Abstract
We propose trainable filters, which we call COSFIRE (Combination Of Shifted Filter REsponses), and use to detect vascular bifurcations in retinal images. We configure a COSFIRE filter to be selective for a bifurcation that is specified by a user in a single-step training phase. The automatic configuration comprises the selection of channels of a bank of Gabor filters and the determination of certain blur and shift parameters. A COSFIRE filter response is computed as the geometric mean of the blurred and shifted responses of the selected Gabor biters, The proposed filters share similar properties with some shape-selective neurons in visual cortex. With only five filters we achieve a recall of 98.57% at a precision of 95.37% on the 40 binary retinal images (from DRIVE), containing more than 5000 bifurcations.
Original language | English |
---|---|
Title of host publication | 2012 25TH INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS) |
Editors | P Soda, F Tortorella |
Place of Publication | NEW YORK |
Publisher | IEEE (The Institute of Electrical and Electronics Engineers) |
Number of pages | 4 |
ISBN (Print) | 978-1-4673-2051-1 |
Publication status | Published - 2011 |
Event | 25th International Symposium on Computer-Based Medical Systems (CBMS) - , Italy Duration: 20-Jun-2012 → 22-Jun-2012 |
Other
Other | 25th International Symposium on Computer-Based Medical Systems (CBMS) |
---|---|
Country/Territory | Italy |
Period | 20/06/2012 → 22/06/2012 |
Keywords
- FEATURES
- IMAGES