This workflow will determine the colors of a foreground object in an image. The workflow builds upon the results from the workflow 'CRAFTED_get-data-MINT_public' and 'CRAFTED_objectdetector_GVision_base64'
Note: this workflow guesses the foreground using coordinates of the foreground object generated by the 'CRAFTED_objectdetector_GVision_base64' workflow.
If you don't want/need to use the object detection workflow, use the workflow 'CRAFTED_get-color-from-region_OpenCV_no-object_public'.
Workflow components:
1. read data about the image and detected object(s) from a MongoDB and loads the image
2. determine the main colors
3. map the colors tot he colours of the European Fashion Thesaurus
4. write the image without background to a local disk
5. write the result in W3C annotation format to a file
6. write the result in W3C annotation format to the MongoDB
Configuration:
- set mongoDB connection to read image metadata [see workflow 'CRAFTED_get-data-MINT_public]
- set CP name and dataset ID
- set path to local disk for foreground image files (in folder 'IMAGES_NO_BCKGRND')
- set mongoDB connection to write results
- set path to annotations folder
- Optional: set number of clusters in the 'get colors' node
- Optional: set threshhold for infrequemnt colours in 'filter colors
Requirements:
- Knime (https://www.knime.com/)
- Python3 environment for Knime, as explained here: https://docs.knime.com/2018-12/python_installation_guide
- MongoDB Compass (see https://www.mongodb.com/products/compass)
To use this workflow in KNIME, download it from the below URL and open it in KNIME:
Download WorkflowDeploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
Try NodePit Runner!Do you have feedback, questions, comments about NodePit, want to support this platform, or want your own nodes or workflows listed here as well? Do you think, the search results could be improved or something is missing? Then please get in touch! Alternatively, you can send us an email to mail@nodepit.com, follow @NodePit on Twitter or botsin.space/@nodepit on Mastodon.
Please note that this is only about NodePit. We do not provide general support for KNIME — please use the KNIME forums instead.