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%.
|Title of host publication||Proceedings - 2014 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images. I3A Workshop 2014|
|Publisher||IEEE Computer Society|
|Number of pages||4|
|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
|Workshop||13A: 1st Workshop on Pattern Recognition Techniques for Indirect Immunofluorescence Images|
|Period||24/08/14 → 24/08/14|
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
FingerprintDive into the research topics of 'HEp-2 Specimen Classification Using Multi-resolution Local Patterns and SVM'. Together they form a unique fingerprint.
Analysis of Colorectal Polyps in Optical Projection TomographyAuthor: Li, W., 2015
Supervisor: Zhang, J. (Supervisor) & McKenna, S. (Supervisor)
Student thesis: Doctoral Thesis › Doctor of PhilosophyFile