MAGE-Vein framework improves age/gender estimation from finger veins

Researchers have developed MAGE-Vein, a new framework for estimating age and gender from finger vein images. This multi-instance, multi-task learning approach uses a hybrid feature-level fusion of three fingers to extract reliable aging signs and simultaneously optimizes gender classification to account for gender-specific vascular variations. Tested on a balanced dataset, MAGE-Vein achieved a mean absolute error of 6.12 years for age estimation and a correlation of 0.880, challenging previous assumptions about the limitations of finger vein analysis for these tasks. AI

IMPACT This research could lead to more accurate biometric identification systems by overcoming demographic biases in existing datasets.

RANK_REASON The item is an academic paper detailing a new methodology and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• computer science
• Computer vision and pattern recognition
• CORE Recommender
• DagsHub
• Gotit.pub
• Hugging Face
• Influence Flower
• MAGE-Vein
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →