About this document

Side Face to Front Face Recognition by 18-1211 Apoorva Gangyada is a document available to read on EtoBox.

This document summarizes a project on side face recognition using GANs. It introduces the challenge of recognizing faces from side angles using a trained GAN model to generate a front face from a side face input. The motivation is that existing approaches only use front faces, failing to recognize poses. The approach uses OpenCV, Haar cascades for detection and a GAN with generator and discriminator for side-to-front generation. Results showed 96.4% accuracy after 100 epochs of GAN training. Future work cou

Author

18-1211 Apoorva Gangyada

Language

EN