Histogram preserving image transformations

Citation
E. Hadjidemetriou et al., Histogram preserving image transformations, INT J COM V, 45(1), 2001, pp. 5-23
Citations number
50
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
INTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN journal
09205691 → ACNP
Volume
45
Issue
1
Year of publication
2001
Pages
5 - 23
Database
ISI
SICI code
0920-5691(200110)45:1<5:HPIT>2.0.ZU;2-K
Abstract
Histograms are used to analyze and index images. They have been found exper imentally to have low sensitivity to certain types of image morphisms, for example, viewpoint changes and object deformations. The precise effect of t hese image morphisms on the histogram, however, has not been studied. In th is work we derive the complete class of local transformations that preserve or scale the magnitude of the histogram of all images. We also derive a mo re general class of local transformations that preserve the histogram relat ive to a particular image. To achieve this, the transformations are represe nted as solutions to families of vector fields acting on the image. The loc al effect of fixed points of the fields on the histograms is also analyzed. The analytical results are verified with several examples. We also discuss several applications and the significance of these transformations for his togram indexing.