Back to Search
Start Over
Automatic Identification of Individual Primates with Deep Learning Techniques
- Source :
- iScience, Vol 23, Iss 8, Pp 101412-(2020), iScience
- Publication Year :
- 2020
- Publisher :
- Elsevier, 2020.
-
Abstract
- Summary The difficulty of obtaining reliable individual identification of animals has limited researcher's ability to obtain quantitative data to address important ecological, behavioral, and conservation questions. Traditional marking methods placed animals at undue risk. Machine learning approaches for identifying species through analysis of animal images has been proved to be successful. But for many questions, there needs a tool to identify not only species but also individuals. Here, we introduce a system developed specifically for automated face detection and individual identification with deep learning methods using both videos and still-framed images that can be reliably used for multiple species. The system was trained and tested with a dataset containing 102,399 images of 1,040 individuals across 41 primate species whose individual identity was known and 6,562 images of 91 individuals across four carnivore species. For primates, the system correctly identified individuals 94.1% of the time and could process 31 facial images per second.<br />Graphical Abstract<br />Highlights • The Tri-AI system can rapidly detect and identify individuals from videos and images • Tri-AI had an ID identification accuracy of 94% for 41 primates and 4 carnivores • The system could individually recognize 31 animals/s with images taken day or night • Systems like Tri-AI make around-the-clock monitoring and behavior analysis possible<br />Zoology; Ethology; Artificial Intelligence
- Subjects :
- 0301 basic medicine
Computer science
Process (engineering)
02 engineering and technology
Ethology
Machine learning
computer.software_genre
Article
03 medical and health sciences
Artificial Intelligence
Face detection
lcsh:Science
Multidisciplinary
business.industry
Deep learning
021001 nanoscience & nanotechnology
Multiple species
030104 developmental biology
Identity (object-oriented programming)
Identification (biology)
lcsh:Q
Artificial intelligence
0210 nano-technology
business
computer
Zoology
Subjects
Details
- Language :
- English
- ISSN :
- 25890042
- Volume :
- 23
- Issue :
- 8
- Database :
- OpenAIRE
- Journal :
- iScience
- Accession number :
- edsair.doi.dedup.....0b727713a7bcb1873f0a3901235ac829