LMFM-12

(Please refer to the 3rd version) Intended for 'A Morphologically Diverse Freshwater Microalgae Dataset for Deep Learning-Based Classification with Transfer Learning Analysis' for the study of microalgae image classification deep learning models. The dataset consist 7,555 images of 12 freshwater microalgae species and splitted into train:val:test (7:2:1). The files inside each folder of classes were labeled according to their ID number in NIES. The 12 microalgae species available are: Closterium gracile Coelastrum morus Micrasterias crux-melitensis Pediastrum duplex Planctonema lauterbornii Scenedesmus acutus Scenedesmus bijuga Selenastrum gracile Spirogyra majuscula Stigeoclonium sp. Tetradesmus dimorphus Treubaria triappendiculata Our paper can be found at: Hussin, A. A. B., Shapiai, M. I., Mohamad, S. E., Iwamoto, K., Kamaroddin, M. F., & Takemoto, K. (2026). A morphologically diverse freshwater microalgae dataset for deep learning-based classification with transfer learning analysis. Ecological Informatics, 94, 103655.