This paper deals with automatic taxa identification based on machine learning methods. The aim is therefore to automatically classify diatoms, in terms of pattern recognition terminology. Diatoms are a kind of algae microorganism with high biodiversity at the species level, which are useful for water quality assessment. The most relevant features for diatom description and classification have been selected using an extensive dataset of 80 taxa with a minimum of 100 samples/taxon augmented to 300 samples/taxon. In addition to published morphological, statistical and textural descriptors, a new textural descriptor, Local Binary Patterns (LBP), to characterize the diatom's valves, and a log Gabor implementation not tested before for this purpose are introduced in this paper. Results show an overall accuracy of 98.11% using bagging decision trees and combinations of descriptors. Finally, some phycological features of diatoms that are still difficult to integrate in computer systems are discussed for future work.

No abstract

Currently, microalgae (i.e., diatoms) constitute a generally accepted bioindicator of water quality and therefore provide an index of the status of biological ecosystems. Diatom detection for specimen counting and sample classification are two difficult time-consuming tasks for the few existing expert diatomists. To mitigate this challenge, in this work, we propose a fully operative low-cost automated microscope, integrating algorithms for: (1) stage and focus control, (2) image acquisition (slide scanning, stitching, contrast enhancement), and (3) diatom detection and a prospective specimen classification (among 80 taxa). Deep learning algorithms have been applied to overcome the difficult selection of image descriptors imposed by classical machine learning strategies. With respect to the mentioned strategies, the best results were obtained by deep neural networks with a maximum precision of 86% (with the YOLO network) for detection and 99.51% for classification, among 80 different species (with the AlexNet network). All the developed operational modules are integrated and controlled by the user from the developed graphical user interface running in the main controller. With the developed operative platform, it is noteworthy that this work provides a quite useful toolbox for phycologists in their daily challenging tasks to identify and classify diatoms.

Many biological objects are barely distinguished with the brightfield microscope because they appear transparent, translucent and colourless. One simple way to make such specimens visible without compromising contrast and resolution is by controlling the amount and the directionality of the illumination light. Oblique illumination is an old technique described by many scientists and microscopists that however has been largely neglected in favour of other alternative methods. Oblique lighting is created by illuminating the sample by only a portion of the light coming from the condenser. If properly used it can improve the resolution and contrast of transparent specimens such as diatoms. In this paper a quantitative evaluation of OL in brigthfield microscopy is presented. Several feature descriptors were selected for characterising contrast and sharpness showing that in general OL provides better performance for distinguishing minute details compared to other lighting modalities. Oblique lighting is capable to produce directionally shadowed differential contrast images allowing to observe phase details in a similar way to differential contrast images (DIC) but at lower cost. The main advantage of OL is that the resolution of the light microscope can be increased by effectively doubling the angular aperture. OL appears as a cost-effective technique both for the amateur and professional scientist that can be used as a replacement of DIC or phase contrast when resources are scarce.

Diatom detection has been a challenging task for computer scientist and biologist during past years. In this work, the new state of art techniques based on the deep learning framework have been tested, in order to check whether they are suitable for this purpose. On the one hand, RCNNs (Region based Convolutional Neural Networks), which select candidate regions and applies a convolutional neural network and, on the other hand, YOLO (You Only Look Once), which applies a single neural network over the whole image, have been tested. The first one is able to reach poor results in out experimentation, with an average of 0.68 recall and some tricky aspects, as for example it is needed to apply a bounding box merging algorithm to get stable detections; but the second one gets remarkable results, with an average of 0.84 recall in the evaluation that have been carried out, and less aspects to take into account after the detection has been performed. Future work related to parameter tuning and processing are needed to increase the performance of deep learning in the detection task. However, as for classification it has been probed to provide succesfully performance.