Assessing the Effect of Data Augmentation on Occluded Frontal Faces Using DWT-PCA/SVD Recognition Algorithm

Abstract

The drift towards face-based recognition systems can be attributed to recent advances in supportive technology and emerging areas of application including voting systems, access control, human-computer interactions, entertainments, and crime control. Despite the obvious advantages of such systems being less intrusive and requiring minimal cooperation of subjects, the performances of their underlying recognition algorithms are challenged by the quality of face images, usually acquired from uncontrolled environments with poor illuminations, varying head poses, ageing, facial expressions, and occlusions. Although several researchers have leveraged on the property of bilateral symmetry to reconstruct half-occluded face images, their approach becomes deficient in the presence of random occlusions. In this paper, we harnessed the benefits of the multiple imputation by the chained equation technique and image denoising using Discrete Wavelet Transforms (DWTs) to reconstruct degraded face images with random missing pixels. Numerical evaluation of the study algorithm gave a perfect (100%) average recognition rate each for recognition of occluded and augmented face images. The study also revealed that the average recognition rate for the augmented face images (75.5811) was significantly lower than the average recognition rate (430.7153) of the occluded face images. MICE augmentation is recommended as a suitable data enhancement mechanism for imputing missing data/pixel of occluded face images.

On the search for efficient face recognition algorithm subject to multiple environmental constraints

“…Transform domain denoising of noisy images involves a forward transformation using specified basis functions, a denoising process and an inverse transformation. The forward transformation process renders an output image showing the different frequency components of the noisy image or images showing different resolution form of an input image as in Discrete Wavelet Transforms [32] . [33] posited that the DWT presents a fast and easy way to filter facial images.…”

“…Many researchers [42] , [32] have employed MICE augmentation to reconstruct occluded face images, and recommended MICE as a suitable imputation technique for finding missing pixel values in occluded images.…”

A feature boosted deep learning method for automatic facial expression recognition

“…Finally, the CNN model has been fine-tuned by trading off data augmentation and deep learning features. The effectiveness of data augmentation in occluded faces is proposed in Asiedu et al (2021) .…”