Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification

TL;DR

Hy-Facial introduces a hybrid feature extraction framework that fuses global VGG19 embeddings with local SIFT and ORB descriptors, followed by clustering-based feature selection and a broad comparison of dimensionality reduction methods. The study demonstrates that nonlinear DR, particularly UMAP, combined with a Random Forest classifier, yields the best FER performance on FER-Plus, achieving up to 83.3% accuracy and surpassing linear reductions and single-feature baselines. By systematically evaluating six DR techniques and three classifiers, the work provides a practical blueprint for balancing feature richness, dimensionality, and computational efficiency in high-dimensional image classification. The findings highlight the pivotal role of dimensionality reduction as both a pre-processing and discriminative step, with broad implications for scalable, interpretable FER systems.

Abstract

Facial expression classification remains a challenging task due to the high dimensionality and inherent complexity of facial image data. This paper presents Hy-Facial, a hybrid feature extraction framework that integrates both deep learning and traditional image processing techniques, complemented by a systematic investigation of dimensionality reduction strategies. The proposed method fuses deep features extracted from the Visual Geometry Group 19-layer network (VGG19) with handcrafted local descriptors and the scale-invariant feature transform (SIFT) and Oriented FAST and Rotated BRIEF (ORB) algorithms, to obtain rich and diverse image representations. To mitigate feature redundancy and reduce computational complexity, we conduct a comprehensive evaluation of dimensionality reduction techniques and feature extraction. Among these, UMAP is identified as the most effective, preserving both local and global structures of the high-dimensional feature space. The Hy-Facial pipeline integrated VGG19, SIFT, and ORB for feature extraction, followed by K-means clustering and UMAP for dimensionality reduction, resulting in a classification accuracy of 83. 3\% in the facial expression recognition (FER) dataset. These findings underscore the pivotal role of dimensionality reduction not only as a pre-processing step but as an essential component in improving feature quality and overall classification performance.

Figures (2)

• Figure 1: Pipeline of the proposed model
• Figure 2: Performance Comparison of Different Algorithms with Dimensionality Reduction