TY  - JOUR
AU  - Khalid, Muhammad Imran
AU  - Komal, Asma
AU  - Hussain, Nasir
AU  - Idrees, Muhammad
AU  - Wagan, Atif Ali
AU  - Hussain, Syed Akif
PY  - 2026
DA  - 2026/02/11
TI  - GeoGaze: A Real-time, Lightweight Gaze Estimation Framework via Geometric Landmark Analysis
JO  - ICCK Transactions on Advanced Computing and Systems
T2  - ICCK Transactions on Advanced Computing and Systems
JF  - ICCK Transactions on Advanced Computing and Systems
VL  - 2
IS  - 2
SP  - 107
EP  - 115
DO  - 10.62762/TACS.2025.798133
UR  - https://www.icck.org/article/abs/TACS.2025.798133
KW  - gaze estimation
KW  - geometric landmark analysis
KW  - facial landmarks
KW  - MediaPipe
KW  - real-time inference
KW  - training-free
AB  - Gaze estimation plays a vital role in human-computer interaction, driver monitoring, and psychological analysis. While state-of-the-art appearance-based methods achieve high accuracy using deep learning, they often demand substantial computational resources, including GPU acceleration and extensive training, limiting their use in resource-constrained or real-time scenarios. This paper introduces GeoGaze, a novel, lightweight, training-free framework that infers categorical gaze direction (“Left”, “Center”, “Right”) solely from geometric analysis of facial landmarks. Leveraging the high-precision 478-point face mesh and iris landmarks provided by MediaPipe, GeoGaze computes a simple normalized iris-to-eye-corner ratio and applies intuitive thresholds, eliminating the need for model training or GPU support. Evaluated on a simulated 1,500-image dataset (SGDD-1500), GeoGaze delivers competitive directional classification accuracy while achieving real-time performance (~66 FPS on CPU), outperforming typical deep learning baselines by more than eight-fold in speed. These results position GeoGaze as an efficient, interpretable alternative for edge devices and applications where precise angular gaze is unnecessary and directional intent suffices.
SN  - 3068-7969
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Khalid2026GeoGaze,
  author = {Muhammad Imran Khalid and Asma Komal and Nasir Hussain and Muhammad Idrees and Atif Ali Wagan and Syed Akif Hussain},
  title = {GeoGaze: A Real-time, Lightweight Gaze Estimation Framework via Geometric Landmark Analysis},
  journal = {ICCK Transactions on Advanced Computing and Systems},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {107-115},
  doi = {10.62762/TACS.2025.798133},
  url = {https://www.icck.org/article/abs/TACS.2025.798133},
  abstract = {Gaze estimation plays a vital role in human-computer interaction, driver monitoring, and psychological analysis. While state-of-the-art appearance-based methods achieve high accuracy using deep learning, they often demand substantial computational resources, including GPU acceleration and extensive training, limiting their use in resource-constrained or real-time scenarios. This paper introduces GeoGaze, a novel, lightweight, training-free framework that infers categorical gaze direction (“Left”, “Center”, “Right”) solely from geometric analysis of facial landmarks. Leveraging the high-precision 478-point face mesh and iris landmarks provided by MediaPipe, GeoGaze computes a simple normalized iris-to-eye-corner ratio and applies intuitive thresholds, eliminating the need for model training or GPU support. Evaluated on a simulated 1,500-image dataset (SGDD-1500), GeoGaze delivers competitive directional classification accuracy while achieving real-time performance (~66 FPS on CPU), outperforming typical deep learning baselines by more than eight-fold in speed. These results position GeoGaze as an efficient, interpretable alternative for edge devices and applications where precise angular gaze is unnecessary and directional intent suffices.},
  keywords = {gaze estimation, geometric landmark analysis, facial landmarks, MediaPipe, real-time inference, training-free},
  issn = {3068-7969},
  publisher = {Institute of Central Computation and Knowledge}
}