<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The main goal of the present research is to classify images of plants to species with deep learning. We used convolutional neural network architectures for feature learning and fully connected layers with logsoftmax output for classification. Pretrained models on ImageNet were used, and transfer learning was applied. In the current research image sets published in the scope of the PlantCLEF 2015 challenge were used. The proposed system surpasses the results of all top competitors of the challenge by 8% and 7% at observation and image levels, respectively. Our secondary goal was to satisfy the users’ needs in content-based image retrieval to give relevant hits during species search task. We optimized the length of the returned lists in order to maximize MAP (Mean Average Precision), which is critical to the performance of image retrieval. Thus, we achieved more than 50% improvement of MAP in the test set compared to the baseline.</p></abstract>

The main goal of the present research is to classify images of plants to species with deep learning. We used convolutional neural network architectures for feature learning and fully connected layers with logsoftmax output for classification. Pretrained models on ImageNet were used, and transfer learning was applied. In the current research image sets published in the scope of the PlantCLEF 2015 challenge were used. The proposed system surpasses the results of all top competitors of the challenge by 8% and 7% at observation and image levels, respectively. Our secondary goal was to satisfy the users’ needs in content-based image retrieval to give relevant hits during species search task. We optimized the length of the returned lists in order to maximize MAP (Mean Average Precision), which is critical to the performance of image retrieval. Thus, we achieved more than 50% improvement of MAP in the test set compared to the baseline.

Deep Learning for Plant Classification and Content-Based Image Retrieval

Budapest University of Technology and Economics

Department of Telecommunications and Media Informatics

Cybernetics and Information Technologies

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Deep Learning for Plant Classification and Content-Based Image Retrieval"}

The main goal of the present research is to classify images of plants to species with deep learning. We used convolutional neural network architectures for...

Deep Learning for Plant Classification and Content-Based Image Retrieval

Online veröffentlicht: 29. März 2019

Seitenbereich: 88 - 100

Eingereicht: 25. Sept. 2018

Akzeptiert: 20. Dez. 2018

DOI: https://doi.org/10.2478/cait-2019-0005

Schlüsselwörter
deep learning, convolutional neural networks, Inception V3, MAP, image retrieval

© 2019 Bálint Pál Gyires-Tóth et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Deep Learning for Plant Classification and Content-Based Image Retrieval

Online veröffentlicht: 29. März 2019

Seitenbereich: 88 - 100

Eingereicht: 25. Sept. 2018

Akzeptiert: 20. Dez. 2018

DOI: https://doi.org/10.2478/cait-2019-0005

Schlüsselwörterdeep learning, convolutional neural networks, Inception V3, MAP, image retrieval

© 2019 Bálint Pál Gyires-Tóth et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
deep learning, convolutional neural networks, Inception V3, MAP, image retrieval