Hybrid Content-Based Image Retrieval System for a Comprised 27-Class Euphorbia Seed Dataset Using Deep Feature Fusion

Year 2025, Volume: 31 Issue: 4, 931 - 940, 30.09.2025

Murat Kürşat , Mücahit Karaduman , Hursit Burak Mutlu , İrfan Emre , Muhammed Yıldırım

https://doi.org/10.15832/ankutbd.1661676

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

CBIR , Retrieval , Seed , Classification , Deep Learning

References

• Apriyanti D H, Arymurthy A M & Handoko L T (2013, November). Identification of orchid species using content-based flower image retrieval. In 2013 International conference on computer, control, informatics and its applications (IC3INA) (pp. 53-57). IEEE.
• Auni A R & Sugiharti E (2024). Optimization of Mango Plant Leaf Disease Classification Using Concatenation Method of MobileNetV2 and DenseNet201 CNN Architectures. Scientific Journal of Informatics 11(4): 1023-1034
• da Silva O L M, Cordeiro I & Caruzo M B R (2016). Seed morphology in Euphorbia and its taxonomic applications: a case study in São Paulo, Brazil. Brazilian Journal of Botany, 39, 349-358.
• Davis P H (1965). 1985. Flora of Turkey and the Aegean Islands, Vol.: I-IX. Dayrell L, Ott T, HorrocksT & Poschlod P (2023). Automated extraction of seed morphological traits from images. Methods in Ecology and Evolution, 14(7), 1708-1718.
• Ding Z, Liu H, Demartino C, Feng M & Sun Z (2024). Neighborhood component analysis-based feature selection in machine learning to predict tendon ultimate stress of unbonded prestressed concrete beams. Case Studies in Construction Materials, 21, e03428.
• Fayed A A & Hassan N M (2007). Systematic significance of the seed morphology and seed coat sculpture of the genus Euphorbia L.(Euphorbiaceae) in Egypt. Flora Mediterrinea 17: 47-64
• Frodin D G (2004). History and concepts of big plant genera. Taxon, 53(3), 753-776.
• Gawli K S & Gaikwad A S (2020). Deep learning for plant species classification. JETIR, 7(11), 99-105.
• Gulzar Y, Hamid,Y, Soomro A.B, Alwan A A, & Journaux, L (2020). A convolution neural network-based seed classification system. Symmetry, 12(12), 2018
• Gyires-Tóth B P, Osváth M, Papp D & Szucs G (2019). Deep learning for plant classification and content-based image retrieval. Cybern. Inf. Technol, 19(1), 88-100.
• Haupt J, Kahl S, Kowerko D & Eibl M (2018). Large-Scale Plant Classification using Deep Convolutional Neural Networks. CLEF (Working Notes), 3.
• Huang Z, Wang R, Cao Y, Zheng S, Teng Y, Wang F & Du J (2022). Deep learning based soybean seed classification. Computers and Electronics in Agriculture, 202, 107393.
• Ibrahim N M, Gabr D G I, Rahman A U, Dash S & Nayyar A (2022). A deep learning approach to intelligent fruit identification and family classification. Multimedia Tools and Applications 81(19): 27783-27798
• Ibrahim N M, Gabr D G, Rahman A, Musleh D, AlKhulaifi D & AlKharraa M (2023). Transfer learning approach to seed taxonomy: a wild plant case study. Big Data and Cognitive Computing, 7(3), 128.
• Karthikeyan M & Raja D (2023). Deep transfer learning enabled DenseNet model for content based image retrieval in agricultural plant disease images. Multimedia Tools and Applications, 82(23), 36067-36090.
• Kumar M S, Neeraja P, Gunamaneni A, Nirmala A V & Nikhil G (2023, September). Deep Learning for Plant Species Classification. In 2023 International Conference on Sustainable Emerging Innovations in Engineering and Technology (ICSEIET) (pp. 559-564). IEEE.
• Kursat M, Başer B, Özbey F & Emre İ (2023). Seed morphology of some taxa of the genus Euphorbia L. (Euphorbiaceae) in Turkey and its taxonomic significance. Turkish Journal of Botany 47(4): 307-322
• Kursat M, Yildirim M, & Emre I (2023). Classification of the images (Plant-21) in the dataset created with 21 different Euphorbia Taxons with the developed AI-based hybrid model. Signal, Image and Video Processing 17(8): 4153-4161
• Lahitani A R, Permanasari A E & Setiawan N A (2016, April). Cosine similarity to determine similarity measure: Study case in online essay assessment. In 2016 4th International conference on cyber and IT service management (pp. 1-6). IEEE.
• Loddo A, Loddo M & Di Ruberto C (2021). A novel deep learning based approach for seed image classification and retrieval. Computers and Electronics in Agriculture, 187, 106269
• Lorenzo P, Luca P & Giorgio G. (2020). Convolutional neural networks for relevance feedback in content based image retrieval. Multimedia Tools and Applications, 79(37-38), 26995-27021
• Muneesawang P & Guan L (2004). An interactive approach for CBIR using a network of radial basis functions. IEEE Transactions on multimedia, 6(5): 703-716
• Pahlevani A H & Akhani H (2011). Seed morphology of Iranian annual species of Euphorbia (Euphorbiaceae). Botanical journal of the Linnean Society 167(2): 212-234
• Pandey N, Krishna S, & Sharma S (2013). Automatic seed classification by shape and color features using machine vision technology. International Journal of Computer Applications Technology and Research 2(2): 208-213
• Patil J K & Kumar R (2017). Analysis of content based image retrieval for plant leaf diseases using color, shape and texture features. Engineering in agriculture, environment and food 10(2): 69-78
• Picek L, Šulc M, Patel Y & Matas J (2022). Plant recognition by AI: Deep neural nets, transformers, and kNN in deep embeddings. Frontiers in plant science, 13, 787527.
• Sandler M, Howard A, Zhu M, Zhmoginov A & Chen L C (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4510-4520). Saritha R R, Paul V & Kumar P G (2019). Content based image retrieval using deep learning process. Cluster Computing, 22(Suppl 2), 41874200.
• Sunnetci K M, Ulukaya S & Alkan A (2022). Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly application. Biomedical Signal Processing and Control, 77, 103844.
• Sutaji D & Yıldız O (2022). LEMOXINET: Lite ensemble MobileNetV2 and Xception models to predict plant disease. Ecological Informatics, 70, 101698.
• Tan M & Le Q (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
• Theerthagiri P, Ruby A U, Chandran J G C, Sardar T H & Shafeeq BM A (2024). Deep SqueezeNet learning model for diagnosis and prediction of maize leaf diseases. Journal of Big Data 11(1), 112.
• Toğaçar M (2022). Using DarkNet models and metaheuristic optimization methods together to detect weeds growing along with seedlings. Ecological Informatics, 68, 101519.
• Yildirim M (2024). Content-Based Image Retrieval and Image Classification System for Early Prediction of Bladder Cancer. Diagnostics, 14(23): 2637
• Yucel N & Yildirim M (2024). Automated deep feature fusion based approach for the classification of multiclass rice diseases. Iran Journal of Computer Science 7(1): 131-138
• Yue J, Li Z, Liu L & Fu Z (2011). Content-based image retrieval using color and texture fused features. Mathematical and Computer Modelling 54(3-4): 1121-1127