Parascript, a Colorado-based company dedicated to creating AI-powered solutions for document processing automation, has been awarded a patent (US 11521428 B1) on December 6th, 2022. The patent is for Methods and Systems for Signature Verification.
Parascript’s patent for Methods and Systems for Signature Verification can help companies that wish to validate individuals’ identities through signature verification. The proposed methods capture a signature image or a signature trajectory on a digital pad where it is then verified by comparing to a reference signature. The reference signature may be available in the form of an image or a trajectory collected during the process of signing on a pen-enabled device. The patent describes several use cases of identity verification: identity verification for remote access to services, identity verification in self-service kiosks, automated in-person identity verification, and the encoding of signature biometrics on IDs, credit cards, etc. Below are some of possible use cases.
- Identity verification for accessing services remotely by smartphone, tablet, or PC (e.g., customer onboarding, registration, verification, etc.) — The signature is captured by a scanner or a camera on the device and is compared to the reference signature. When an Identification Document (ID) is captured by camera or scanner, the reference signature is extracted from the image on the ID for verification.
- Identity verification in self-service kiosks — Signatures are captured on a signature pad or with a camera embedded in a self-service kiosk such as an Interactive Teller Machine (ITM) and verified against a signature extracted from an identification card scanned by the machine (driver’s license, passport, other).
- Automated in-person identity verification — A paper document that bears the signature-in-question (for example a store-branded credit card application) is scanned and automatically matched against the signature on a scanned ID. Alternatively, the signature-in-question may be signed in person on a digital signature pad.
- Encoding biometrics of a signature on identification cards, credit cards, cards and other documents that may require identity verification — A person’s signature is collected when the person applies for a driver’s license, passport, credit card or other ID. This signature is encoded on the document (chip, magnetic stripe). The encoded data may be read and used for signature verification purposes, eliminating the need for reference signature databases, and enabling an immediate and reliable method of identity verification. This method allows for increased security as the reference signature is not exposed.
Parascript’s Methods and Systems for Signature Verification enables high accuracy automatic signature verification for identity verification. Innovative machine learning technologies allow for simultaneous processing of signatures presented in different forms (trajectory or image) without converting them to the same input type. This eliminates limitations that impeded the use of automatic signature verification for identity verification purposes, and it enhances the accuracy of signature verification.
Parascript’s software saves companies over $1 billion annually. Parascript state-of-the-art software incorporates proprietary AI technologies to provide robust data capture solutions that bring the highest levels of accuracy when processing documents. With over three decades of experience applying AI to solve complex problems, Parascript can automate document-oriented processes in structured, semi-structured, and unstructured formats, drastically reducing human involvement. Parascript has automated the postal industry, mortgage, payment processing, and hundreds of other processes.