Optimizing Genetic Algorithms with Multilayer Perceptron Networks for Enhancing TinyFace Recognition

2024-12-30

Data and Metadata

AI Summary

To address the low recognition accuracy of few-shot, low-quality face images in the TinyFace dataset, this paper proposes a GA-MLP-PCA collaborative optimization framework: genetic algorithm (GA)-driven feature selection for a multilayer perceptron (MLP), jointly integrated with principal component analysis (PCA) for dimensionality reduction, enabling end-to-end fine-tuning on TinyFace. We present the first systematic empirical validation that GA exhibits superior robustness over conventional PCA in selecting discriminative features from highly complex facial data. Furthermore, we uncover a complementary synergy between feature selection and dimensionality reduction—where GA refines feature relevance while PCA preserves maximal variance in the reduced subspace. Experiments demonstrate significant improvements in recognition accuracy over both standalone MLP and PCA baselines. Crucially, the method maintains stable performance under severe degradations—including noise, motion blur, and low resolution—establishing a novel paradigm for resource-constrained, few-shot face recognition.

Technology Category

• Machine Learning: Dimensionality Reduction/Feature Selection
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This study conducts an empirical examination of MLP networks investigated through a rigorous methodical experimentation process involving three diverse datasets: TinyFace, Heart Disease, and Iris. Study Overview: The study includes three key methods: a) a baseline training using the default settings for the Multi-Layer Perceptron (MLP), b) feature selection using Genetic Algorithm (GA) based refinement c) Principal Component Analysis (PCA) based dimension reduction. The results show important information on how such techniques affect performance. While PCA had showed benefits in low-dimensional and noise-free datasets GA consistently increased accuracy in complex datasets by accurately identifying critical features. Comparison reveals that feature selection and dimensionality reduction play interdependent roles in enhancing MLP performance. The study contributes to the literature on feature engineering and neural network parameter optimization, offering practical guidelines for a wide range of machine learning tasks

Problem

• Optimizing genetic algorithms for TinyFace recognition
• Comparing feature selection and dimensionality reduction methods
• Enhancing MLP performance in complex datasets

Innovation

• Genetic Algorithm optimizes MLP feature selection
• PCA reduces dimensions for noise-free datasets
• Combined methods enhance TinyFace recognition accuracy