law firm
90% Admin Reduction with Signature Fraud Detection
![](https://vacon.ai/wp-content/uploads/2023/06/IMG-20221222-WA0010-1024x677.jpg)
![](https://vacon.ai/wp-content/uploads/2023/02/Challenge-Icon.webp)
The Challenge
The client is a leading law firm with an obligation to verify client signatures on all documents. The task was labor-intensive, time-consuming and subject to human error given signatures can evolve.
The procedure required manually inspecting client signature cards and identification documents, and comparing them with signed legal documents.
![](https://vacon.ai/wp-content/uploads/2023/02/Solution-Icon.webp)
Solution
Vacon developed an AI tool to identify and extract all signatures from documents to compare to a signature library of clients.
How it works:
- Using Amazon Textract, signatures are extracted from client signature files, identification, and signed documents. Signature extraction includes connected components from an image file.
- A PyTorch model classifies signature images to accommodate natural signature variations in width and height ratios. The confidence of the trained model helped remove false positives.
![](https://vacon.ai/wp-content/uploads/2023/02/Tech-Icon.webp)
Tech Stack
![Python](https://vacon.ai/wp-content/uploads/2023/02/python-icon.webp)
![Flask](https://vacon.ai/wp-content/uploads/2023/02/flask-icon.webp)
![opencv-logo](https://vacon.ai/wp-content/uploads/2023/02/opencv-logo.webp)
![PyTorch](https://vacon.ai/wp-content/uploads/2023/02/pytorch-logo.webp)
![](https://vacon.ai/wp-content/uploads/2023/02/Results-Icon.webp)
Results
- 90% accuracy of document signature verification within seconds.
- Seconds to verify signatures.
- Instant detection of signature fraud.
- 90% reduction in administrative resources for document authenticity.