Data and Image Classification of Haematococcus pluvialis Based on SVM Algorithm

作者：Mengyu Yang, Shigang Cui, Yongli Zhang, Jingyu Zhang, Xinqi Li · 发表于：2021 China Automation Congress (CAC) · 年份：2021 · DOI：10.1109/cac53003.2021.9727433 · 被引用次数：4 · 研究领域：Digital Imaging for Blood Diseases

The growth process of Haematococcus pluvialis includes cell proliferation stage and astaxanthin accumulation stage. There are differences in cell radius, cell color and cell number between the two stages. In this paper, cell images and cell data of two growth stages were collected, and SVM algorithm was used to establish two classification models of data and image of Haematococcus pluvialis cell. 30% of the data in the samples were selected as the test set. In cell data binary classification problem, SVM classification algorithm was used, and the final classification result was 0.855; In the problem of image binary classification, the accuracy of the model is tested by the method of ten-fold cross validation, and the ROC curve and AUC area are used to evaluate the model. Finally, the classification result of the model for Haematococcus pluvialis cell image is 0.90, and the performance is good.