Recognizing plankton images from the shadow image particle profiling evaluation recorder

We present a system to recognize underwater plankton images from the shadow image particle profiling evaluation recorder (SIPPER). The challenge of the SIPPER image set is that many images do not have clear contours. To address that, shape features that do not heavily depend on contour information w...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on cybernetics 2004-08, Vol.34 (4), p.1753-1762
Main Authors: Tong Luo, Kramer, K., Goldgof, D.B., Hall, L.O., Samson, S., Remsen, A., Hopkins, T.
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial Intelligence
Data mining
Decision trees
Digital cameras
Environmental Monitoring - methods
Image Enhancement - methods
Image Interpretation, Computer-Assisted - methods
Image recognition
Information Storage and Retrieval - methods
Marine vegetation
Neural networks
Particle Size
Pattern Recognition, Automated
Photography - methods
Plankton - classification
Plankton - cytology
Probability
Reproducibility of Results
Sensitivity and Specificity
Shape
Studies
Support vector machine classification
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a system to recognize underwater plankton images from the shadow image particle profiling evaluation recorder (SIPPER). The challenge of the SIPPER image set is that many images do not have clear contours. To address that, shape features that do not heavily depend on contour information were developed. A soft margin support vector machine (SVM) was used as the classifier. We developed a way to assign probability after multiclass SVM classification. Our approach achieved approximately 90% accuracy on a collection of plankton images. On another larger image set containing manually unidentifiable particles, it also provided 75.6% overall accuracy. The proposed approach was statistically significantly more accurate on the two data sets than a C4.5 decision tree and a cascade correlation neural network. The single SVM significantly outperformed ensembles of decision trees created by bagging and random forests on the smaller data set and was slightly better on the other data set. The 15-feature subset produced by our feature selection approach provided slightly better accuracy than using all 29 features. Our probability model gave us a reasonable rejection curve on the larger data set.
ISSN:1083-4419
2168-2267
1941-0492
2168-2275
DOI:10.1109/TSMCB.2004.830340