Facial Recognition: Using Experimental Color Image Processing Techniques

Date

2020

Authors

Trevino, Isaac

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Facial Recognition is a developing topic as systems are improved almost daily, whether such systems benefit the public or if security outweighs popular opinion. Regardless, most facial recognition systems rely on sophisticated neural networks which use training data to produce accurate models for application [1]. However, with drawbacks for certain models such as relying on gray-scale images rather than color images introduces disadvantages. This Thesis will be a general overview of facial recognition systems using color image processing techniques to improve current pattern recognition methods and understanding the potential of such systems in the near-future. The use of color data could be used as features to be classified in pattern recognition models by introducing image enhancement and color transformation methods. For most security surveillance cctv-cameras are still the main source of population identification converting most images to gray scale in the process. With state-of-the-art bio-metrics such as thermal imaging, three-dimensional facial modeling will be supplanted without color image processing. This happens to be a growing concern where accuracy does benefit popular opinion, and where all possibilities should be considered.

Description

This item is available only to currently enrolled UTSA students, faculty or staff. To download, navigate to Log In in the top right-hand corner of this screen, then select Log in with my UTSA ID.

Keywords

Facial Recognition, Histogram Equalization, Image Processing, LBP, Quantum Image, Quaternion Image

Citation

Department

Electrical and Computer Engineering