Classification of Microscopic Algae: An Observational Study with AlexNet

Classification of algae is one of challenging task due to its micro-size and similarity in shapes. Therefore, the manual taxonomic classification of algae is very difficult and needs high-level expertise. In this case, it becomes error prone and tidy task for biologist. In this paper, we presented high end, fast, accurate and efficient system based on image processing and machine learning algorithms for classification of microscopic algae. We have applied convolutional neural networks by using AlexNet architecture on publicly available dataset of microscopic algae. We have achieved the encouraging results with very small training dataset, while using the deep learning.

[1]  Gabriel Cristóbal,et al.  Automated Diatom Classification (Part A): Handcrafted Feature Approaches , 2017 .

[2]  Primo Coltelli,et al.  Water monitoring: automated and real time identification and classification of algae using digital microscopy. , 2014, Environmental science. Processes & impacts.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Michael H. F. Wilkinson,et al.  Automatic diatom identification using contour analysis by morphological curvature scale spaces , 2005, Machine Vision and Applications.

[5]  M. Kumagai,et al.  Fluorescence-assisted image analysis of freshwater microalgae. , 2002, Journal of microbiological methods.

[6]  Bernd Hamann,et al.  Region Growing for Segmenting Green Microalgae Images , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[7]  Pakaket Wattuya,et al.  Automated Microalgae Image Classification , 2014, ICCS.

[8]  Paulo Drews,et al.  Microalgae classification using semi-supervised and active learning based on Gaussian mixture models , 2013, Journal of the Brazilian Computer Society.

[9]  Gabriel Cristóbal,et al.  Automated Diatom Classification (Part B): A Deep Learning Approach , 2017 .

[10]  Burkhard A. Hense,et al.  Use of fluorescence information for automated phytoplankton investigation by image analysis , 2008 .

[11]  Phooi Yee Lau,et al.  A framework for the automatic identification of algae (Neomeris vanbosseae M.A. Howe):U3S , 2014, 2014 International Conference on Computer and Information Sciences (ICCOINS).

[12]  Guangrong Ji,et al.  Application of Connected Morphological Operators to Image Smoothing and Edge Detection of Algae , 2009, 2009 International Conference on Information Technology and Computer Science.

[13]  C. Mathers,et al.  Cancer incidence and mortality worldwide: Sources, methods and major patterns in GLOBOCAN 2012 , 2015, International journal of cancer.

[14]  Antanas Verikas,et al.  An Integrated Approach to Analysis of Phytoplankton Images , 2015, IEEE Journal of Oceanic Engineering.

[15]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[16]  Bernd Hamann,et al.  A Highly Accurate Level Set Approach for Segmenting Green Microalgae Images , 2015, 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images.