A4 Refereed article in a conference publication
Novel feature descriptor based on microscopy image statistics
Authors: Bayramoglu N, Kannala J, Akerfelt M, Kaakinen M, Eklund L, Nees M, Heikkila J
Conference name: IEEE International Conference on Image Processing (ICIP)
Publishing place: Quebec City, CANADA
Publication year: 2015
Journal: IEEE International Conference on Image Processing
Book title : 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Journal name in source: 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP)
Journal acronym: IEEE IMAGE PROC
First page : 2695
Last page: 2699
Number of pages: 5
ISBN: 978-1-4799-8339-1
ISSN: 1522-4880
DOI: https://doi.org/10.1109/ICIP.2015.7351292
Abstract
In this paper, we propose a novel feature description algorithm based on image statistics. The pipeline first performs independent component analysis on training image patches to obtain basis vectors (filters) for a lower dimensional representation. Then for a given image, a set of filter responses at each pixel is computed. Finally, a histogram representation, which considers the signs and magnitudes of the responses as well as the number of filters, is applied on local image patches. We propose to apply this idea to a microscopy image pixel identification system based on a learning framework. Experimental results show that the proposed algorithm performs better than the state-of-the-art descriptors in biomedical images of different microscopy modalities.
In this paper, we propose a novel feature description algorithm based on image statistics. The pipeline first performs independent component analysis on training image patches to obtain basis vectors (filters) for a lower dimensional representation. Then for a given image, a set of filter responses at each pixel is computed. Finally, a histogram representation, which considers the signs and magnitudes of the responses as well as the number of filters, is applied on local image patches. We propose to apply this idea to a microscopy image pixel identification system based on a learning framework. Experimental results show that the proposed algorithm performs better than the state-of-the-art descriptors in biomedical images of different microscopy modalities.