I-Nema: a large-scale microscopic image dataset for nematode recognition

Nematode worms are one of the most abundant metazoan groups, occupying diverse ecological niches. Accurate recognition or identification of nematodes is of great importance for pest control, soil ecology, biogeography, habitat conservation, and climate change. Computer vision has witnessed a few successes in species recognition of nematodes; however, it is still in great demand. In this paper, we identify two main bottlenecks: (1) the lack of a publicly available microscopic-imaging dataset for diverse species of nematodes (especially the species only found in a natural environment) which requires considerable human resources in fieldwork and experts in taxonomy, and (2) the lack of a standard benchmark of state-of-the-art deep learning techniques on this dataset which demands the discipline background in computer science. With these in mind, we propose a large-scale microscopic image dataset consisting of 9215 images and 40 species (4 laboratories cultured and 36 naturally isolated species), which, to our knowledge, is the first time in the community. We further set up a species recognition benchmark by employing state-of-the-art deep learning networks on this dataset. We discuss the experimental results, compare the recognition accuracy of different networks, and show the challenges of our dataset. We will make our dataset publicly available.