Authors:
James Mapp
1
;
Mark Fisher
1
;
Anthony Bagnall
1
;
Jason Lines
1
;
Sally Warne
2
and
Joe Scutt Phillips
2
Affiliations:
1
University of East Anglia, United Kingdom
;
2
CEFAS Laboratory, United Kingdom
Keyword(s):
CSS, Curvature, Scale-space, Shapelets, Otolith, Intraspecies, Classification, Random-forrest, Imageprocessing, LOOCV, Cross-validation.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Feature Selection and Extraction
;
Object Recognition
;
Pattern Recognition
;
Shape Representation
;
Software Engineering
;
Theory and Methods
Abstract:
We present a study comparing Curvature Scale Space (CSS) representation with Shapelet transformed data with a view to discriminating between sagittal otoliths of North-Sea and Thames Herring using otolith boundary and boundary metrics. CSS transformed boundaries combined with measures of their circularity, eccentricity and aspect-ratio are used to classify using nearest-neighbour selections with distance being computed using CSS matching methods. Shapelet transformed data are classified using a number of techniques (Nearest-Neighbour, Naive-Bayes, C4.5, Support Vector Machines, Random and Rotation Forest) and compared to CSS classification results. Both methods use Leave One Out Cross Validation (LOOCV). We describe the method of encoding and the matching algorithm used during CSS classification and give an overview of Shapelet transforms and the classifiers that are used on the data. It is shown that whilst CSS forms part of the MPEG-7 standard and performs better than random select
ion, it can be significantly out-performed by recent additions to machine-learning methods in this application. Shapelets also show that with regard to intra-species distinction, the discriminatory features of otolith boundaries may lie not in the major inflection points, but the boundary points between them.
(More)