Fish Classification Using Support Vector Machine

Fish recognition is presently a very complex and difficult task despite its commercial and agricultural usefulness. Some of the challenges facing accurate and reliable fish recognition include distortion, noise, segmentation error, overlap and occlusion. Several techniques, which include K-Nearest Neighbor (KNN), K-mean Clustering and Neural Network, have been widely used to resolve these challenges. Each of these approaches has inherent limitations, which limit classification accuracy. In this paper, a Support Vector Machine (SVM)-based technique for the elimination of the limitations of some existing techniques and improved classification of fish species is proposed. The technique is based on the shape features of fish that was divided into two subsets with the first comprising 76 fish as training set while the second comprises of 74 fish as testing set. The body and the five fin lengths; namely anal, caudal, dorsal, pelvic and pectoral were extracted in centimeter (cm). Results based on the new technique show a classification accuracy of 78.59%, which is significantly higher than what obtained for ANN, KNN and K-mean clustering-based algorithms.

[1]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[2]  Ariel G. Cabreira,et al.  Artificial neural networks for fish-species identification , 2009 .

[3]  Rasmus Larsen,et al.  Shape and Texture Based Classification of Fish Species , 2009, SCIA.

[4]  Sergio Bermejo,et al.  Fish age classification based on length, weight, sex and otolith morphological features , 2007 .

[5]  M. Barangé,et al.  Species identification of pelagic fish schools on the South African continental shelf using acoustic descriptors and ancillary information , 2001 .

[6]  Jake K. Aggarwal,et al.  Supervised parametric and non-parametric classification of chromosome images , 2005, Pattern Recognit..

[7]  R. Kastner,et al.  Automated Techniques for Detection and Recognition of Fishes using Computer Vision Algorithms , 2012 .

[8]  Peter L. M. Goethals,et al.  Application of classification trees and support vector machines to model the presence of macroinvertebrates in rivers in Vietnam , 2010, Ecol. Informatics.

[9]  Shahrul Azman Mohd Noah,et al.  Fish recognition based on robust features extraction from color texture measurements using back-propagation classifier , 2010 .

[10]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Shahrul Azman Mohd Noah,et al.  Fish Recognition Based on Robust Features Extraction from Size and Shape Measurements Using Neural Network , 2010 .

[12]  Sarah Jane Delany.  k-Nearest Neighbour Classifiers , 2007 .

[13]  Dah-Jye Lee,et al.  Contour matching for a fish recognition and migration-monitoring system , 2004, SPIE Optics East.

[14]  Phoenix X. Huang,et al.  Balance-guaranteed optimized tree with reject option for live fish recognition , 2014 .

[15]  Jan Tore Øvredal,et al.  Automatic species recognition, length measurement and weight determination, using the CatchMeter computer vision system , 2006 .

[16]  Shahrul Azman Mohd. Noah,et al.  Fish recognition based on the combination between robust feature selection, image segmentation and geometrical parameter techniques using Artificial Neural Network and Decision Tree , 2009, ArXiv.

[17]  Inmaculada Pulido-Calvo,et al.  Acoustic identification of small pelagic fish species in Chile using support vector machines and neural networks , 2010 .

[18]  Soumya.D.S Arya.V,et al.  Chromosome Segmentation Using K-Means Clustering , 2013 .

[19]  Jung Uk Cho,et al.  Field Programmable Gate Array (FPGA) Based Fish Detection Using Haar Classifiers , 2009 .

[20]  Phoenix X. Huang,et al.  Hierarchical Classification for Live Fish Recognition , 2012 .

[21]  Andrew Rova,et al.  One Fish, Two Fish, Butterfish, Trumpeter: Recognizing Fish in Underwater Video , 2007, MVA.

[22]  Flávio L. C. Pádua,et al.  Automatic fish species classification based on robust feature extraction techniques and artificial immune systems , 2010, 2010 IEEE Fifth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA).

[23]  Rosalina Abdul Salam,et al.  Adaptation of K-Means Algorithm for Image Segmentation , 2009 .