Face Identification from Manipulated Facial Images using SIFT

TL;DR

This paper presents a method for identifying faces from heavily manipulated images using SIFT features, comparing its effectiveness against eigenface approaches in real-world scenarios.

Contribution

It introduces the use of SIFT features for face identification from manipulated images and compares its performance with eigenface methods.

Findings

SIFT-based method outperforms eigenface in manipulated face identification

SIFT features provide robustness against facial image alterations

Experimental results validate the effectiveness of the proposed approach

Abstract

Editing on digital images is ubiquitous. Identification of deliberately modified facial images is a new challenge for face identification system. In this paper, we address the problem of identification of a face or person from heavily altered facial images. In this face identification problem, the input to the system is a manipulated or transformed face image and the system reports back the determined identity from a database of known individuals. Such a system can be useful in mugshot identification in which mugshot database contains two views (frontal and profile) of each criminal. We considered only frontal view from the available database for face identification and the query image is a manipulated face generated by face transformation software tool available online. We propose SIFT features for efficient face identification in this scenario. Further comparative analysis has been given with well known eigenface approach. Experiments have been conducted with real case images to evaluate the performance of both methods.