What is it about?

This document presents the implementation of an original method to solve the problem of facial recognition from a single picture of the person, i.e. a single image; the latter can be difficult to exploit, in particular because of changes in facial expression, posture, lighting or even occultation (example of the mask in the difficult health context that we have been experiencing for many months).

Featured Image

Why is it important?

Single-Sample Face Recognition (SSFR) is a computer vision challenge. In this scenario, there is only one example from each individual on which to train the system, making it difficult to identify persons in unconstrained environments, mainly when dealing with changes in facial expression, posture, lighting, and occlusion. This paper discusses the relevance of an original method for SSFR, called Multi-Block Color-Binarized Statistical Image Features (MB-C-BSIF), which exploits several kinds of features, namely, local, regional, global, and textured-color characteristics. The average classification accuracies are 96.17% and 99% for the AR database with two specific protocols (i.e., Protocols I and II, respectively), and 38.01% for the challenging LFW database. These performances are clearly superior to those obtained by state-of-the-art methods. Furthermore, the proposed method uses algorithms based only on simple and elementary image processing operations that do not imply higher computational costs as in holistic, sparse or deep learning methods, making it ideal for real-time identification.

Perspectives

In the future, we aim to explore the effectiveness of combining both deep learning and traditional methods in addressing the SSFR issue. Hybrid features combine hand-crafted features with deep characteristics to collect richer information than those obtained by a single feature extraction method, thus improving the level of recognition. Besides, we plan to develop a deep learning method based on semantic information, such as age, gender, and ethnicity, to solve the problem of SSFR, which is an area that deserves further study. We also aim to investigate and analyze the SSFR issue in un-constrained environments using large-scale databases that hold millions of facial images.

ASSOCIATE PROFESSOR SEBASTIEN JACQUES
Universite Francois-Rabelais de Tours

Read the Original

This page is a summary of: Multi-Block Color-Binarized Statistical Images for Single-Sample Face Recognition, Sensors, January 2021, MDPI AG,
DOI: 10.3390/s21030728.
You can read the full text:

Read

Contributors

The following have contributed to this page