Facial classification Using Hybrid Quantum Machine Learning
Abstract
Hybrid quantum methods have received limited study for resource-constrained facial biometrics. We present a hybrid quantum-classical facial recognition pipeline designed to run on standard computing hardware. Images undergo gamma correction, contrast enhancement, and principal component analysis before their features are encoded into an eight-qubit variational quantum classifier. Classical image matching then performs recognition. In experiments with 50,000 images, comprising 25,000 faces from CelebA and 25,000 non-face images from CIFAR-10, the method outperformed the reported CPU-trained FaceNet baseline in accuracy and training efficiency. The pipeline was also evaluated on GPU and quantum hardware. In an attendance monitoring deployment at Mahindra University in collaboration with Lloyds Technology Centre, CPU inference took 0.2 to 0.5 seconds per person, and the system remained robust to the use of spectacles. These findings support the feasibility of deploying hybrid quantum methods for facial recognition on existing CPU hardware.
Related
- Failure classification of wind turbine operational conditions using hybrid machine learning
- HyQ-LC: Improving Light-Curve Classification with Hybrid Quantum--Classical Learning
- Sample-Size Scalability and Representation Sensitivity of Quantum Machine Learning Models for Higgs Boson Event Classification
- Comparative Study of Quantum and Classical Machine Learning Models in Binary Classification
- Exoskeleton-based user's pose estimation: a hybrid geometric and machine learning approach
BibTeX
@misc{bandlapalli2026facial,
title = {{Facial classification Using Hybrid Quantum Machine Learning}},
author = {Roshan Babu Bandlapalli and Srinivas V Katakam and Jitendra Chougala and Ravi Kumar Kappagantu and Jayasri Dontabhaktuni},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.31915},
eprint = {2609.31915},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31915},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Facial classification Using Hybrid Quantum Machine Learning
AU - Roshan Babu Bandlapalli
AU - Srinivas V Katakam
AU - Jitendra Chougala
AU - Ravi Kumar Kappagantu
AU - Jayasri Dontabhaktuni
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2609.31915
UR - https://arxiv.org/abs/2609.31915
AB - Hybrid quantum methods have received limited study for resource-constrained facial biometrics. We present a hybrid quantum-classical facial recognition pipeline designed to run on standard computing hardware. Images undergo gamma correction, contrast enhancement, and principal component analysis before their features are encoded into an eight-qubit variational quantum classifier. Classical image matching then performs recognition. In experiments with 50,000 images, comprising 25,000 faces from CelebA and 25,000 non-face images from CIFAR-10, the method outperformed the reported CPU-trained FaceNet baseline in accuracy and training efficiency. The pipeline was also evaluated on GPU and quantum hardware. In an attendance monitoring deployment at Mahindra University in collaboration with Lloyds Technology Centre, CPU inference took 0.2 to 0.5 seconds per person, and the system remained robust to the use of spectacles. These findings support the feasibility of deploying hybrid quantum methods for facial recognition on existing CPU hardware.
ER -