Wood identification based on macroscopic images using deep and transfer learning approaches
Identifying forest types is vital for evaluating the ecological, economic, and social benefits provided by forests, and for protecting, managing, and sustaining them. Although traditionally based on expert observation, recent developments have increased the use of technologies such as artificial int...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2024-02-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/17021.pdf |
| _version_ | 1797289216809369600 |
|---|---|
| author | Halime Ergun |
| author_facet | Halime Ergun |
| author_sort | Halime Ergun |
| collection | DOAJ |
| description | Identifying forest types is vital for evaluating the ecological, economic, and social benefits provided by forests, and for protecting, managing, and sustaining them. Although traditionally based on expert observation, recent developments have increased the use of technologies such as artificial intelligence (AI). The use of advanced methods such as deep learning will make forest species recognition faster and easier. In this study, the deep network models RestNet18, GoogLeNet, VGG19, Inceptionv3, MobileNetv2, DenseNet201, InceptionResNetv2, EfficientNet and ShuffleNet, which were pre-trained with ImageNet dataset, were adapted to a new dataset. In this adaptation, transfer learning method is used. These models have different architectures that allow a wide range of performance evaluation. The performance of the model was evaluated by accuracy, recall, precision, F1-score, specificity and Matthews correlation coefficient. ShuffleNet was proposed as a lightweight network model that achieves high performance with low computational power and resource requirements. This model was an efficient model with an accuracy close to other models with customisation. This study reveals that deep network models are an effective tool in the field of forest species recognition. This study makes an important contribution to the conservation and management of forests. |
| first_indexed | 2024-03-07T19:00:55Z |
| format | Article |
| id | doaj.art-d1566409b6bd4de09cb322cd71b3d18c |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-07T19:00:55Z |
| publishDate | 2024-02-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-d1566409b6bd4de09cb322cd71b3d18c2024-03-01T15:05:24ZengPeerJ Inc.PeerJ2167-83592024-02-0112e1702110.7717/peerj.17021Wood identification based on macroscopic images using deep and transfer learning approachesHalime ErgunIdentifying forest types is vital for evaluating the ecological, economic, and social benefits provided by forests, and for protecting, managing, and sustaining them. Although traditionally based on expert observation, recent developments have increased the use of technologies such as artificial intelligence (AI). The use of advanced methods such as deep learning will make forest species recognition faster and easier. In this study, the deep network models RestNet18, GoogLeNet, VGG19, Inceptionv3, MobileNetv2, DenseNet201, InceptionResNetv2, EfficientNet and ShuffleNet, which were pre-trained with ImageNet dataset, were adapted to a new dataset. In this adaptation, transfer learning method is used. These models have different architectures that allow a wide range of performance evaluation. The performance of the model was evaluated by accuracy, recall, precision, F1-score, specificity and Matthews correlation coefficient. ShuffleNet was proposed as a lightweight network model that achieves high performance with low computational power and resource requirements. This model was an efficient model with an accuracy close to other models with customisation. This study reveals that deep network models are an effective tool in the field of forest species recognition. This study makes an important contribution to the conservation and management of forests.https://peerj.com/articles/17021.pdfWood identificationTransfer learningShuffleNet |
| spellingShingle | Halime Ergun Wood identification based on macroscopic images using deep and transfer learning approaches PeerJ Wood identification Transfer learning ShuffleNet |
| title | Wood identification based on macroscopic images using deep and transfer learning approaches |
| title_full | Wood identification based on macroscopic images using deep and transfer learning approaches |
| title_fullStr | Wood identification based on macroscopic images using deep and transfer learning approaches |
| title_full_unstemmed | Wood identification based on macroscopic images using deep and transfer learning approaches |
| title_short | Wood identification based on macroscopic images using deep and transfer learning approaches |
| title_sort | wood identification based on macroscopic images using deep and transfer learning approaches |
| topic | Wood identification Transfer learning ShuffleNet |
| url | https://peerj.com/articles/17021.pdf |
| work_keys_str_mv | AT halimeergun woodidentificationbasedonmacroscopicimagesusingdeepandtransferlearningapproaches |