Shape- and Texture-Based Fish Image Recognition System

Thisresearchdevelopedacomputersystemcapableofrecognizingsomefishimages.�The� systemknownasthe�"shape-�andtexture-basedfishimagerecognitionsystem"�(FIRS)�consistsoffive� subsystems—namely: 1) image acquisition, 2) image preprocessing 3) feature extraction, 4) image recognitionand�5)�resultpresentation.�Theexperimentwasconductedon�30�fishspecies,�whichconsisted� of�600�fishimagesasthetrainingdatasetand�300�fishimagesfortesting.�Thesystemcomparedtwo� recognitiontechniques—aEuclideandistancemethod�(EDM)�andartificialneuralnetworks�(ANN).� Thesystemwasabletorecognizeall�30�speciesofthetrainingfishimageswithaprecisionof�99.00� and 81.67% for the ANN and the EDM techniques, respectively. The average access times were 24.4 and 154.43 sec per image for the EDM and ANN techniques, respectively.

[1]  Edward A. Fox,et al.  Superimposed Image Description and Retrieval for Fish Species Identification , 2009, ECDL.

[2]  O. R. Vincent,et al.  A Descriptive Algorithm for Sobel Image Edge Detection , 2009 .

[3]  François Michaud,et al.  Intelligent system for automated fish sorting and counting , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[4]  Mei-Yi Wu,et al.  A tank fish recognition and tracking system using computer vision techniques , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[5]  Ukkrit Satapoomin,et al.  THE FISHES OF SOUTHWESTERN THAILAND, THE ANDAMAN SEA - A REVIEW OF RESEARCH AND A PROVISIONAL CHECKLIST OF SPECIES , 2011 .

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

[7]  F. Beamish,et al.  Total length-weight relationships among Thai freshwater fishes and the influence of capture location and preservation , 2011 .

[8]  Frank Storbeck,et al.  Fish species recognition using computer vision and a neural network , 2001 .

[9]  Itsuo Kumazawa,et al.  "...It's Orange and Small, and White Stripes..." - Augmented-Reality System for Fish Species Identification in Aquariums , 2012, PCM.

[10]  Yongwei Zhang,et al.  A SOA-Based Fish Recognition System Prototype , 2011, 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics.

[11]  Mohamed Cheriet,et al.  AdOtsu: An adaptive and parameterless generalization of Otsu's method for document image binarization , 2012, Pattern Recognit..

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

[13]  M. Nakai,et al.  Proposal of an automatic fish sorting system by intelligent image processing , 2008, 2008 World Automation Congress.

[14]  Dah-Jye Lee,et al.  Contour Matching for Fish Species Recognition and Migration Monitoring , 2008, Applications of Computational Intelligence in Biology.

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