Oriented Shape Index Histograms for Cell Classification

Anders Boesen Lindbo Larsen, Anders Bjorholm Dahl, Rasmus Larsen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We propose a novel extension to the shape index histogram feature descriptor where the orientation of the second-order curvature is included in the histograms. The orientation of the shape index is reminiscent but not equal to gradient orientation which is widely used for feature description. We evaluate our new feature descriptor using a public dataset consisting of HEp-2 cell images from indirect immunoflourescence lighting. Our results show that we can improve classification performance significantly when including the shape index orientation. Notably, we show that shape index orientation outperforms the gradient orientation on the dataset.
Original languageEnglish
Title of host publicationImage Analysis : 19th Scandinavian Conference, SCIA 2015 Copenhagen, Denmark, June 15–17, 2015 Proceedings
Number of pages10
PublisherSpringer Science+Business Media
Publication date2015
Pages29-38
ISBN (Print)978-3-319-19664-0
ISBN (Electronic)978-3-319-19665-7
DOIs
Publication statusPublished - 2015
Event19th Scandinavian Conference on Image Analysis - Copenhagen, Denmark
Duration: 15 Jun 201517 Jun 2015
Conference number: 19
http://www.scia2015.org/

Conference

Conference19th Scandinavian Conference on Image Analysis
Number19
Country/TerritoryDenmark
CityCopenhagen
Period15/06/201517/06/2015
Internet address
SeriesLecture Notes in Computer Science
ISSN0302-9743

Fingerprint

Dive into the research topics of 'Oriented Shape Index Histograms for Cell Classification'. Together they form a unique fingerprint.

Cite this