| Title: | HEp-2 Staining Pattern Classification |
| Fulltext: |  |
| Authors: | Strandmark, Petter and Ulén, Johannes and Kahl, Fredrik |
| Year: | 2012 |
| Document Type: | Conference Paper |
| Conference: | International Conference on Pattern Recognition (ICPR) |
| Status: | In Press |
| Refereed: | Yes |
| Publisher: | ffl |
| BibTeX item: |  |
| Abstract: | Classifying images of HEp-2 cells from indirect immunofluorescence has important clinical applications. We have developed an automatic method based on random forests that classifies an HEp-2 cell image into one of six classes. The method is applied to the data set of the ICPR 2012 contest. The previously obtained best accuracy is 79.3% for this data set, whereas we obtain an accuracy of 97.4%. The key to our result is due to carefully designed feature descriptors for multiple level sets of the image intensity. These features characterize both the appearance and the shape of the cell image in a robust manner. |
Similar Publications
- Book:
8th International Conference on Energy Minimazation Methods in Computer Vision and Pattern Recognition, EMMCVPR 2011
Yuri Boykov
Fredrik Kahl
Victor Lempitsky
Frank Schmidt - Conference paper:
Blood Flow Patterns in the Left Ventricle of the Healthy Human Heart Described by Lagrangian Coherent Structures Computed from 4D Phase Contrast MRI
Johannes Töger
Johannes Ulén
Marcus Carlsson
Gustaf Söderlind
Hĺkan Arheden
Questions: webmaster
Last updated: 2012-01-17
Centre for Mathematical Sciences, Box 118, SE-22100, Lund. Phone: 046-222 00 00