Face Recognition for Blind People

Abstract

It is estimated that 285 million people globally are visually impaired, and without additional interventions, these numbers are predicted to increase significantly. One of the most difficult tasks faced by the visually impaired is identification of people. The inability to recognize known individuals in the absence of audio or haptic cues severely limits the visually impaired in their social interactions and puts them at risk from a security perspective. In this thesis Matlab software was used to simulate a system that aids the blind person to recognize his family and friends facial images that are stored in a database, and if a match is found on the database, the system will announce the name of the person via speakers to the blind person. Two face recognition algorithms will be used; Principle Component Analysis (PCA), and Hidden Markov Model (HMM) to compare their performance. The simulation considered the recognition of a static facial image (photo) and a live facial image. The results showed that the PCA algorithm performs better than the HMM. It has a small recognition time and work properly under different face orientation.