Assessing the potential for deep learning and computer vision to identify bumble bee species from images
| Autor: | Richard G. Hatfield, Krushi Patel, Brian P. McCornack, Claudio Gratton, Guanghui Wang, William H. Hsu, Brian J. Spiesman, Sarina Jepsen |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
0106 biological sciences
0301 basic medicine Conservation of Natural Resources Databases Factual Computer science Ecology (disciplines) Science 010603 evolutionary biology 01 natural sciences Convolutional neural network Bottleneck Article 03 medical and health sciences Deep Learning Species Specificity Pollinator Artificial Intelligence Machine learning Image Processing Computer-Assisted Web application Species identification Animals Computer vision Community ecology Pollination Ecosystem Multidisciplinary Ecology business.industry Pigmentation Conservation biology Deep learning Biodiversity Bees Identification (information) 030104 developmental biology North America Medicine Artificial intelligence Neural Networks Computer business |
| Zdroj: | Scientific Reports Scientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) |
| ISSN: | 2045-2322 |
| Popis: | Pollinators are undergoing a global decline. Although vital to pollinator conservation and ecological research, species-level identification is expensive, time consuming, and requires specialized taxonomic training. However, deep learning and computer vision are providing ways to open this methodological bottleneck through automated identification from images. Focusing on bumble bees, we compare four convolutional neural network classification models to evaluate prediction speed, accuracy, and the potential of this technology for automated bee identification. We gathered over 89,000 images of bumble bees, representing 36 species in North America, to train the ResNet, Wide ResNet, InceptionV3, and MnasNet models. Among these models, InceptionV3 presented a good balance of accuracy (91.6%) and average speed (3.34 ms). Species-level error rates were generally smaller for species represented by more training images. However, error rates also depended on the level of morphological variability among individuals within a species and similarity to other species. Continued development of this technology for automatic species identification and monitoring has the potential to be transformative for the fields of ecology and conservation. To this end, we present BeeMachine, a web application that allows anyone to use our classification model to identify bumble bees in their own images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink