Icon

IOU_​workflow

Object Segmentation by using SAM (Segment Anything Model)1. Here, We used Interactive Prompt to draw bounding boxes (bbox) over the objects and saved bbox coorinates into CSV file.2. Input CSV file (bbox coordinates) into the Prompt Segmentation (SAM) model 3. Read the Ground Truth Masks (binary images) and compute IOU (Intersection Over Union) of the two binary images to evaluate the SAM results.
PNG files reading
List Files/Folders
bounding_boxes_object-detection.csvExtracted Bounding boxes through Interactive Prompt (bbox)
CSV Reader
SAM model apply on the images by using prompt bounding box
Prompt Segmentation (SAM)
Ground Truth binary Masks
Image Loader
Draw bounding boxesbounding_boxes_object-detection.csv
Interactive Prompt (bbox)
enabled file name matches if GT masks and image are at different locations with the same name of file
IOU
Path to String
PNG files reading
List Files/Folders
4 images OD
Image Loader
Path to String convert
Path to String

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: ali
Created at: 2025-05-11
On NodePit since: 2026-10-03
Last update: 2026-10-04
Created with KNIME version: v5.12.0

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!