Hybrid Content-Based Image Retrieval System for a Comprised 27-Class Euphorbia Seed Dataset Using Deep Feature Fusion
Open Access
- 30 September 2025
- journal article
- Published by Ankara University Faculty of Agriculture in Tarım Bilimleri Dergisi
- Vol. 31 (4) , 931-940
Abstract
Content-based Image Retrieval (CBIR) systems have been used frequently in recent years, along with developing technology. Especially in large datasets, retrieval-based systems produce more successful results. This study created a dataset consisting of 27 different Euphorbia seed types belonging to the same genus. It is difficult for Convolutional Neural Network (CNN) architectures to produce successful results in the created dataset. In addition, the high computational and memory requirements of CNN architectures have further increased the need for CBIR systems in large datasets. Therefore, a hybrid retrieval system was developed to make inferences from 27 different seed images. In the developed system, feature extraction was performed using Darknet53, Xception, and Densenet201 architectures. These extracted features were concatenated to bring together different features of the same image. Then, unnecessary features were eliminated from the combined features with the Neighborhood Component Analysis (NCA) method. The cosine similarity measurement metric was used to measure the similarity between the query image and other images. Precision-recall curves and Average Precision (AP) metrics were used to measure the performance of the proposed retrieval-based system. In the study, an average AP value of 0.96809 was obtained. The morphology of the seeds is a critical characteristic of Euphorbia, and this work has validated the artificial intelligence methodology.Keywords
This publication has 31 references indexed in Scilit:
- Neighborhood component analysis-based feature selection in machine learning to predict tendon ultimate stress of unbonded prestressed concrete beamsCase Studies in Construction Materials, 2024
- Automated deep feature fusion based approach for the classification of multiclass rice diseasesIran Journal of Computer Science, 2023
- Classification of the images (Plant-21) in the dataset created with 21 different Euphorbia Taxons with the developed AI-based hybrid modelSignal, Image and Video Processing, 2023
- Deep transfer learning enabled DenseNet model for content based image retrieval in agricultural plant disease imagesMultimedia Tools and Applications, 2023
- Deep learning based soybean seed classificationComputers and Electronics in Agriculture, 2022
- Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly applicationBiomedical Signal Processing and Control, 2022
- A deep learning approach to intelligent fruit identification and family classificationMultimedia Tools and Applications, 2022
- A novel deep learning based approach for seed image classification and retrievalComputers and Electronics in Agriculture, 2021
- Convolutional neural networks for relevance feedback in content based image retrievalMultimedia Tools and Applications, 2020
- Seed morphology in Euphorbia and its taxonomic applications: a case study in São Paulo, BrazilBrazilian Journal of Botany, 2015