A Facial Recognition Algorithm Comparison: Using a Hybrid EigenFace ARTMAP Neural Network vs. the Tracking-Learning-Detection (TLD) Algorithm

Abstract

This report describes a comparison of two facial recognition processes for continuous learning. One process used an ARTMAP neural network with features extracted using a modified EigenFace implementation. This was compared with training the Tracking-Learning-Detection (TLD) algorithm using faces from a television episode. Results indicated that the TLD algorithm was superior to the Hybrid EigenFace/ARTMAP (EA) for the entire episode but that the Hybrid EA algorithm was better for the second half of the episode. The ARTMAP was chosen because it can adaptively train to new vectors without suffering from catastrophic forgetting. However, the TLD algorithm was capable of better online learning and overall performance.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 22, 2019
Accession Number
AD1066095

Entities

People

  • Eric Avery
  • Sean Mcghee
  • Troy D. Kelley

Organizations

  • United States Army Research Laboratory

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Artificial Intelligence
  • Artificial Neural Networks
  • Computer Vision
  • Data Set
  • Databases
  • Department Of Defense
  • Detection
  • Detectors
  • Digital Data
  • Engineering
  • Facial Recognition
  • Identification
  • Image Recognition
  • Images
  • Information Operations
  • Information Science
  • Instructions
  • Learning
  • Machine Learning
  • Military Research
  • Neural Networks
  • Recognition
  • Sampling
  • Training

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Phased Array Antenna Design.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks