Effect of Super Resolution on High Dimensional Features for Unsupervised Face Recognition in the Wild

• Published in: 2017 IEEE Applied Imagery Pattern Recognition Workshop (AIPR) pp. 1 - 5
• Main Authors: ElSayed, Ahmed, Mahmood, Ausif, Sobh, Tarek
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2017
• Subjects: Face; Face recognition; Feature extraction; high dimensional features; Histograms; Image resolution; label faces in the wild (lfw); Protocols; Signal resolution; Super-Resolution; unsupervised learning
• ISSN: 2332-5615
• DOI: 10.1109/AIPR.2017.8457967

Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wild, environment. Because of cameras' limited capabilities, it is common for these captured facial images to be blurred or low resolution. Super resolution algorithms are therefore crucial in improving the resolution of such images especially when the image size is small and enlargement is required. This paper aims to demonstrate the effect of one of the state-of-the-art algorithms in the field of image super resolution. To demonstrate the functionality of the algorithm, various before and after 3D face alignment cases are provided using the images from the Labeled Faces in the Wild (lfw) dataset. Resulting images are subject to test on a closed set recognition protocol using unsupervised algorithms with high dimensional extracted features. The inclusion of super resolution algorithm resulted in significant improvement in recognition rate over recently reported results obtained from unsupervised algorithms on the same dataset.