Abstract
This work describes experiments aimed at finding a straightforward but effective way of comparing face images.We discuss properties of the basic concepts, such as the Euclidean, cosine and correlation metrics, test the simplest version of elastic templates, and compare these solutions with distances based on texture descriptors (Local Ternary Patterns). The influence of selected image processing methods (e.g. bilateral ltering) on image comparison results is also considered. Additionally, the new metric, in which differences between LTP histograms are weighted with alignment coefficients, is proposed.
Citations
-
0
CrossRef
-
0
Web of Science
-
1
Scopus
Author (1)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- materiały konferencyjne indeksowane w Web of Science
- Title of issue:
- International Conference on Computer Vision and Graphics (ICCVG) strony 341 - 352
- Language:
- English
- Publication year:
- 2016
- Bibliographic description:
- Smiatacz M..: Similarity Measures for Face Images: An Experimental Study, W: International Conference on Computer Vision and Graphics (ICCVG), 2016, Springer International Publishing,.
- DOI:
- Digital Object Identifier (open in new tab) 10.1007/978-3-319-46418-3_30
- Verified by:
- Gdańsk University of Technology
seen 104 times