Differentiating butterfly species from each other using deep learning methods

It is of great importance to know which species a butterfly belongs to. Butterflies play a role in the continuation of plant species by pollinating flowers. They are also frequently the subject of natural life research. Knowing which species a butterfly belongs to gives clues about how this butterfly species will affect people, animals and plants. However, it is not easy to determine which species the butterflies belong to. Most of the time, their detection requires expertise. Therefore, studies have been carried out in the field of deep learning to distinguish butterfly species. Different methods have been suggested and improvements have been made in order to obtain better results. In this thesis, pre-trained deep learning models were used. Models were trained on the edited dataset and, in line with the results, a new model proposal was made based on the most successful model.