An Intelligent Vision-Based System for Automated Short Pants Detection Using MediaPipe Landmark Estimation and MobileNet Classification
Published:
Final-year BINUS student capstone, supervised by Gabriel Asael Tarigan. This work automates dress-code compliance detection with a MediaPipe Pose landmark estimator and a transfer-learned MobileNetV2 classifier, grounding compliance in a standardized fingertip rule and resolving ambiguous cases with a multi-cue hybrid decision pipeline.