Semantic classification of images based on their low-level visual features is a challenging task in the field of image retrieval and classification. In this paper, the effect of weighting color, shape and texture feature vectors and also their components on image classification is investigated. The way that the classification rate is affected by the database size is also studied. A database of 1000 images from 10 semantic groups, 100 images in each group, is used. A k-nearest neighbor classifier is employed and the leave-one-out rule is used to evaluate the results. The optimum weights for each type of the feature vectors and also their components are found by a genetic algorithm.
Nezamabadi-pour,H. and Kabir,E. (2004). Combining Low-level Features for Semantic Image Classification. (e215951). The CSI Journal on Computer Science and Engineering, 2(1), e215951
MLA
Nezamabadi-pour,H. , and Kabir,E. . "Combining Low-level Features for Semantic Image Classification" .e215951 , The CSI Journal on Computer Science and Engineering, 2, 1, 2004, e215951.
HARVARD
Nezamabadi-pour H., Kabir E. (2004). 'Combining Low-level Features for Semantic Image Classification', The CSI Journal on Computer Science and Engineering, 2(1), e215951.
CHICAGO
H. Nezamabadi-pour and E. Kabir, "Combining Low-level Features for Semantic Image Classification," The CSI Journal on Computer Science and Engineering, 2 1 (2004): e215951,
VANCOUVER
Nezamabadi-pour H., Kabir E. Combining Low-level Features for Semantic Image Classification. CSIonJCSE, 2004; 2(1): e215951.
The CSI Journal on Computer Science and Engineering