iMeDIA Lab
Intelligent Medical and Document Image Analytics
Advancing healthcare and information extraction through state-of-the-art computer vision and deep learning.
Explore Our ResearchAbout Our Lab
Our Mission
At the iMeDIA lab, we develop robust, scalable, and intelligent AI solutions. Our primary domains include analyzing complex medical imaging data for computer-aided diagnosis, video anomaly detection, and extracting structured information from unstructured document images using OCR and layout analysis.
We collaborate with clinical experts and industry partners to bridge the gap between theoretical machine learning and real-world application.
Core Technologies
- Deep Learning & Neural Networks
- Computer Vision
- Medical Image Segmentation & Classification
- Optical Character Recognition (OCR)
- Document Layout Analysis
- Natural Language Processing (NLP) integration
- Object detection & tracking
- Video Understanding
Research Areas
Medical Image Diagnostics
Medical Image Diagnostics
Developing AI models to analyze retinal fundus images and infrared dryeye images to assist radiologists in early detection of anomalies and diseases.
Document AI
Document AI
Creating algorithms capable of reading, understanding, and structuring data from scanned documents, historical archives, and handwritten notes.
Multimodal Learning
Multimodal Learning
Combining visual data (images) with textual data (clinical reports or document text) to create comprehensive AI reasoning systems.
Deep Learning & Generative Models
Deep Learning & Generative Models
Leveraging neural networks to learn powerful data representations. Generating realistic data using GANs, VAEs, and diffusion-based models.
Video Understanding
Video Understanding
Analyzing spatial and temporal patterns in video data. Enabling tasks like action recognition, event or anomaly detection, and scene interpretation.
Object Detection and Tracking
Object Detection and Tracking
Detecting and localizing objects in images and videos with high precision. Tracking their movement across frames for real-time and intelligent analysis.
News & Announcements
Paper Accepted at IEEE TENCON 2026, Bali, Indonesia
We are pleased to announce that our research paper, "Air-Char-Tracker: Air-Written Numeral Recognition Using a Vision Transformer Appr…
Paper accepted at ICDAR 2026
We are pleased to announce that our research paper, "Efficient Table QA via Progressive Inference and TableGrid Navigation", has be…
Our Research Featured in Dainik Jagran
We are pleased to announce that our recent research on deep learning based dry eye segmentation has been featured in Dainik Jagran, one of India’s le…
Pre-thesis Submission (Open) Seminar of Mr. Suvramalya Basak (RSI2022003)
Pre-thesis Submission (Open) Seminar of Mr. Suvramalya Basak (RSI2022003) will be held on 23 April 2026 at 11:30 AM in Room 5322, Computer Center-III (CC3). Th…
Recent Publications
View Paper / PDF
View Paper / PDF
View Paper / PDF
View Paper / PDF
View Paper / PDF
Our Team
Professors
Dr. Mohammed Javed
Associate Professor
javed@iiita.ac.in
Specializes in Document Image Analysis, Handwriting Recognition, and Deep Learning applications.
Dr. Anjali Gautam
Assistant Professor
anjaligautam@iiita.ac.in
Specializes in Medical Image Analysis and Deep Learning applications.
Students
Suvramalya Basak
Research Scholar
rsi2022003@iiita.ac.in
Video Anomaly Detection
Apurba Chakraborty
Research Scholar
rsi2024005@iiita.ac.in
Document Image Analysis
Ankit Kumar Verma
Research Scholar
rsi2024501@iiita.ac.in
Retinal Image Analysis
Amirtansh Maurya
Research Scholar
rsi2024503@iiita.ac.in
Document Analysis
Aarti Jha
Research Scholar
rsi2025509@iiita.ac.in
Generative AI
Arbiya Sabri
Research Scholar
rsi2026007@iiita.ac.in
Generative AI
Vivek Vishwakarma
Junior Research Assistant
prf.vivek@iiita.ac.in
Alt Text Generation
Contact Us
Address: Room 5402 Computer Center-III (CC3)
Indian Institute of Information Technology
Allahabad, Uttar Pradesh 211015, India
Email: javed.iiita@gmail.com,
anjaligautam.iiita@gmail.com &
imedia.iiita@gmail.com