D. A. Konovalov
ABSTRACT
In aquaculture breeding programs where large numbers of fish need to be rapidly phenotyped, the absolute physical dimensions of fish (in millimeters or inches) are often required to be extracted from electronic images in order to measure the size of the fish. While it is possible to infer the length of the fish in pixels, the absolute scale of the image (in pixels-per-millimeter or dots-per-inch) is largely unknown without a reference grid, or requires additional hardware, data collection and/or record-keeping management overheads. One cost and time effective solution is to capture the absolute scale by including a measuring ruler in the photographed scene and from which a computer program can automatically identify the scale of the photo and calculate fish morphometric measurements. To assist such workflow, this study developed an algorithm that automatically detects a ruler in a given image, and automatically extracts its scale as distance (in fractional number of pixels) between the ruler's graduation marks. The algorithm was applied to 445 publicly available images of barramundi or Asian seabass (Lates calcarifer), where a millimeter-graded ruler was included in each image. Convolutional Neural Network (CNN) was trained to segment the images into ruler, background, fish and label sections. Then the distance-extraction algorithm was applied to the ruler section of the images. The false-negative rate was less than 2%, where the ruler graduation distances could not be extracted in only 2-6 (out of 445) images even when the test images were rotated up to 90 degrees. The mean absolute relative error (MARE) of the inferred distances was 1-2%.
- Hong, H., Yang, X., You, Z., Cheng, F. 2014. Visual quality detection of aquatic products using machine vision. Aquacult. Eng. 63, 62--71.Google Scholar
Cross Ref
- Miranda, J.M., Romero, M. 2017. A prototype to measure rainbow trout's length using image processing. Aquacult. Eng. 76, 41--49.Google ScholarCross Ref
- Zion, B. 2012. The use of computer vision technologies in aquaculture a review. Comput. Electron. Agr. 88, 125--132. Google ScholarDigital Library
- Zion, B., Shklyar, A., Karplus, I. 2000. In-vivo fish sorting by computer vision. Aquacult. Eng. 22, 165--179.Google ScholarCross Ref
- Saberioon, M., Gholizadeh, A., Cisar, P., Pautsina, A., Urban, J. 2016. Application of machine vision systems in aquaculture with emphasis on fish: state-of-the-art and key issues. Rev. Aquacult. 9, 369--387.Google ScholarCross Ref
- Costa, C., Antonucci, F., Boglione, C., Menesatti, P., Vandeputte, M., Chatain, B. 2013. Automated sorting for size, sex and skeletal anomalies of cultured seabass using external shape analysis. Aquacult. Eng. 52, 58--64.Google ScholarCross Ref
- Viazzi, S., Van Hoestenberghe, S., Goddeeris, B.M., Berckmans, D. 2015. Automatic mass estimation of jade perch scortum barcoo by computer vision. Aquacult. Eng. 64, 42--48.Google ScholarCross Ref
- Cobb, J.N., DeClerck, G., Greenberg, A., Clark, R., McCouch, S. 2013. Next-generation phenotyping: requirements and strategies for enhancing our understanding of genotype-phenotype relationships and its relevance to crop improvement. Theor. Appl. Genet. 126, 867--887.Google ScholarCross Ref
- Ueda, K., Baba, T., Nakagawa, Y., Amano, K. 2005. Detection of scale intervals in digital images. In 21st International Conference on Data Engineering Workshops (ICDEW'05). 1232--1232. Google ScholarDigital Library
- Zambanini, S., Herrmann, M., Kampel, M. 2013. An Automatic Method to Determine the Diameter of Historical Coins in Images. Scientific Computing and Cultural Heritage. Contributions in Mathematical and Computational Sciences. 3. Springer, Berlin, Heidelberg. 99--106.Google Scholar
- Bhalerao, A., Reynolds, G. 2014. Ruler detection for autoscaling forensic images. Int. J. Digit. Crime For. 6, 9--27. Google ScholarDigital Library
- Konovalov, D.A., Domingos, J.A., Bajema, C., White, R.D., Jerry, D.R. 2017. Ruler detection for automatic scaling of fish images, In Proceedings of the International Conference on Advances in Image Processing (Bangkok, Thailand). ACM, New York, NY, 90--95. Google ScholarDigital Library
- LeCun, Y., Bengio, Y., Hinton, G. 2015. Deep learning. Nature 521, 436--444.Google ScholarCross Ref
- Shelhamer, E., Long, J., Darrell, T. 2016. Fully Convolutional Models for Semantic Segmentation. PAMI 2016. https://arxiv.org/abs/1411.4038.Google Scholar
- Long, J., Shelhamer, E., Darrell, T. 2015. Fully Convolutional Models for Semantic Segmentation. CVPR 2015. https://arxiv.org/abs/1411.4038v2.Google Scholar
- Ronneberger, O., Fischer, P., Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015. Lecture Notes in Computer Science, 9351. Springer, Cham, 234--241.Google Scholar
- Simonyan, K., Zisserman, A. 2014. Very deep convolutional networks for large-scale image recognition. CoRR. https://arxiv.org/abs/1409.1556.Google Scholar
- Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L. 2009. ImageNet: A Large-Scale Hierarchical Image Database, In IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, 248--255.Google ScholarCross Ref
- Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bern- stein, M., Berg, A.C., Fei-Fei, L. 2015. ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. 115, 211--252. Google ScholarDigital Library
- Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T. 2014. Caffe: Convolutional architecture for fast feature embedding. In Proceedings of the 22Nd ACM International Conference on Multimedia (Orlando, Florida, USA) ACM, New York, NY. 675--678. Google ScholarDigital Library
- Chollet, F., et al. 2015. Keras. https://github.com/fchollet/keras.Google Scholar
- Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X. 2015. TensorFlow: Large- scale machine learning on heterogeneous systems. http://tensorflow.org.Google Scholar
- Glorot, X., Bengio, Y. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (Sardinia, Italy). PMLR 9, 249--256. http://proceedings.mlr.press/v9/glorot10a.html.Google Scholar
- Badrinarayanan, V., Kendall, A., Cipolla, R. 2017. Segnet: A deep convolutional encoder-decoder architecture for scene segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 39, 2481--2495.Google ScholarCross Ref
- Zuiderveld, K. 1994. Contrast Limited Adaptive Histogram Equalization. Graphics Gems IV. Academic Press Professional Inc., San Diego, CA. 474--485. Google ScholarDigital Library
- Kingma, D.P., Ba, J. 2015. Adam: A method for stochastic optimization. In 3rd International Conference for Learning Representations, San Diego, http://arxiv.org/abs/1412.6980.Google Scholar
- Schneider, C.A., Rasband, W.S., Eliceiri, K.W. 2012. NIH Image to Imagej: 25 years of image analysis. Nat. Meth. 9, 671--675.Google ScholarCross Ref
- Fawcett, T. 2006. An introduction to ROC analysis. Pattern Recog. Lett. 27, 861--874. Google ScholarDigital Library
Index Terms
- Automatic Scaling of Fish Images
Recommendations
Ruler Detection for Automatic Scaling of Fish Images
ICAIP '17: Proceedings of the International Conference on Advances in Image ProcessingFast and low-cost image collection and processing is often required in aquaculture farms for quality/size attributes and breeding programs. For example, the absolute physical dimensions of fish (in millimeters or inches) could be estimated from ...
Computer vision and robotics techniques in fish farms
This paper presents new low-cost systems for the automation of some fish farm operations. Particularly, computer vision is applied to non-contact fish weight estimation. Stereo vision systems with synchronised convergent cameras are employed to perform ...
Ruler Detection for Autoscaling Forensic Images
The assessment of forensic photographs often requires the calibration of the resolution of the image so that accurate measurements can be taken of crime-scene exhibits or latent marks. In the case of latent marks, such as fingerprints, image calibration ...
Comments