Signature Comparison

Out of the Box Packages > UiPath Image Analysis > SignatureComparison

This model is a proprietary model that is developed to determine the similarity between a pair of signature. The input is a pair of signature for comparison, and the output is a similarity score (between 0 and 1) and a preliminary determination if the signatures are from the same author or different authors based on a defined threshold. The threshold can be adjusted.

Important: Please note that signature detection and extraction are not part of this offering.

For structured documents when signatures always appear in the same position (e.g., forms, checks), please leverage the existing signature detection feature with the Intelligent Form Extractor feature in Document Understanding^TM.

For more complex use cases where the signatures can not be easily detected (for example, a multi-page contract in which signature can appear anywhere), please explore other approaches such as training an object detection model to detect signatures first before using the signature comparison model.

Requirements

To use the package, you need to have access to UiPath® AI Center and deploy the out of the box package in your tenant.

Model details

Input type

FILE

Input description

A pair of signature images in a list.

Accepted file formats are PNG and JPEG.

Output description

Similarity score (between 0 and 1) and a preliminary determination if the signatures are from the same author or different authors based on a threshold in a JSON format.

How to use the Signature Comparison ML package?

Below are the specific steps to deploy the model and consume the model with the ML skill activity. Please ensure that you have pre-processed the files to have a pair of signature images ready before using the model.

Log in to your Automation Cloud^TM account and go to the AI Center tab. Go to the ML Packages >Out of the box Packages > UiPath Image Analysis > SignatureComparison.
Click and deploy the Signature Comparison ML Package.
Go to the ML Skills tab and create a new ML Skill. Select the package you have deployed and deploy the ML Skill. No need to enable GPU or auto-update for this ML Skill.

For more details on ML Skills, please check the Managing ML Skills page.
You have the option to make the ML Skill public if you want to consume the model from a robot that is not connected with this Orchestrator tenant. Just click Modify current deployment and switch on the Make ML Skill Public toggle to make the ML Skill public.
To use the deployed ML skill in UiPath Studio, please ensure you have installed UiPath.MLServices.Activities package from the Manage Packages button in the ribbon.
Open Studio, drag and drop the ML Skill activity into the RPA workflow and select the refresh ML Skills option. This action populates the drop-down list with all the successfully deployed ML Skills from the Orchestrator connected to this Robot. Select the Signature Comparison ML Skill you deployed in the previous steps.
If you opt to use the public ML Skill option, select the Endpoint option from the Connection Mode drop-down, copy and paste the URL and endpoint displayed in AI Center after you make the ML Skill public.
Run the workflow. You have the option to add any post processing of the JSON output. You can also add Action Center to include the human in the loop validation.