Dados do Trabalho

Título

MODELING TEXTILE IMAGES WITH MARKOV RANDOM FIELDS

Data de titulação

19/02/2018

Instituição de titulação

IMECC - UNICAMP

RESUMO (abstract)

When new textile dyeing technologies are developed, evaluating the quality of these
techniques involves measuring the resulting color homogeneity using digital images. The
presence of a texture effect caused by the fabric creates a sophisticated dependence
structure in pixels coloring. Fourier transform is used with regularization techniques to
remove the texture signal from the image. Images are then modeled as a hidden Markov
random field and Fourier basis as covariates, allowing an entropy-based evaluation of color
homogeneity using the filtered signal that corresponds to the dyeing process only.