they are also slowly but steadily gaining popularity. However, prototyping them for practical use remains a domain of experienced coders. Furthermore, current tools can be quite costly and difficult to put together for the non-domain AI coder. Whereas there are a few dozen papers using these powerful techniques - few describe beginner-friendly ways to prototype classifiers. This paper describes how non-expert ecologists with basic python experience and a well-curated image dataset; can prototype an expert taxonomist level classifier leveraging on already existing open-source accessible tools and libraries. This can be used by ecologists all over the world and widely adapted for citizen science as well as other applications not envisioned in this paper.
Point 2: We compiled open-source tools and an easy to use AI algorithm; to illustrate how experts in the natural history of their taxa; but non-domain experts in AI, with basic python skills can use their own species image datasets to create species classifiers. We include annotated code in form of a Jupyter Notebook that any reader can follow to understand the pipeline and which can be easily adapted to their own unique dataset that can range from satellite images, animals to bacteria.
Point 3: We illustrate our approach with a case study of 219 images of 3 three seastar species - and show that with minimal parameter tuning and tweaking of the AI pipeline we can create a classifier with 87% accuracy. We further propose ways of understanding the misclassified images and curating the dataset to push the accuracy further in instances where greater accuracy is essential before the classifier is deployed for classification purposes.
Point 4: We now live in a golden age where non-experts in AI can easily build and prototype species classifiers that can have great impacts on accurate species identifications and further implications for citizen science, biodiversity monitoring and other directions not envisioned here. Here we demonstrate one technique that could lead the way into this exciting future.