Developing a Measure of Similarity between Pixel Signatures
Author(s) -
A. Holmes,
Chris Taylor
Publication year - 1999
Publication title -
citeseer x (the pennsylvania state university)
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5244/c.13.61
Subject(s) - measure (data warehouse) , similarity measure , earth mover's distance , pixel , computer science , similarity (geometry) , euclidean distance , artificial intelligence , pattern recognition (psychology) , receiver operating characteristic , data mining , image (mathematics) , machine learning
Our previous work in computer-aided mammography has used scaleorientation pixel signatures that provide a rich description of local structure. We describe work using the transportation (`earth mover') algorithm to de ne a measure of similarity between two signatures that recognises similar structures whilst remaining robust to background variability and the presence of other structures. Speci cally, we investigate an un-normalised, normalised and novel best-partialmatching (BPM) approach to measuring this transportation distance and compare it with Euclidean distance. Receiver operating characteristic (ROC) methodology is used to compare performance and an example of clinical application is given. The BPM approach outperforms the other methods.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom