Results 1 -
2 of
2
Semantic evaluation and efficiency comparison of the edge pixel neighboring histogram in image retrieval
- in WITSP’02 first workshop on the internet, telecommunications and signal processing
, 2002
"... A novel approach in image retrieval based on middle-level features, instead of low-level features, is applied in trademark matching problem. The approach is de-veloped utilizing edge pixel neighboring histograms for capturing the overall image structure. The closeness of the method to human perceptu ..."
Abstract
-
Cited by 3 (3 self)
- Add to MetaCart
(Show Context)
A novel approach in image retrieval based on middle-level features, instead of low-level features, is applied in trademark matching problem. The approach is de-veloped utilizing edge pixel neighboring histograms for capturing the overall image structure. The closeness of the method to human perceptual judgment is evaluated by a subjective test along with the efficiency in com-parison with four other methods known from the liter-ature. The query set and the image database used in the tests are taken from the MPEG-7 dataset and the ex-perimental results show a significant supremacy in se-mantic compatibility over the histogram of edge angles, MPEG-7’s edge histogram descriptor (EHD), and the in-variant moments method. The proposed method is more efficient than the correlation method which is closer to human perception. 1
