Label Classification Model, Pixel Color Count, Image Threshold, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Gaze Detection, Reference Path Visualization, Camera Focus, Stability AI Image Generation, Stitch Images, Stability AI Outpainting, Image Slicer, SmolVLM2, OpenAI, Roboflow Dataset Upload, Depth Estimation, YOLO-World Model, Google Gemini, CogVLM, Image Preprocessing, VLM as Detector, Florence-2 Model, Image Convert Grayscale, SAM 3, Byte Tracker, Dynamic Crop, Time in Zone, Perception Encoder Embedding Model, Moondream2, Triangle Visualization, Dot Visualization, OCR Model, Seg Preview, Crop Visualization, Twilio SMS/MMS Notification, Perspective Correction, EasyOCR, SAM 3, Google Gemini, Object Detection Model, Text Display, Trace Visualization, Pixelate Visualization, OpenAI, CLIP Embedding Model, Camera Calibration, Roboflow Dataset Upload, Buffer, Barcode Detection, Object Detection Model, Single-Label Classification Model, QR Code Detection, VLM as Detector, Background Subtraction, Bounding Box Visualization, Contrast Equalization, Model Comparison Visualization, Halo Visualization, Label Visualization, OpenAI, Circle Visualization, Qwen2.5-VL, Image Contours, Image Blur, Background Color Visualization, Mask Visualization, Dominant Color, VLM as Classifier, Google Vision OCR, Llama 3.2 Vision, Color Visualization, Corner Visualization, Classification Label Visualization, Single-Label Classification Model, OpenAI, Segment Anything 2 Model, Clip Comparison, Template Matching, Line Counter Visualization, Icon Visualization, Ellipse Visualization, Image Slicer, Detections Stabilizer, Absolute Static Crop, VLM as Classifier, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Qwen3-VL, SAM 3, Keypoint Detection Model, Relative Static Crop, SIFT, Blur Visualization, Multi-Label Classification Model

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Absolute Static Crop in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • x_center (integer): X coordinate of the center point of the crop region in absolute pixel coordinates. Must be a positive integer. The crop region is centered at this X coordinate. The actual crop boundaries are calculated as x_min = x_center - width/2 and x_max = x_min + width. If the calculated crop extends beyond image bounds, the crop will be clipped or may return None if the crop would be empty..
  • y_center (integer): Y coordinate of the center point of the crop region in absolute pixel coordinates. Must be a positive integer. The crop region is centered at this Y coordinate. The actual crop boundaries are calculated as y_min = y_center - height/2 and y_max = y_min + height. If the calculated crop extends beyond image bounds, the crop will be clipped or may return None if the crop would be empty..
  • width (integer): Width of the crop region in pixels. Must be a positive integer. Defines the horizontal extent of the crop. The crop extends width/2 pixels to the left and right of the x_center coordinate. Total crop width equals this value. If the calculated crop extends beyond the image's width, it will be clipped to image boundaries..
  • height (integer): Height of the crop region in pixels. Must be a positive integer. Defines the vertical extent of the crop. The crop extends height/2 pixels above and below the y_center coordinate. Total crop height equals this value. If the calculated crop extends beyond the image's height, it will be clipped to image boundaries..

• output

  • crops (image): Image in workflows.

Example JSON definition of step Absolute Static Crop in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/absolute_static_crop@v1",
    "images": "$inputs.image",
    "x_center": 40,
    "y_center": 40,
    "width": 40,
    "height": 40
}