🔍 Detect anatomical landmarks in chest X-rays using ResNet-18 transfer learning, achieving 8.13 pixels average error for clinical excellence.

ROIs calibration/alignment on trousers with deep learning-based keypoint detection.

Official academic page for the paper: "Are X-ray landmark Detection Models fair? A preliminary assessment and mitigation strategy" (ICCV 2025 Stream Workshop)

Professional & Modular Image Processing Library in Python

PyTorch-based toolkit for landmark localization

Gaze estimation algorithms in C++ using laptop's camera as input and machine learning algorithms for the prediction of gaze's direction.

Focus Detection System

A videogame that uses body pose classification via a webcam feed to engage players in an interactive experience.

Anatomy-constrained chest X-ray pipeline: lung segmentation + two-stage heatmap regression for hemidiaphragm landmark localisation.

[ultralytics v8.3.75][yolov8/yolo11-pose][WIDER FACE]Upgrade YOLO5Face to YOLO8Face and YOLO11Face

HandTrackPy is a real time hand tracking which detects and tracks multiple hands, providing key landmarks for gesture recognition and interactive applications.

Real time hand detection and classification with landmark visualization. Works with any webcam for fast and efficient hand tracking.

Cephalometry Using YOLOv9 A computer vision project that applies YOLOv9 object detection for automated cephalometric analysis in dental and orthodontic imaging. This project enables precise detection and measurement of anatomical landmarks in cephalometric X-ray images.

Demo using MediaPipe to control a webpage using facial gestures

Medical Landmarks Prediction with Deep Learning: Achieving Clinical Excellence (8.13px precision) using ResNet-18 Transfer Learning for Anatomical Landmark Detection in Chest X-rays

Bone Age Maturity estimation using a Lateral Cephalogram X-ray image and deep neural networks (UNet)

[ACCV 2024 (Oral)] Official Implementation of "RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspace", Pragyan Shrestha, Chun Xie, Yuichi Yoshii, Itaru Kitahara

Code to reproduce all the experiments in the paper "CHaRM: Conditioned Heatmap Regression Methodology for Accurate and Fast Dental Landmark Localization"

Official PyTorch implementation of the paper: "Self-supervised pre-training with diffusion model for few-shot landmark detection in x-ray images" (WACV 2025)

Landmark detection engine for 3D medical images (MICCAI workshop 2021)