• Raja
• Dr. M. Karthikeyan

Content-Based Image Retrieval (CBIR) is considered the most influential technology in the field of agriculture which enables agronomists, researchers, and farmers for efficient investigation and management of enormous agriculture image collections. CBIR method utilizes the image's visual contents like textures shapes, and colours instead of depending on textual or metadata descriptions for matching or retrieving identical images. Most prevalent methods for feature extraction process comprise texture descriptors (e.g., Local Binary Patterns), histograms, and deep learning model-based techniques which implement pre-trained Convolutional Neural Network (CNNs) for learning high-level image depictions. This study designs a new Grey Wolf Optimizer with Deep Learning Assisted Agricultural Content Based Image Retrieval (GWODL-ACBIR) model. In the GWODL-ACBIR technique, ResNet50 model is utilized for deriving the high-level features of the images, allowing effective depiction of the visual contents. To optimize the performance of the CBIR system, GWO is utilized to tune hyperparameters, such as learning rates and batch sizes, facilitating better convergence and accuracy during model training. Finally, the GWODL-ACBIR system determines the Euclidean distance between the query image's features and the features stored in the database, sorting the retrieved images based on their similarity to the query images. The simulation result analysis highlights the enhanced performance of the GWODL-ACBIR system over conventional approaches, accomplishing enhanced retrieval performance.

Content based image retrieval; Deep learning; Agricultural sector; Grey wolf optimizer; Computer vision

"Grey Wolf Optimizer with Deep Learning Assisted Agricultural Content Based Image Retrieval Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.j101-j112, July-2023, Available :http://www.jetir.org/papers/JETIR2307915.pdf

"Grey Wolf Optimizer with Deep Learning Assisted Agricultural Content Based Image Retrieval Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppj101-j112, July-2023, Available at : http://www.jetir.org/papers/JETIR2307915.pdf