Linear models of Cumulative Distribution Function for content based medical image retrieval

K. N. Manjunath, U. C. Niranjan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We propose an Image matching method based n Cumulative Distribution Function (CDF). The CDF f the query and database Images are approximated by piecewise linear models with two parameters, slope and intercept at various grayscale intervals. The equations solving the least squares line fitting algorithm are very simple to form, due to closed form expressions The contiguous set of lines approximating the CDFs enables us to compare query and database images with corresponding estimated slopes and intercepts. As the dynamic range f CDF is from 0 to 1, images of different sizes can be compared. Approximation of CDFs with lines further reduces the dimension f the image features and thus improves the speed f matching. Also, the monotonically increasing CDF is well suited for approximations with lines. Resolving the CDF with lines f different lengths recasts the matching to a hierarchical methodology.

Original languageEnglish
Title of host publicationProceedings of the 2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Pages6472-6475
Number of pages4
Volume7 VOLS
Publication statusPublished - 01-12-2005
Event2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005 - Shanghai, China
Duration: 01-09-200504-09-2005

Conference

Conference2005 27th Annual International Conference of the Engineering in Medicine and Biology Society, IEEE-EMBS 2005
Country/TerritoryChina
CityShanghai
Period01-09-0504-09-05

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Linear models of Cumulative Distribution Function for content based medical image retrieval'. Together they form a unique fingerprint.

Cite this