Case Study

Near Real-time AI Solution for Automated Invoice and Order Data Extraction for an Apparel Manufacturing Company

Download the Case Study



AWS Lambda, Amazon API Gateway, Amazon S3, AWS IAM, Amazon CloudWatch, Amazon DynamoDB, Amazon Textract


Innovative OCR Engine leveraging AWS designed to extract key data from English invoices efficiently. A custom React JS web UI with real-time mapping and Tailwind.css styling facilitates seamless data handling on AWS, ensuring accuracy and redundancy-free database updates.

About the Client

MBM Group has been a leading Dhaka-based manufacturing company since 1983. They produce top-tier apparel for global brands, prioritizing value creation and environmental concerns and enhancing a vibrant ecosystem for their dedicated team. 


Streamlining data processing

OCR Data Extraction

Key Field and Table Separation

Data organization and eliminating redundancy

Innovative Web UI with Real-time Mapping

Seamless Tailwind.css styling

The Challenge

The client wanted an automated solution for organizing invoices, bills, and orders from PDFs and images, necessitating an AI-powered web interface for real-time data extraction and analysis to overcome workflow delays caused by manual analysis. 


  • All client data is stored in an Amazon S3 Data Lake, ensuring reliable and scalable storage. 
  • Input documents undergo pre- and post-processing using AWS Lambda, applying image processing techniques like Gray Scaling and leveraging Amazon Textract for data extraction. 
  • An AI-powered Optical Character Recognition engine is built on AWS serverless services, offering high scalability, reliability, and cost-effectiveness. 
  • Amazon Textract extracts structured data, including forms and tables, by analyzing data relationships. 
  • Amazon API Gateway facilitates seamless interaction between the Web UI and AWS system. 
  • The results are post-processed and returned to the Web User Interface for easy access. 
  • The Web UI, powered by React JS, incorporates real-time data modification capabilities and a user-friendly mapping feature. 
  • Once data mapping is complete, the updated data is stored in Amazon DynamoDB through an internal API call. 
  • The mapped data is further restructured and stored in the NoSQL database of Amazon DynamoDB, triggered by an AWS Lambda function via the Web UI. 
  • The solution utilizes AWS services such as Amazon S3, Amazon Textract, AWS Lambda, Amazon DynamoDB, and Amazon API Gateway. 

The Results

Successfully implemented OCR Engine on AWS, efficiently extracting and organizing key data from English invoices, complemented by a customized React JS Web UI with real-time mapping, ensuring accurate database updates. 

Download the Case Study

AWS Partner - MLOps Competency

Pioneering MLOps space by being an AWS Partner - MLOps Services Competency.

Learn more

An authorized partner for all major cloud providers

A cloud agnostic organization with the rare distinction of being an authorized partner for AWS, Microsoft, Google and VMware.

Learn more

A house of strong pool of certified consulting experts

150+ cloud certified experts in AWS, Azure, GCP, VMware, etc.; delivered 300+ projects for top 100 Fortune 500 companies.

Learn more

Get The Most Out Of Us

Our support doesn't end here. We have monthly newsletters, study guides, practice questions, and more to assist you in upgrading your cloud career. Subscribe to get them all!