Application of statistical learning theory to plankton image analysis


a service of the MBLWHOI Library | About WHOAS

Show simple item record

dc.contributor.author Hu, Qiao
dc.date.accessioned 2006-09-22T18:12:46Z
dc.date.available 2006-09-22T18:12:46Z
dc.date.issued 2006-06
dc.identifier.uri http://hdl.handle.net/1912/1237
dc.description Submitted to the Joint Program in Applied Ocean Science and Engineering in partial fulfillment of the requirements for the degree of Doctor of Philosophy At the Massachusetts Institute of Technology and the Woods Hole Oceanographic Institution June 2006 en
dc.description.abstract A fundamental problem in limnology and oceanography is the inability to quickly identify and map distributions of plankton. This thesis addresses the problem by applying statistical machine learning to video images collected by an optical sampler, the Video Plankton Recorder (VPR). The research is focused on development of a real-time automatic plankton recognition system to estimate plankton abundance. The system includes four major components: pattern representation/feature measurement, feature extraction/selection, classification, and abundance estimation. After an extensive study on a traditional learning vector quantization (LVQ) neural network (NN) classifier built on shape-based features and different pattern representation methods, I developed a classification system combined multi-scale cooccurrence matrices feature with support vector machine classifier. This new method outperforms the traditional shape-based-NN classifier method by 12% in classification accuracy. Subsequent plankton abundance estimates are improved in the regions of low relative abundance by more than 50%. Both the NN and SVM classifiers have no rejection metrics. In this thesis, two rejection metrics were developed. One was based on the Euclidean distance in the feature space for NN classifier. The other used dual classifier (NN and SVM) voting as output. Using the dual-classification method alone yields almost as good abundance estimation as human labeling on a test-bed of real world data. However, the distance rejection metric for NN classifier might be more useful when the training samples are not “good” ie, representative of the field data. In summary, this thesis advances the current state-of-the-art plankton recognition system by demonstrating multi-scale texture-based features are more suitable for classifying field-collected images. The system was verified on a very large realworld dataset in systematic way for the first time. The accomplishments include developing a multi-scale occurrence matrices and support vector machine system, a dual-classification system, automatic correction in abundance estimation, and ability to get accurate abundance estimation from real-time automatic classification. The methods developed are generic and are likely to work on range of other image classification applications. en
dc.description.sponsorship This work was supported by National Science Foundation Grants OCE-9820099 and Woods Hole Oceanographic Institution academic program.
dc.format.extent 5847417 bytes
dc.format.mimetype application/pdf
dc.language.iso en_US en
dc.publisher Massachusetts Institute of Technology and Woods Hole Oceanographic Institution en
dc.relation.ispartofseries WHOI Theses en
dc.subject Plankton en_US
dc.subject Measurement en_US
dc.subject Machine learning en_US
dc.title Application of statistical learning theory to plankton image analysis en
dc.type Thesis en
dc.identifier.doi 10.1575/1912/1237

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search WHOAS


My Account