Medical ultrasound image similarity measurement by human visual system (HVS) modelling

D de Cunha, L Eadie, B Adams, D Hawkes

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

Abstract

We applied a four stage model of human vision to the problem of similarity measurement of medical (liver) ultrasound images. The results showed that when comparing a given image to a set that contained images with similar features, the model was able to correctly identify the most similar image in the set. Additionally, the shape of the similarity function closely followed a subjective measure of visual similarity for images around the best match. Removing some computational steps to reduce processing time enabled the comparison method to run in near real-time (< 5 seconds), but with some acceptable loss of accuracy. These results could not be achieved using conventional similarity measurements based on image grey level statistics.

Original languageEnglish
Title of host publicationBIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS
EditorsHH Bulthoff, SW Lee, TA Poggio, C Wallraven
Place of PublicationBERLIN
PublisherSPRINGER-VERLAG BERLIN
Pages340-347
Number of pages8
ISBN (Print)3-540-00174-3
Publication statusPublished - 2002
Event2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002) - TUBINGEN
Duration: 22 Nov 200224 Nov 2002

Conference

Conference2nd International Workshop on Biologically Motivated Computer Vision (BMCV 2002)
CityTUBINGEN
Period22/11/0224/11/02

Cite this

de Cunha, D., Eadie, L., Adams, B., & Hawkes, D. (2002). Medical ultrasound image similarity measurement by human visual system (HVS) modelling. In HH. Bulthoff, SW. Lee, TA. Poggio, & C. Wallraven (Eds.), BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDINGS (pp. 340-347). SPRINGER-VERLAG BERLIN.