Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance

Owing to climate change and human indiscriminate development, the population of endangered species has been decreasing. To protect endangered species, many countries worldwide have adopted the CITES treaty to prevent the extinction of endangered plants and animals. Moreover, research has been conduc...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Woohyuk Jang, Eui Chul Lee
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/f1702ca2f8b040d0950a380aa7406d59
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:f1702ca2f8b040d0950a380aa7406d59
record_format dspace
spelling oai:doaj.org-article:f1702ca2f8b040d0950a380aa7406d592021-11-25T16:47:24ZMulti-Class Parrot Image Classification Including Subspecies with Similar Appearance10.3390/biology101111402079-7737https://doaj.org/article/f1702ca2f8b040d0950a380aa7406d592021-11-01T00:00:00Zhttps://www.mdpi.com/2079-7737/10/11/1140https://doaj.org/toc/2079-7737Owing to climate change and human indiscriminate development, the population of endangered species has been decreasing. To protect endangered species, many countries worldwide have adopted the CITES treaty to prevent the extinction of endangered plants and animals. Moreover, research has been conducted using diverse approaches, particularly deep learning-based animal and plant image recognition methods. In this paper, we propose an automated image classification method for 11 endangered parrot species included in CITES. The 11 species include subspecies that are very similar in appearance. Data images were collected from the Internet and built in cooperation with Seoul Grand Park Zoo to build an indigenous database. The dataset for deep learning training consisted of 70% training set, 15% validation set, and 15% test set. In addition, a data augmentation technique was applied to reduce the data collection limit and prevent overfitting. The performance of various backbone CNN architectures (i.e., VGGNet, ResNet, and DenseNet) were compared using the SSD model. The experiment derived the test set image performance for the training model, and the results show that the DenseNet18 had the best performance with an mAP of approximately 96.6% and an inference time of 0.38 s.Woohyuk JangEui Chul LeeMDPI AGarticleobject detectiondeep neural networkparrot classificationCITESillegal transactionBiology (General)QH301-705.5ENBiology, Vol 10, Iss 1140, p 1140 (2021)
institution DOAJ
collection DOAJ
language EN
topic object detection
deep neural network
parrot classification
CITES
illegal transaction
Biology (General)
QH301-705.5
spellingShingle object detection
deep neural network
parrot classification
CITES
illegal transaction
Biology (General)
QH301-705.5
Woohyuk Jang
Eui Chul Lee
Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
description Owing to climate change and human indiscriminate development, the population of endangered species has been decreasing. To protect endangered species, many countries worldwide have adopted the CITES treaty to prevent the extinction of endangered plants and animals. Moreover, research has been conducted using diverse approaches, particularly deep learning-based animal and plant image recognition methods. In this paper, we propose an automated image classification method for 11 endangered parrot species included in CITES. The 11 species include subspecies that are very similar in appearance. Data images were collected from the Internet and built in cooperation with Seoul Grand Park Zoo to build an indigenous database. The dataset for deep learning training consisted of 70% training set, 15% validation set, and 15% test set. In addition, a data augmentation technique was applied to reduce the data collection limit and prevent overfitting. The performance of various backbone CNN architectures (i.e., VGGNet, ResNet, and DenseNet) were compared using the SSD model. The experiment derived the test set image performance for the training model, and the results show that the DenseNet18 had the best performance with an mAP of approximately 96.6% and an inference time of 0.38 s.
format article
author Woohyuk Jang
Eui Chul Lee
author_facet Woohyuk Jang
Eui Chul Lee
author_sort Woohyuk Jang
title Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
title_short Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
title_full Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
title_fullStr Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
title_full_unstemmed Multi-Class Parrot Image Classification Including Subspecies with Similar Appearance
title_sort multi-class parrot image classification including subspecies with similar appearance
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/f1702ca2f8b040d0950a380aa7406d59
work_keys_str_mv AT woohyukjang multiclassparrotimageclassificationincludingsubspecieswithsimilarappearance
AT euichullee multiclassparrotimageclassificationincludingsubspecieswithsimilarappearance
_version_ 1718412992602701824