Paper Title

OPTIMIZED AI MODELS FOR FACIAL LANDMARK ESTIMATION ON SMARTPHONES AND IOT DEVICES

Authors

Profile picture of mj iaeme
mj iaeme
Profile picture of Priya Balasubramanian
Priya Balasubramanian

Keywords

  • facial landmark detection mobile ai optimization
  • deep learning on edge devices
  • blazeface
  • mobilenetv2
  • knowledge distillation
  • quantization
  • edge ai
  • iot vision systems.

Journal

International Journal of Information Technology and Management Information Systems (IJITMIS) External link

Publication Info

Volume: 15 | Issue: 2 | Pages: 106-124

Published On

November, 2024

Downloads

PDF icon FULL PDF
CITATION
COPY LINK

Abstract

Facial landmark estimation plays a pivotal role in diverse real-time applications, including identity authentication, expression recognition, and augmented reality. With the proliferation of resource-constrained devices like smartphones and IoT nodes, optimizing AI models for efficiency, speed, and accuracy is critical. This research examines the development and deployment of lightweight yet accurate deep learning models tailored for mobile and edge computing environments. Leveraging knowledge distillation, pruning, quantization, and architecture design such as MobileNetV2 and BlazeFace, this paper evaluates state-of-the-art strategies to balance precision and computational feasibility in facial landmark estimation on low-resource platforms.

View more »

Uploaded Document Preview