RT Journal Article
T1 Analyzing the influence of contrast in large-scale recognition of natural images
A1 Sánchez, Ángel
A1 Moreno, A. Belén
A1 Vélez Serrano, Daniel
A1 Vélez, José F.
AB This paper analyzes both the isolated influence of illumination quality in 2D facial recognition and also the influence of contrast measures in large-scale recognition of low-resolution natural images. First, using the Yale Face Database B, we have shown that by separately estimating the illumination quality of facial images (through a fuzzy inference system that combines average brightness and global contrast of the patterns) and by recognizing the same images using a multilayer perceptron, there exists a nearly-linear correlation between both illumination and recognition results. Second, we introduced a new contrast measure, called Harris Points Measured Contrast (HPMC), which assigns values of contrast in a more consistent form to images, according to their recognition rate than other global and local compared contrast analysis methods. For our experiments on image contrast analysis, we have used the CIFAR-10 dataset with 60,000 images and convolutional neural networks as classification models. Our results can be considered to decide if it is worth using a given test image, according to its calculated contrast applying the proposed HPCM metric, for further recognition tasks.
PB IOS Press
SN 1069-2509
YR 2016
FD 2016
LK https://hdl.handle.net/20.500.14352/98372
UL https://hdl.handle.net/20.500.14352/98372
LA eng
NO Á. Sánchez, A.B. Moreno, D. Vélez, J.F. Vélez, Analyzing the influence of contrast in large-scale recognition of natural images, ICA 23 (2016) 221–235. https://doi.org/10.3233/ICA-160516.
NO Ministerio de Economía, Comercio y Empresa (España)
DS Docta Complutense
RD 17 abr 2025