A computer vision prototype designed to detect digital overlays and manipulation in receipt images (JPG, PNG, PDF).
This project focuses on identifying inconsistencies such as altered totals, misaligned text, and unnatural image artifacts that may indicate fraud.
Techniques include image preprocessing, edge detection, and pattern analysis to flag potential tampering.
A hybrid NLP chatbot that combines rule-based logic with intent classification to respond to user questions.
This project explores how structured data and natural language processing can be used to create more dynamic and engaging interactions.
We use cookies to analyze website traffic and optimize your website experience. By accepting our use of cookies, your data will be aggregated with all other user data.