Illumination Normalization of Face Images Using Layers Extraction and Histogram Processing

An illumination normalization algorithm for face images is proposed. For preprocessing of the input image, low light is enhanced to improve image quality. The reflection layer of image is normalized for edge preservation and to remove the artifacts, which is added to a small-scale image. Noise is re...

Full description

Saved in:
Bibliographic Details
Published in:Arabian journal for science and engineering (2011) 2021-04, Vol.46 (4), p.3319-3328
Main Authors: Iqbal, Mehwish, Riaz, Muhammad Mohsin, Ghafoor, Abdul, Ahmad, Attiq
Format: Article
Language:English
Subjects:
Algorithms
Engineering
Histograms
Humanities and Social Sciences
Illumination
Image acquisition
Image contrast
Image enhancement
Image quality
multidisciplinary
Research Article-Computer Engineering and Computer Science
Science
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:An illumination normalization algorithm for face images is proposed. For preprocessing of the input image, low light is enhanced to improve image quality. The reflection layer of image is normalized for edge preservation and to remove the artifacts, which is added to a small-scale image. Noise is removed, and details are enhanced to improve the quality of the image. Contrast is corrected by histogram truncation. Shape from shading is extracted and passed through a guided filter to acquire a face image having illumination normalized. Simulation outcome on Multi-PIE, CAS-PEAL, and Extended Yale B face dataset shows the strength of the suggested approach.
ISSN:2193-567X
1319-8025
2191-4281
DOI:10.1007/s13369-020-05142-w