Author:
Durso Andrew M.,Moorthy Gokula Krishnan,Mohanty Sharada P.,Bolon Isabelle,Salathé Marcel,Ruiz de Castañeda Rafael
Abstract
We trained a computer vision algorithm to identify 45 species of snakes from photos and compared its performance to that of humans. Both human and algorithm performance is substantially better than randomly guessing (null probability of guessing correctly given 45 classes = 2.2%). Some species (e.g., Boa constrictor) are routinely identified with ease by both algorithm and humans, whereas other groups of species (e.g., uniform green snakes, blotched brown snakes) are routinely confused. A species complex with largely molecular species delimitation (North American ratsnakes) was the most challenging for computer vision. Humans had an edge at identifying images of poor quality or with visual artifacts. With future improvement, computer vision could play a larger role in snakebite epidemiology, particularly when combined with information about geographic location and input from human experts.
Reference94 articles.
1. Geographic variation in mimetic precision among different species of coral snake mimics;Akcali;J. Evol. Biol.,2017
2. Image classification for snake species using machine learning techniques;Amir,2016
3. Objectnet: a large-scale bias-controlled dataset for pushing the limits of object recognition models;Barbu,2019
4. Identifying biodiversity using citizen science and computer vision: introducing Visipedia
BarryJ.
2016
5. The battle against the long tail;Bengio,2015
Cited by
17 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献