Estimating Mass of Harvested Asian Seabass Lates calcarifer from Images

Total of 1072 Asian seabass or barramundi (Lates calcarifer) were harvested at two different locations in Queensland, Australia. Each fish was digitally photographed and weighed. A subsample of 200 images (100 from each location) were manually segmented to extract the fish-body area (S in cm2), excluding all fins. After scaling the segmented images to 1mm per pixel, the fish mass values (M in grams) were fitted by a single-factor model (M=aS1.5, a=0.1695 )achieving the coefficient of determination (R2) and the Mean Absolute Relative Error (MARE) of R2=0.9819 and MARE=5.1%, respectively. A segmentation Convolutional Neural Network (CNN) was trained on the 200 hand-segmented images, and then applied to the rest of the available images. The CNN predicted fish-body areas were used to fit the mass-area estimation models: the single-factor model, M=aS1.5, a=0.170, R2=0.9819, MARE=5.1%; and the two-factor model, M= aSb, a=0.124, b=0.155, R2=0.9834, MARE=4.5%.

[1]  Dmitry A. Konovalov,et al.  Individual Minke Whale Recognition Using Deep Learning Convolutional Neural Networks , 2018 .

[2]  D. Brady,et al.  Landing strips: Model development for estimating body surface area of farmed Atlantic salmon ( Salmo salar ) , 2017 .

[3]  D. Jerry,et al.  Fate of genetic diversity within and between generations and implications for DNA parentage analysis in selective breeding of mass spawners: A case study of commercially farmed barramundi, Lates calcarifer , 2014 .

[4]  Yvan Vander Heyden,et al.  Robust Cross-Validation of Linear Regression QSAR Models , 2008, J. Chem. Inf. Model..

[5]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[6]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[7]  Boaz Zion,et al.  Sorting fish by computer vision , 1999 .

[8]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[9]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  R. D. White,et al.  Automatic Scaling of Fish Images , 2018, ICAIP '18.

[12]  Bahar Gümüş,et al.  Prediction of the weight of Alaskan pollock using image analysis. , 2010, Journal of food science.

[13]  J. Holm,et al.  Distribution and structure of the population of sea lice, Lepeophtheirus salmonis Krøyer, on Atlantic salmon, Salmo salar L., under typical rearing conditions , 1992 .

[14]  Boaz Zion,et al.  Review: The use of computer vision technologies in aquaculture - A review , 2012 .

[15]  D. A. Konovalov,et al.  Ruler Detection for Automatic Scaling of Fish Images , 2017 .

[16]  K. Zenger,et al.  The next wave in selective breeding: implementing genomic selection in aquaculture , 2017 .

[17]  Ivan Laptev,et al.  Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  J. Huxley.  Constant Differential Growth-Ratios and their Significance , 1924, Nature.

[19]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[20]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[21]  Daniel Berckmans,et al.  Automatic mass estimation of Jade perch Scortum barcoo by computer vision , 2015 .