Surveying Facial Recognition Models for Diverse Indian Demographics: A Comparative Analysis on LFW and Custom Dataset

TL;DR

The paper addresses the fairness and accuracy gaps in facial recognition for diverse Indian demographics by introducing the IITJ Faces of Academia Dataset (JFAD) and conducting a cross-dataset evaluation against LFW. It benchmarks traditional, CNN-based, and hybrid approaches under a unified pipeline, revealing that CNNs and Hybrid models generally perform best, while traditional methods can excel on JFAD with proper tuning. The findings highlight the critical role of region-specific benchmarks in driving equitable performance and guide future development toward culturally aware recognition systems. Overall, the work provides a rigorous, demographically informed assessment framework and emphasizes the need to expand diverse datasets to improve real-world applicability in India.

Abstract

Facial recognition technology has made significant advances, yet its effectiveness across diverse ethnic backgrounds, particularly in specific Indian demographics, is less explored. This paper presents a detailed evaluation of both traditional and deep learning-based facial recognition models using the established LFW dataset and our newly developed IITJ Faces of Academia Dataset (JFAD), which comprises images of students from IIT Jodhpur. This unique dataset is designed to reflect the ethnic diversity of India, providing a critical test bed for assessing model performance in a focused academic environment. We analyze models ranging from holistic approaches like Eigenfaces and SIFT to advanced hybrid models that integrate CNNs with Gabor filters, Laplacian transforms, and segmentation techniques. Our findings reveal significant insights into the models' ability to adapt to the ethnic variability within Indian demographics and suggest modifications to enhance accuracy and inclusivity in real-world applications. The JFAD not only serves as a valuable resource for further research but also highlights the need for developing facial recognition systems that perform equitably across diverse populations.

Figures (9)

• Figure 1: Methodology overview.
• Figure 2: Subjects and Images from proposed JFAD dataset (after Face Extraction )
• Figure 3: Accuracy vs K value plot for LDA+KNN.
• Figure 4: Laplacianfaces obtained from LFW dataset
• Figure 5: Eigenfaces obtained from LFW dataset