Fisher, Bob

Williams, Chris

Huang, Xuan

Huang, Phoenix X.

Fish4Knowledge project

2014-12-04T14:26:50Z

2014-12-04T14:26:50Z

2014-11-27

This thesis investigates the computer vision application of live fish recognition, which is needed in application scenarios where manual annotation is too expensive, when there are too many underwater videos. This system can assist ecological surveillance research, e.g. computing fish population statistics in the open sea. Some pre-processing procedures are employed to improve the recognition accuracy, and then 69 types of features are extracted. These features are a combination of colour, shape and texture properties in different parts of the fish such as tail/head/top/bottom, as well as the whole fish. Then, we present a novel Balance-Guaranteed Optimized Tree with Reject option (BGOTR) for live fish recognition. It improves the normal hierarchical method by arranging more accurate classifications at a higher level and keeping the hierarchical tree balanced. BGOTR is automatically constructed based on inter-class similarities. We apply a Gaussian Mixture Model (GMM) and Bayes rule as a reject option after the hierarchical classification to evaluate the posterior probability of being a certain species to filter less confident decisions. This novel classification-rejection method cleans up decisions and rejects unknown classes. After constructing the tree architecture, a novel trajectory voting method is used to eliminate accumulated errors during hierarchical classification and, therefore, achieves better performance. The proposed BGOTR-based hierarchical classification method is applied to recognize the 15 major species of 24150 manually labelled fish images and to detect new species in an unrestricted natural environment recorded by underwater cameras in south Taiwan sea. It achieves significant improvements compared to the state-of-the-art techniques. Furthermore, the sequence of feature selection and constructing a multi-class SVM is investigated. We propose that an Individual Feature Selection (IFS) procedure can be directly exploited to the binary One-versus-One SVMs before assembling the full multiclass SVM. The IFS method selects different subsets of features for each Oneversus- One SVM inside the multiclass classifier so that each vote is optimized to discriminate the two specific classes. The proposed IFS method is tested on four different datasets comparing the performance and time cost. Experimental results demonstrate significant improvements compared to the normal Multiclass Feature Selection (MFS) method on all datasets.

http://hdl.handle.net/1842/9779

en

The University of Edinburgh

P. X. Huang, B. J. Boom, R. B. Fisher, “Underwater Live Fish Recognition using a Balance-Guaranteed Optimized Tree”, ACCV 2012. 422-433. http://homepages.inf.ed.ac.uk/rbf/PAPERS/accv2012finalpaper.pdf

P. X. Huang, B. J. Boom, R. B. Fisher, “Hierarchical Classification for Live Fish Recognition”, BMVC student workshop, September 2012. http://www.bmva.org/bmvc/2012/WS/paper1.pdf

P. X. Huang, B. J. Boom, R. B. Fisher, “GMM improves the reject option in hierarchical classification for fish recognition”, WACV 2014, http://homepages.inf.ed.ac.uk/s1064211/thesis/egpaper.pdf

P. X. Huang, B. J. Boom, R. B. Fisher, “Hierarchical classification with reject option for live fish recognition”, submitted to Machine Vision and Application, 2014. http://homepages.inf.ed.ac.uk/s1064211/thesis/fishRecognition.pdf

P. X. Huang, R. B. Fisher, “Individual feature selection in each One-versus-One classifier improves multi-class SVM performance”, PRL, 2014. http://homepages.inf.ed.ac.uk/s1064211/thesis/icpr14.pdf

B. J. Boom, P. X. Huang, J. He, R. B. Fisher, “Supporting Ground-Truth annotation of image datasets using clustering”, 21st Int. Conf. on Pattern Recognition (ICPR), 2012. http://homepages.inf.ed.ac.uk/rbf/PAPERS/PID2432553.pdf

Balance-Guaranteed Optimized Tree with Reject

BGOTR

live fish recognition

hierarchical classification

reject option

Gaussian Mixture Model

GMM

Balance-guaranteed optimized tree with reject option for live fish recognition

Thesis or Dissertation

Doctoral

PhD Doctor of Philosophy