PCA means Principal Component Analysis.
It is a method to make data smaller and simpler.
PCA keeps the most important information and removes extra data.
It works by finding directions where data changes the most.
These important directions are called principal components.
In face recognition, one face image has thousands of pixels.
PCA converts each face image into few important features.
These features are called eigenfaces.
Faces are compared using these features instead of full images.
This makes face recognition faster and more accurate.