Underwater Live Fish Recognition Using a Balance-Guaranteed Optimized Tree

Live fish recognition in the open sea is a challenging multi-class classification task. We propose a novel method to recognize fish in an unrestricted natural environment recorded by underwater cameras. This method extracts 66 types of features, which are a combination of color, shape and texture properties from different parts of the fish and reduce the feature dimensions with forward sequential feature selection (FSFS) procedure. The selected features of the FSFS are used by an SVM. We present a Balance-Guaranteed Optimized Tree (BGOT) to control the error accumulation in hierarchical classification and, therefore, achieve better performance. A BGOT of 10 fish species is automatically constructed using the inter-class similarities and a heuristic method. The proposed BGOT-based hierarchical classification method achieves about 4% better accuracy compared to state-of-the-art techniques on a live fish image dataset.

[1]  Fei-Fei Li,et al.  What Does Classifying More Than 10, 000 Image Categories Tell Us? , 2010, ECCV.

[2]  Farzin Mokhtarian,et al.  Robust Image Corner Detection Through Curvature Scale Space , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[4]  A. D. Gordon.  A Review of Hierarchical Classification , 1987 .

[5]  B. K. Liew,et al.  Automated Fish Counting Using Image Processing , 2009, 2009 International Conference on Computational Intelligence and Software Engineering.

[6]  Robert B. Fisher,et al.  Automatic fish classification for underwater species behavior understanding , 2010, ARTEMIS '10.

[7]  Boaz Zion,et al.  In-vivo fish sorting by computer vision , 2000 .

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  M. Okamoto,et al.  Fundamental study to estimate fish biomass around coral reef using 3-dimensional underwater video system , 2000, OCEANS 2000 MTS/IEEE Conference and Exhibition. Conference Proceedings (Cat. No.00CH37158).

[10]  N. J. C. Strachan,et al.  Recognition of fish species by colour and shape , 1993, Image Vis. Comput..

[11]  J. A. Marchant,et al.  Fish sizing and monitoring using a stereo image analysis system applied to fish farming , 1995 .

[12]  Alex A. Freitas,et al.  A survey of hierarchical classification across different application domains , 2010, Data Mining and Knowledge Discovery.

[13]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Alastair R. Allen,et al.  Fish species recognition by shape analysis of images , 1990, Pattern Recognit..

[15]  Robert B. Fisher,et al.  A flexible system for automated composition of intelligent video analysis , 2011, 2011 7th International Symposium on Image and Signal Processing and Analysis (ISPA).

[16]  Thomas M. Breuel,et al.  Classification using a hierarchical Bayesian approach , 2002, Object recognition supported by user interaction for service robots.

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

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

[19]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[20]  Norval J. C. Strachan,et al.  Length measurement of fish by computer vision , 1993 .

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

[22]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[23]  Nelson H. C. Yung,et al.  Curvature scale space corner detector with adaptive threshold and dynamic region of support , 2004, ICPR 2004.