Robust face recognition via sparse reconstruction vector

Cemil Turan

2017

Closed access Metadata (CSL-JSON)
DOI 10.1109/icecco.2017.8333342
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

Recognition rate and recognition time of algorithms are the major issues in face recognition. There are several types of algorithm used for face recognition such as eigenface or fisherface. Face recognition based sparse representation is successfully used in this area recently. In this work, both recognition rate and recognition time of Principal Component Analysis-PCA (eigenface) and Sparse Representation-based Classification-SRC are compared. SRC algorithm is modified for a high recognition rate. The simulation results show that modified SRC algorithm is indisputably superior to PCA algorithm for performance of recognition rate and algorithm time if the training set has enough number of samples.