활어 개체어의 광대역 음향산란신호에 대한 시간-주파수 이미지의 어파인 변환과 주성분 분석을 이용한 어종식별
Identification of Fish Species using Affine Transformation and Principal Component Analysis of Time–Frequency Images of Broadband Acoustic Echoes from Individual Live Fish
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Joint time–frequency images of the broadband echo signals of six fish species were obtained using the smoothed pseudo-Wigner–Ville distribution in controlled environments. Affine transformation and principal component analysis were used to obtain eigenimages that provided species-specific acoustic features for each of the six fish species. The echo images of an unknown fish species, acquired in real time and in a fully automated fashion, were identified by finding the smallest Euclidean or Mahalanobis distance between each combination of weight matrices of the test image of the fish species to be identified and of the eigenimage classes of each of six fish species in the training set. The experimental results showed that the Mahalanobis classifier performed better than the Euclidean classifier in identifying both single- and mixed-species groups of all species assessed.
Abstract
Joint time–frequency images of the broadband echo signals of six fish species were obtained using the smoothed pseudo-Wigner–Ville distribution in controlled environments. Affine transformation and principal component analysis were used to obtain eigenimages that provided species-specific acoustic features for each of the six fish species. The echo images of an unknown fish species, acquired in real time and in a fully automated fashion, were identified by finding the smallest Euclidean or Mahalanobis distance between each combination of weight matrices of the test image of the fish species to be identified and of the eigenimage classes of each of six fish species in the training set. The experimental results showed that the Mahalanobis classifier performed better than the Euclidean classifier in identifying both single- and mixed-species groups of all species assessed.
참고문헌 (28)
- Abdullah M, "Optimizing face recognition using PCA", Intern J Artific Intellig Applicat, 3, pp.23~31 (2012)
- David Alonso-Caneiro, "Speckle reduction in optical coherence tomography imaging by affine-motion image registration", Journal of Biomedical Optics, 16(11), pp.116027~ (2011), SPIE-Intl Soc Optical Eng[DOI]
- M. Arathi, "Performance of Mahalanobis Distance in Time Series Classification Using Shapelets", International Journal of Machine Learning and Computing, 4(4), pp.339~345 (2014), EJournal Publishing[DOI]
- Bhat FA, "Improved face recognition algorithm using eigen faces", Internat J Advan Res Comp Sci Softw Engin, 3, pp.824~828 (2013)
- Dong Y, "Analysis of a new joint time-frequency distribution of suppressing cross-term", Res J Appl Sci Eng Technol, 4, pp.1580~1584 (2012)
- S. M. M. Fässler, "Depthe-dependent swimbladder compression in herring Clupea haengus observed using magnetic resonance imaging", Journal of Fish Biology, 74(1), pp.296~303 (2009), Wiley[DOI]
- Foote KG, "Importance of the swimbladder in acoustic scattering by fish : A Comparison of gadoid and mackerel target strengths", J Acoust Soc Am, 67, pp.2084~2089 (1980)
- Fuh CS, "Motion displacement estimation using affine model for image matching", Optical Engineering, 30, pp.881~887 (1991)
- Gautam S, "Face recognition using eigen faces and dimensionality reduction by PCA", Internat J Emerg Res Manage Technolo, 2, pp.21~28 (2013)
- Gupta B, "Analyzing face recognition using PCA and comparison between different distance classifier", Internat J Eenin Sci Res Technolo, 2, pp.683~686 (2013)
- J JAFFE, "Using multi-angle scattered sound to size fish swimbladders", ICES Journal of Marine Science, 63(8), pp.1397~1404 (2006), Oxford University Press (OUP)[DOI]
- Latha P, "Face recognition using neural networks", Sign Process Internat J, 3, pp.153~160 (2009)
- 이대재, "펄스압축기법을 이용한 활어 개체어에 대한 광대역 음향산란신호의 분석 및 식별", 한국수산과학회지, 48(2), pp.207~220 (2015), 한국수산과학회
- 이대재, "고등어( Scomber japonicus ), 불볼락( Sebastes thompsoni ) 및 쥐노래미( Hexagrammos otakii )에 의한 광대역 음향산란신호의 시간-주파수 분석", 한국수산과학회지, 48(2), pp.221~232 (2015), 한국수산과학회
- 이대재, "어류 부레의 형태학적 차이에 따른 음향산란강도의 자세 및 주파수 의존성의 변화", 한국수산과학회지, 48(2), pp.233~243 (2015), 한국수산과학회
- 이대재, "활어 개체어의 광대역 음향산란신호로부터 어종식별을 위한 시간-주파수 특징 추출", 한국수산과학회지, 49(2), pp.214~223 (2016), 한국수산과학회
- 이대재, "인공 신경망에 의한 6개 어종의 음향학적 식별", 한국수산과학회지, 49(2), pp.224~233 (2016), 한국수산과학회
- Nesse TL, "Measurement of acoustic-scattering spectra from the whole and pars of Atlantic mackerel", ICES J Mar Sci, 66, pp.1169~1175 (2009)[DOI]
- Prasad MSRS, "Face recognition using PCA and feed forward neural networks", Internat J Electron Communicat Technol, 2, pp.79~82 (2011)
- Priscilla CV, "Image registration and noise detection using affine transformation", Internat J Comput Technolo Applicat, 4, pp.209~216 (2013)
- Rihaczek AW, "Signal energy distribution in time and frequency", IEEE Trans Inform Theory, IT-14, pp.369~374 (1968)
- Rizon M, "Face recognition using eigenfaces and neural networks. Ameri J", Appl Sci, 2, pp.1872~1875 (2006)
- Semmlow JL, "Biosignal and Biomedical Image Processing:Matlab-Based Applications", pp.320~327 (2004), Marcel Dekker Inc
- Shui PL, "Instantaneous frequency estimation based on directionally smoothed pseudo-Wegner-Ville distribution bank", IET Radar Sonar Navig, 1, pp.317~325 (2007)[DOI]
- Sijbers J, "Quantification and improvement of the signal-tonoise ratio in a magnetic resonance image acquisition procedure", Magn Reson Imaging, 14, pp.1157~1163 (1996)
- Singla J, "A systematic way of affine transformation using image registration", Internat J Infomat Technolo Knowledge Managm, 5, pp.239~243 (2012)
- Slavkovic M, "Face recognition using eigenface approach", Serbian J Electri Engin, 9, pp.121~130 (2012)
- Stanton TK, "New broadband methods for resonance classification and high-resolution imagery of fish with swimbladders using a modified commercial broadband echosounder", ICES J Mar Sci, 67, pp.365~378 (2010)[DOI]