Developed during the Computer Vision course under the guidance of Dr. Pritee Khanna at IVE Lab, IIITDMJ, this research project uses state-of-the-art deep learning algorithms like Mask RCNN for automatic segmentation of smoke regions in images.

Technologies used: Deep Learning, Computer Vision, Python, Google Colab

Green area represents actual smoke area (ground truth), Red area represents automatic segmented area, Brown region is the overlap between these.

Redactio.ml, a solution developed during the IBM 24-hr Hackathon organised at IIITDM Jabalpur. It allows you to anonymize your data by automatically detecting fields that could be personal information and bringing them to your notice before redaction. The fields identified include: Name, Gender, govt. IDs like Aadhaar, PAN, and also bank details like Credit/Debit card numbers and Bank account number. Companies spend a lot in maintaining compliance with policies like GDPR, since experts would have to manually delete personal information from chats and other interactions with their customers for both internal and external purposes. Our solution would be a boon to them. It would also be useful for Complaint Systems online forums, automating the process done by moderators.

A mobile computer/IoT based solution for helping visually challenged people using latest advancements in Image Processing. The pain points of our target users were assessed. This was essential to make the overall design of the product more user friendly. Various interaction modalities were considered, and aural method was selected for conveying information about the current scene. Technologies used: Python, Raspberry Pi Zero W, PiCam module, Cloudsight API, IBM Watson API, espeak TTS library