Abstract
This article discusses methods of recognizing images by comparing their color histograms. Different formulas for comparing histograms are compared, as well as various forms of color histograms and different color spaces. Experiments have been carried out with sets of standard images and sets of images to be recognized. In one case, the standard images and the images to be recognized were photographs of the same objects or the same sites with identical lighting, but from a changed aspect. In other cases, both the standards and the images to be recognized were objects on a monochromatic background and on a multicolored background. As a result, robust criteria are proposed for comparing the histograms, and effective types of histograms are also distinguished.
© 2015 Optical Society of America
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription