loading page

Examining the Impact of Data Sufficiency in Face Classification Accuracy using PCA and HOG
  • Navin Ipe
Navin Ipe

Corresponding Author:[email protected]

Author Profile


This research presents an empirical analysis on the realities of feature extraction and generalization of images of human faces. Experiments performed using principal component analysis (PCA) and histogram of oriented gradients (HOG) provided new insights on the variance of classification accuracy based on the quantity of data, and the actuality of data captured by specific principal components. HOG features provided greater classification accuracy for exact matches, and eigen faces of PCA were more accurate for generalization to previously unseen data. The results presented offer practical insights that can assist in the selection and design of algorithms that utilize PCA or HOG for data analysis. This is of particular significance in avoiding errors when data may undergo variations in sample size.
16 May 2024Submitted to TechRxiv
21 May 2024Published in TechRxiv