BRISC is a high-quality, expert-annotated MRI dataset curated for brain tumor segmentation and classification. It addresses common limitations in existing datasets (e.g., BraTS, Figshare), including class imbalance, narrow tumor focus, and annotation inconsistencies.
MFSD is a dataset with pixel-level annotations of face-mask regions. It’s useful for training precise mask-segmentation models and reducing occlusion problems in face tasks like recognition, alignment, and attribute analysis.
OIN dataset contains 1,920 Iranian newspaper images for training and evaluating Persian OCR systems. It emphasizes challenging layouts, varied fonts, and print artifacts, making it especially useful for document layout analysis (DLA) and text-line detection (TLD).
Person responsible for daily coordination, onboarding, and operational supervision.
Active lab members including PhD, MSc, and undergraduate students.
External researchers and faculty who collaborate with the lab on studies and co-supervision.
Former lab members who completed degrees or moved to industry.
Address: Department, University, Street, City, Country
Email: lab@example.edu
Links: GitHub • Google Scholar • Shahrood University of Technology
