Fast and efficient compact feature descriptor for face recognition
Leona Thomas Kutty, S Lakshmy · 2017
Face recognition task has been used worldwide due to its effectiveness in different disciplines, but because of the complexity of the procedures it is a very difficult task to accurately recognize variations in face images. Large set of feature extraction of face is difficult to handle since the storage and the computation of such dense feature makes the process of recognition more complicated. The encoding scheme used in this work reduces large set of features into a less compact representation by using the concept of intra user correlation. By reducing the facial features, storage and computation will be cheaper. A sparse classifier is used for the matching of the face recognition technique. The sparse classifier reduces the time consumption for the recognition process.