Anomaly Detection for In situ Marine Plankton Images
Abstract
Machine learning and deep learning algorithms have achieved great success in plankton image recognition, but most of them are proposed to deal with closed-set tasks, where the distribution of the test data is the same as the training one. In reality, however, we face the challenges of open-set tasks, which are also recognized as the anomaly detection problems. In these tasks, there often exist abnormal classes, which are not in the training set, and the final goal of anomaly detection is to detect the anomalies correctly so that the misclassification of them can be reduced. However, little attention has been paid to anomaly detection in marine related fields. In this paper, to help marine plankton observers to detect anomalies conveniently and efficiently, we propose an anomaly detection pipeline including both the training and the testing phases. The training phase includes two parts, the pre-training and the post-training. In the pre-training phase, we propose a new loss function to better detect the abnormal classes and classify the normal classes simultaneously, which incorporates the expected cross-entropy loss, the expected Kullback-Leibler divergence, and the Anchor loss. We conduct several experiments to show the efficacy of the proposed method and compare its performance with other competitors based on a newly released dataset of in situ marine plankton images. Numerical results show that the proposed method outperforms its competitors in terms of classification accuracy and other commonly used criteria.
BibTeX
@inproceedings{Priya2023MachineLearning,
author = {Priya, R.Mahalakshmi and Barani, R. and Sumathi, M.},
booktitle = {2023 5th International Conference on Inventive Research in Computing Applications (ICIRCA)},
title = {Machine Learning for Plankton Species Identification and Classification: A New Era in Marine Ecology},
year = {2023},
volume = {},
number = {},
pages = {101-108},
abstract = {As a key component of aquatic food webs and a major contributor to global biogeochemical cycles, plankton identification and classification are critical tasks in marine biology. While identifying and categorizing plankton species manually can be time-consuming, it requires considerable expertise. Machine learning approaches are proposed here for identifying and categorizing plankton. As well as providing insights into plankton ecology and biogeochemistry, automatic identification and classification of plankton species can inform management strategies for marine ecosystems. Training the model required a dataset of images of phytoplankton and zooplankton, which were classified into multiple categories by the model. The model was also evaluated for robustness against noise, occlusion, and illumination variations. A threshold-based segmentation method is used to detect plankton objects during the classification phase. Plankton classification using this threshold-based segmentation method requires the extraction of features from the image, such as shape, size, color, and texture. These features are used to categorize the different species of plankton. The model was then tested on field images to validate its accuracy. The results showed that the model was able to achieve high accuracy in classifying the different plankton species.},
keywords = {Training;Image segmentation;Machine learning algorithms;Shape;Biological system modeling;Ecosystems;Sociology;Plankton;phytoplankton;zooplankton;microorganisms;marine ecosystem;segmentation;identification;classification},
doi = {10.1109/ICIRCA57980.2023.10220751},
issn = {},
month = {Aug},
}