Communications for Statistical Applications and Methods

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of algae in watersheds using elastic shape

  • Tae-Young Heo (Department of Information Statistics, Chungbuk National University) ;
  • Jaehoon Kim (Department of Information Statistics, Chungbuk National University) ;
  • Min Ho Cho (Department of Statistics, Inha University)
  • Received : 2023.08.29
  • Accepted : 2023.12.24
  • Published : 2024.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Identifying algae in water is important for managing algal blooms which have great impact on drinking water supply systems. There have been various microscopic approaches developed for algae classification. Many of them are based on the morphological features of algae. However, there have seldom been mathematical frameworks for comparing the shape of algae, represented as a planar continuous curve obtained from an image. In this work, we describe a recent framework for computing shape distance between two different algae based on the elastic metric and a novel functional representation called the square root velocity function (SRVF). We further introduce statistical procedures for multiple shapes of algae including computing the sample mean, the sample covariance, and performing the principal component analysis (PCA). Based on the shape distance, we classify six algal species in watersheds experiencing algal blooms, including three cyanobacteria (Microcystis, Oscillatoria, and Anabaena), two diatoms (Fragilaria and Synedra), and one green algae (Pediastrum). We provide and compare the classification performance of various distance-based and model-based methods. We additionally compare elastic shape distance to non-elastic distance using the nearest neighbor classifiers.

Keywords

Acknowledgement

This study was supported by K-water (Korea Water Resources Corportion). This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (RS-2022-00167077) and a INHA UNIVERSITY Research Grant.

References

  1. Besl PJ and McKay ND (1992). Method for registration of 3-D shapes, Sensor Fusion IV: Control Paradigms and Data Structures, 1611, 586-607.  https://doi.org/10.1117/12.57955
  2. Cho MH, Kurtek S, and MacEachern SN (2021). Aggregated pairwise classification of elastic planar shapes, The Annals of Applied Statistics, 15, 619-637. 
  3. Coltelli P, Barsanti L, Evangelista V, Frassanito AM, and Gualtieri P (2014). Water monitoring: Automated and real time identification and classification of algae using digital microscopy, Environmental Science: Processes & Impacts, 16, 2656-2665.  https://doi.org/10.1039/C4EM00451E
  4. Dauta A, Devaux J, Piquemal F, and Boumnich L (1990). Growth rate of four freshwater algae in relation to light and temperature, Hydrobiologia, 207, 221-226.  https://doi.org/10.1007/BF00041459
  5. Dryden IL and Mardia KV (2016). Statistical Shape Analysis: With Applications in R, Wiley.
  6. Grenander U and Miller MI (1998). Computational anatomy: An emerging discipline, Quarterly of Applied Mathematics, LVI, 617-694.  https://doi.org/10.1090/qam/1668732
  7. Joshi SH, Klassen E, Srivastava A, and Jermyn IH (2007). A novel representation for Riemannian analysis of elastic curves in ℝn. In Proceedings of 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, 1-7. 
  8. Kendall DG (1984). Shape manifolds, procrustean metrics, and complex projective spaces, Bulletin of the London Mathematical Society, 16, 81-121.  https://doi.org/10.1112/blms/16.2.81
  9. Kurtek S, Srivastava A, Klassen E, and Ding Z (2012). Statistical modeling of curves using shapes and related features, Journal of the American Statistical Association, 107, 1152-1165.  https://doi.org/10.1080/01621459.2012.699770
  10. Kurtek S, Su J, Grimm C, Vaughan M, Sowell R, and A Srivastava (2013). Statistical analysis of manual segmentations of structures in medical images, Computer Vision and Image Understanding, 117, 1036-1050.  https://doi.org/10.1016/j.cviu.2012.11.014
  11. Malladi R, Sethian JA, and Vemuri BC (1996). A fast level set based algorithm for topology-independent shape modeling, Journal of Mathematical Imaging and Vision, 6, 269-290.  https://doi.org/10.1007/BF00119843
  12. Medina E, Petraglia MR, Gomes JGR, and Petraglia A (2017). Comparison of cnn and mlp classifiers for algae detection in underwater pipelines. In Proceedings of 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), Montreal, QC, 1-6. 
  13. Michor PW and Mumford D (2006). Riemannian geometries on spaces of plane curves, Journal of European Mathematical Society, 8, 1-48. 
  14. Mio W, Srivastava A, and Joshi SH (2007). On shape of plane elastic curves, International Journal of Computer Vision, 73, 307-324.  https://doi.org/10.1007/s11263-006-9968-0
  15. Paerl HW and Otten TG (2013). Harmful cyanobacterial blooms: Causes, consequences, and controls, Microbial Ecology, 65, 995-1010.  https://doi.org/10.1007/s00248-012-0159-y
  16. Pal S, Woods RP, Panjiyar S, Sowell ER, Narr KL, and Joshi SH (2017). A Riemannian framework for linear and quadratic discriminant analysis on the tangent space of shapes, In Proceedings of Workshop on Differential Geometry in Computer Vision and Machine Learning, Honolulu, HI, 726-734. 
  17. Park J, Lee H, Park CY, Hasan S, Heo T-Y, and Lee WH (2019). Algal morphological identification in watersheds for drinking water supply using neural architecture search for convolutional neural network, Water, 11, 1338, 1-19. 
  18. Pizer SM, Jung S, Goswami D et al. (2013). Nested sphere statistics of skeletal models, In Innovations for Shape Analysis: Models and Algorithms, 93-115. 
  19. Robinson DT (2012). Functional data analysis and partial shape matching in the square root velocity framework (Ph.D thesis), Florida State University, Tallahassee, FL. 
  20. Srivastava A, Jermyn IH, and Joshi S (2007). Riemannian analysis of probability density functions with applications in vision, In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, 1-8. 
  21. Srivastava A, Klassen E, Joshi SH, and Jermyn IH (2011). Shape analysis of elastic curves in Euclidean spaces, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 1415-1428.  https://doi.org/10.1109/TPAMI.2010.184
  22. Srivastava A and Klassen EP (2016). Functional and Shape Data Analysis, Springer, New York. 
  23. Weinberger KQ and Saul LK (2009). Distance metric learning for large margin nearest neighbor classification, Journal of Machine Learning Research, 10, 207-244.