Similarity Estimation of Textile Materials Based on Image Quality Assessment Methods

摘要

In this paper some experimental results obtained by the application of various image quality assessment methods for the estimation of similarity of textile materials are presented. Such approach is considered as a part of an artificial intelligence based system developed for the recognition of clothing styles based on multi-dimensional analysis of descriptors and features. For the verification of the usefulness of image quality metrics for this purpose, mainly those based on the comparison of the local similarity of image fragments have been chosen. Nevertheless, since the most of them are applied only for grayscale images, various methods of color to grayscale conversion have been analyzed. Obtained results are promising and may be successfully applied in combination with some other algorithms used e.g. in CBIR systems. Since the analyzed metrics do not use any information related to shape of objects, further combination with shape and color descriptors may be used.