Fully-automated identification of fish species based on otolith contour: using short-time Fourier transform and discriminant analysis (STFT-DA)
A peer-reviewed article of this Preprint also exists.
Author and article information
Abstract
Background. Fish species may be identified based on their unique otolith shape or contour. Several pattern recognition methods have been proposed to classify fish species through morphological features of the otolith contours. However, there has been no fully-automated species identification model with the accuracy higher than 80%. The purpose of the current study is to develop a fully-automated model, based on the otolith contours, to identify the fish species with the high classification accuracy. Methods. Images of the right sagittal otoliths of 14 fish species from three families namely Sciaenidae, Ariidae, and Engraulidae were used to develop the proposed identification model. Short-time Fourier transform (STFT) was used, for the first time in the area of otolith shape analysis, to extract important features of the otolith contours. Discriminant Analysis (DA), as a classification technique, was used to train and test the model based on the extracted features. Results. Performance of the model was demonstrated using species from three families separately, as well as all species combined. Overall classification accuracy of the model was greater than 90% for all cases. In addition, effects of STFT variables on the performance of the identification model were explored in this study. Conclusions. Short-time Fourier transform could determine important features of the otolith outlines. The fully-automated model proposed in this study (STFT-DA) could predict species of an unknown specimen with acceptable identification accuracy. The current model has flexibility to be used for more species and families in future studies.
Cite this as
2015. Fully-automated identification of fish species based on otolith contour: using short-time Fourier transform and discriminant analysis (STFT-DA) PeerJ PrePrints 3:e1517v1 https://doi.org/10.7287/peerj.preprints.1517v1Author comment
This article is currently being peer-reviewed in the journal PeerJ.
Sections
Supplemental Information
MATLAB scripts and function used for training and testing the model
otolith images of Arius maculatus species (Ariidae family) used to train and test the model
otolith images of Cryptarius truncatus species from Ariidae family
otolith images of Hexanematichtys sagor species from Ariidae family
otolith images of Nemapteryx caelata species from Ariidae family
otolith images of Osteogeneiosus militaris species from Ariidae family
otolith images of Plicofollis argyropleuron species from Ariidae family
otolith images of Coilia dussumieri species from Engraulidae family
otolith images of Setipinna taty species from Engraulidae family
otolith images of Thryssa hamiltonii species from Engraulidae family
otolith images of Dendrophysa russelli species from Sciaenidae family
otolith images of Johnius belangerii species from Sciaenidae family
otolith images of Johnius carouna species from Sciaenidae family
otolith images of Otolithes ruber species from Sciaenidae family
otolith images of Panna microdon species from Sciaenidae family
Additional Information
Competing Interests
The authors declare that they have no competing interests.
Author Contributions
Nima Salimi performed the experiments, analyzed the data, contributed reagents/materials/analysis tools, wrote the paper, prepared figures and/or tables.
Kar Hoe Loh performed the experiments, contributed reagents/materials/analysis tools, reviewed drafts of the paper.
Sarinder Kaur Dhillon conceived and designed the experiments, reviewed drafts of the paper.
Ving Ching Chong conceived and designed the experiments, reviewed drafts of the paper.
Animal Ethics
The following information was supplied relating to ethical approvals (i.e., approving body and any reference numbers):
1. University of Malaya-Institutional Animal Care and Use Committee (UM-IACUC). 2. No approval was required since project was based on dead fish collected from fish landings.
Data Deposition
The following information was supplied regarding data availability:
Data sets (Otolith images) as well as MATLAB codes have been submitted.
Funding
This work was supported by University of Malaya Research Grants (UMRG), RP008-2012C and RP008-2012A. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.