Comparing computational and human measures of visual similarity
There have been many attempts to quantify visual similarity within different categories of objects, with a view to using such measures to predict impaired recognition performance. Although many studies have linked measures of visual similarity to behavioral outcomes associated with object recognition, there has been little research on whether these measures are associated with human ratings of perceived similarity. In this work, we compare similarity measures extracted from Principal Component Analysis, Isometric Feature Mapping and wavelets representations with ratings of human subjects. Our results show that features extracted by calculating the standard deviation of wavelet coefficients provides the closest fit to the human rating data of all the methods we applied here.
Item Type | Other |
---|---|
Date Deposited | 27 Jul 2024 00:19 |
Last Modified | 27 Jul 2024 00:19 |
-
picture_as_pdf - 901760.pdf
Explore Further
Read more research from the creator(s):
Find work associated with the faculties and division(s):