Evaluating the Influence of Image Modifications upon Content-Based Multimedia Retrieval

In this paper, evaluation of properties of MUVIS software package is presented. Images are modified in several ways (e.g. blurred, noise added, etc.) and added into the existing MUVIS databases. Simulations show that a satisfactory retrieval performance can be obtained from small set of extracted features (in comparison with large default set), even when significantly different number of images in databases are observed. YUV feature (color), GLCM (texture) and CANN (shape) feature are extracted from images. Applied image modifications have greatest impact on extracted YUV feature (color), which differs most in comparison with original image, while the lowest impact is observed on GLCM feature (gray level co-occurrence matrix), which shows that texture was not significantly changed during image modifications. CANN feature (shape and edges extraction feature) is only slightly different from original image. These results are similar for databases with various numbers of elements