Heliconius butterflies, a genus of butterfly that lives in South America, exhibit Mullerian mimicry, a type of mimicry in which toxic unrelated species evolve to share warning signals to teach and reinforce their toxicity to predators. A common point of contact between biology and computer science uses machine learning and computer vision to classify species. Building upon previous work in this field, this paper seeks to expand classification to capture the biological mechanisms underlying mimicry. By modifying the training methods and inputs used in machine learning, computer vision is capable of creating representations of natural systems of mimicry. One approach, which modified the training method, trained classification on one Heliconius species before testing on its mimic, in order to approximate the training and learning process undertaken by avian predators in the wild. The other sought to account for the visual complexities of butterfly mimicry by adjusting the visual acuity of the images to better represent butterfly and bird vision. These methods were successful, with significant results indicating that the model effectively represents the mimicry system.