KYC Automation

KYC Automation - Automate KYC processing & Efficiently

Banks, financial institutions and lenders are required by law to perform "Know Your Customer" (KYC) processes before opening accounts. Across millions of customers, and multiples of millions of accounts, BFSI companies spend a good part of their operational time and resources in KYC-related tasks.

What if you could automate this, reliably? KYC Automation automatically extracts data — such as document ID, name, and date of birth — from RBI-approved KYC documents, and verifies them with government databases instantly. KYC Automation is available as a mobile application for agents/users to capture images of KYC documents and extract data from the same.

Product Components:


KYC Automation mobile app has an in-built camera feature that allows users to capture images of documents. The camera feature performs edge detection and alignment correction to guide the user in capturing the document in its entirety and at a good image quality.


Once the document image is captured, KYC Automation classifies the document into one of the following types:

KYC Automation extracts the following information from each of the document types:

Post extraction the extracted fields or data is sent back to the app screen for confirmation by the agent that the extracted data is accurate.


Once the data is extracted, the KYC Automation app will ping respective government databases to authenticate information extracted from the image.

Manual Override

KYC Automation also allows users to edit the data extracted automatically.

Most Salient Features are

How we achieve near-100% accuracy?

Multiple algorithms for region-of-interest detection

In KYC Automation, there are multiple algorithms working simultaneously on region-of-interest identification, ensuring 100% detection.


De-noising systems from simple Otsu methods to deep learning-based segmentation algorithms improve KYC Automation’s extraction quality.

Adaptive field-of-view

KYC Automation’s mobile app ensures the information to be captured is within the field-of-view while taking the picture.

Dual algorithmic journeys for building quorum

It builds quorum using two algorithms for every field. Each algorithm has different deep learning bases and maths for feature extraction methods, number of layers, loss functions etc.