Real Time Face Recognition with limited training data: Feature Transfer Learning integrating CNN and Sparse Approximation

Abstract

It is highly challenging to obtain high performance with limited and unconstrained data in real time face recognition applications. Sparse Approximation is a fast and computationally efficient method for the above application as it requires no training time as compared to deep learning methods. It eliminates the training time by assuming that the test image can be approximated by the sum of individual contributions of the training images from different classes and the class with maximum contribution is closest to the test image. The efficiency of the Sparse Approximation method can be further increased by providing high quality features as input for classification. Hence, we propose to integrate pre-trained CNN architecture to extract the highly discriminative features from the image dataset for Sparse classification. The proposed approach provides better performance even for one training image per class in complex environment as compared to the existing methods. Highlight of the present approach is the results obtained for LFW dataset with one and thirteen training images per class are 84.86% and 96.14% respectively, whereas the existing deep learning methods use a large amount of training data to achieve comparable results.

Feature Level Combination for Face Recognition Based on Convolutional Neural Networks

“…The outcomes obtained when using a single approach or a combination of two models, GoogLeNet and VggNet-16, with all datasets are provided in Table (2). The results of all approaches GoogLeNet-SVM, VggNet-SVM, and combination-SVM with all datasets are displayed in Figure (10) according to each approach and Figure (9) according to each dataset.…”

“…S. Bajpai et al the author presents a method for a face recognition system combining pre-trained Inception-Resnetv1 CNN architecture for extracting image features and sparse linear approximation for classification. The experiment shows that the approach performs better even in an unconstrained environment as compared to the existing methods [9]. Y. Yang et al a new face matching approach called the SR-CNN model has been introduced a combination of the CNN, the rotation-invariant textures feature (RITF) vector, and the scale-invariant features transform (SIFT) vector.…”