HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM

Siyamalan Manivannan; Wenqi Li; Shazia Akbar; Ruixuan Wang; Jianguo Zhang; Stephen J. McKenna

doi:10.1109/I3A.2014.20

HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM

Siyamalan Manivannan (Lead / Corresponding author), Wenqi Li, Shazia Akbar, Ruixuan Wang, Jianguo Zhang, Stephen J. McKenna

Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Citations (Scopus)

Abstract

A pattern recognition system was developed to classify immunofluorescence images of HEp-2 specimens into seven classes: homogeneous, speckled, nucleolar, centromere, golgi, nuclear membrane, and mitotic spindle. Root-SIFT features together with multi-resolution local patterns were used to capture local shape and texture information. Sparse coding with max-pooling was applied to get an image representation from these local features. Specimens were classified using a linear support vector machine. Leave-one-specimen-out experiments on the I3A Contest Task 2 data set predicted a mean class accuracy of 89.9%.

Original language	English
Title of host publication	Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014
Publisher	IEEE Computer Society
Pages	41-44
Number of pages	4
ISBN (Print)	9781479942527
DOIs	https://doi.org/10.1109/I3A.2014.20
Publication status	Published - 2014
Event	13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images - Stockholm Waterfront, Stockholm, Sweden Duration: 24 Aug 2014 → 24 Aug 2014 http://i3a2014.unisa.it/

Workshop

Workshop	13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images
Country/Territory	Sweden
City	Stockholm
Period	24/08/14 → 24/08/14
Internet address	http://i3a2014.unisa.it/

ASJC Scopus subject areas

Computer Vision and Pattern Recognition

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/I3A.2014.20

Cite this

@inproceedings{1752b8a27eb64fda98967b0527abacc0,

title = "HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM",

abstract = "A pattern recognition system was developed to classify immunofluorescence images of HEp-2 specimens into seven classes: homogeneous, speckled, nucleolar, centromere, golgi, nuclear membrane, and mitotic spindle. Root-SIFT features together with multi-resolution local patterns were used to capture local shape and texture information. Sparse coding with max-pooling was applied to get an image representation from these local features. Specimens were classified using a linear support vector machine. Leave-one-specimen-out experiments on the I3A Contest Task 2 data set predicted a mean class accuracy of 89.9\%.",

author = "Siyamalan Manivannan and Wenqi Li and Shazia Akbar and Ruixuan Wang and Jianguo Zhang and McKenna, \{Stephen J.\}",

year = "2014",

doi = "10.1109/I3A.2014.20",

language = "English",

isbn = "9781479942527",

pages = "41--44",

booktitle = "Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014",

publisher = "IEEE Computer Society",

note = "13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images ; Conference date: 24-08-2014 Through 24-08-2014",

url = "http://i3a2014.unisa.it/",

}

Manivannan, S, Li, W, Akbar, S, Wang, R, Zhang, J & McKenna, SJ 2014, HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM. in Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014. IEEE Computer Society, pp. 41-44, 13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images, Stockholm, Sweden, 24/08/14. https://doi.org/10.1109/I3A.2014.20

HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM. / Manivannan, Siyamalan (Lead / Corresponding author); Li, Wenqi; Akbar, Shazia et al.
Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014. IEEE Computer Society, 2014. p. 41-44.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM

AU - Manivannan, Siyamalan

AU - Li, Wenqi

AU - Akbar, Shazia

AU - Wang, Ruixuan

AU - Zhang, Jianguo

AU - McKenna, Stephen J.

PY - 2014

Y1 - 2014

N2 - A pattern recognition system was developed to classify immunofluorescence images of HEp-2 specimens into seven classes: homogeneous, speckled, nucleolar, centromere, golgi, nuclear membrane, and mitotic spindle. Root-SIFT features together with multi-resolution local patterns were used to capture local shape and texture information. Sparse coding with max-pooling was applied to get an image representation from these local features. Specimens were classified using a linear support vector machine. Leave-one-specimen-out experiments on the I3A Contest Task 2 data set predicted a mean class accuracy of 89.9%.

AB - A pattern recognition system was developed to classify immunofluorescence images of HEp-2 specimens into seven classes: homogeneous, speckled, nucleolar, centromere, golgi, nuclear membrane, and mitotic spindle. Root-SIFT features together with multi-resolution local patterns were used to capture local shape and texture information. Sparse coding with max-pooling was applied to get an image representation from these local features. Specimens were classified using a linear support vector machine. Leave-one-specimen-out experiments on the I3A Contest Task 2 data set predicted a mean class accuracy of 89.9%.

UR - https://www.scopus.com/pages/publications/84919433668

U2 - 10.1109/I3A.2014.20

DO - 10.1109/I3A.2014.20

M3 - Conference contribution

AN - SCOPUS:84919433668

SN - 9781479942527

SP - 41

EP - 44

BT - Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014

PB - IEEE Computer Society

T2 - 13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images

Y2 - 24 August 2014 through 24 August 2014

ER -

HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM

Abstract

Workshop

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Analysis of Colorectal Polyps in Optical Projection Tomography

Cite this

HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM

Abstract

Workshop

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Student theses

Analysis of Colorectal Polyps in Optical Projection Tomography

Cite this