Automatic identification of species with neural networks
A new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the imag...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2014-11-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/563.pdf |
| _version_ | 1797421744696328192 |
|---|---|
| author | Andrés Hernández-Serna Luz Fernanda Jiménez-Segura |
| author_facet | Andrés Hernández-Serna Luz Fernanda Jiménez-Segura |
| author_sort | Andrés Hernández-Serna |
| collection | DOAJ |
| description | A new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the images. Artificial neural networks (ANNs) were used as the pattern recognition method. We tested a data set that included 740 species and 11,198 individuals. Our results show that the system performed with high accuracy, reaching 91.65% of true positive fish identifications, 92.87% of plants and 93.25% of butterflies. Our results highlight how the neural networks are complementary to species identification. |
| first_indexed | 2024-03-09T07:21:52Z |
| format | Article |
| id | doaj.art-59d22845ca4f4fa0854beee3435ca65b |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T07:21:52Z |
| publishDate | 2014-11-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-59d22845ca4f4fa0854beee3435ca65b2023-12-03T07:15:18ZengPeerJ Inc.PeerJ2167-83592014-11-012e56310.7717/peerj.563563Automatic identification of species with neural networksAndrés Hernández-Serna0Luz Fernanda Jiménez-Segura1Grupo de Ictiología, Instituto de Biología, Universidad de Antioquia, Medellín, ColombiaGrupo de Ictiología, Instituto de Biología, Universidad de Antioquia, Medellín, ColombiaA new automatic identification system using photographic images has been designed to recognize fish, plant, and butterfly species from Europe and South America. The automatic classification system integrates multiple image processing tools to extract the geometry, morphology, and texture of the images. Artificial neural networks (ANNs) were used as the pattern recognition method. We tested a data set that included 740 species and 11,198 individuals. Our results show that the system performed with high accuracy, reaching 91.65% of true positive fish identifications, 92.87% of plants and 93.25% of butterflies. Our results highlight how the neural networks are complementary to species identification.https://peerj.com/articles/563.pdfPlantButterfliesFishNeural networkFeature extractionDigital image |
| spellingShingle | Andrés Hernández-Serna Luz Fernanda Jiménez-Segura Automatic identification of species with neural networks PeerJ Plant Butterflies Fish Neural network Feature extraction Digital image |
| title | Automatic identification of species with neural networks |
| title_full | Automatic identification of species with neural networks |
| title_fullStr | Automatic identification of species with neural networks |
| title_full_unstemmed | Automatic identification of species with neural networks |
| title_short | Automatic identification of species with neural networks |
| title_sort | automatic identification of species with neural networks |
| topic | Plant Butterflies Fish Neural network Feature extraction Digital image |
| url | https://peerj.com/articles/563.pdf |
| work_keys_str_mv | AT andreshernandezserna automaticidentificationofspecieswithneuralnetworks AT luzfernandajimenezsegura automaticidentificationofspecieswithneuralnetworks |