Automated Signature Validation Using Deep Learning

By
Amit Jnagal
Founder & CEO

Signatures are seen everywhere - in art, cryptography, music, bank cheques, etc. It is a mark of a person for a proof of identity and intent. It is distinctive and unique to that person. It’s also a way to confirm the person's identity. Although it is unique and private to that person, it can be forged. Banks use the signature to verify the cheques, cryptocurrencies use the digital signature to verify a transaction, art museums use the signature to identify the art’s owner. Hence, identifying the authenticity of the signature is of utmost importance. This is where the automated signature validation becomes important.

In the past, people used to manually do signature validation. Wherein, the bank’s employee would authenticate the signature on the cheque, art museum’s employee would authenticate the signature on the art and so on. This requires a good eye to notice any subtle differences and is prone to error. Also, it is quite a time-consuming process. With the advent of the latest technology with incredible capabilities, this process is now automatized. It reduces the errors and also fastens the process. Nowadays, where billions of transactions occur on a daily basis, it is imperative that this process is fast and seamless.

There are multiple ways to automate the process of signature validation. The traditional way is to obtain the image of the signature. Then use image processing techniques such as Gray conversion, Noise reduction, Edge enhancement, binarization, and others to get the signature in a good format. Then, extract features from the processed image of the signature. High level features such as width, height, aspect ratio. Low-level features from specific parts of the signature such as the count of the transition from black to the white pixel and vice-versa. Then store these features to compare it with the signature that needs to be verified. While there are other approaches such as using Fuzzy models, Hidden Markov models and others, the current best approach is to use Deep Learning. Deep Learning has done wonders with images and it outperforms all the other approaches currently known.

The human resources required to process and verify the innumerable transactions that occur on a daily basis is no longer an option. The automation of signature validation is not just to verify but to detect fraud. Automated Signature validation is a solution for efficient and fast validation of the signature.

Frequently asked questions

What does your pricing model look like?

We price based on the annual volume of pages and complexity of document type.  We can get you preliminary pricing once we outlined a solution.  Let's do this.

To know more, book a 15-min session with an IDP expert

How can I try Infrrd before I commit to a full deployment?

Sure.  The first step is to schedule a guided demo where you get to jump into the thick of it.  After you explore our solution you can try a proof of concept. When you're ready, you can deploy the system to one use case.  Then more use cases.  Then across your enterprise.

To know more, book a 15-min session with an IDP expert

How does your system integrate with others in my enterprise?

We play nice.  Our solutions are API-based.  Your documents are feed into the solution using APIs. And extracted data is sent out through APIs.  We use REST APIs.

To know more, book a 15-min session with an IDP expert

Does your solution run in the cloud or on premise?

Our solution is cloud-native but is also design for premise deployments.  Your choice on how you want to deploy it.

To know more, book a 15-min session with an IDP expert

Does Infrrd run on mobile or desktop device?

Glad you asked.  Our data extraction process runs on servers.  We have found performance and accuracy decline when running on a desktop or mobile device. (Remember Infrrd is running a powerful AI stack).

To know more, book a 15-min session with an IDP expert

Does your system work out of the box or does it require training?

Common documents and use cases work out of the box.  The cool thing is your solution will improve as the system learns from your documents upfront and over time.

To know more, book a 15-min session with an IDP expert

How does your solution handle corrections?

Did you know no system is 100% accurate all the time?  When extraction errors occur you want to correct them.  We provide a simple UI that your business analyst will use to make corrections.

To know more, book a 15-min session with an IDP expert

Does your solution work with handwriting?

Our solution excels at data extraction from handwriting.  We've got proprietary methods and techniques that do the trick.  It's pretty cool.  See for yourself.

To know more, book a 15-min session with an IDP expert