Query-based image tagging model using ensemble learning with enhanced artificial bee colony optimization

Digital images make up most multimedia data and are analysed in computer vision applications. Daily uploads of millions pictures to Internet archives such as satellite image repositories complicate content graphs. As feature vectors, based retrieval (CBIR) classification models represent high-level viewpoints. Observing photos recognizes objects evaluates their significance for enhancement. To access the visual information big datasets, efficiently retrieve query picture The artificial bee colony (ABC) algorithm is inspired by foraging behaviour honeybee swarms. ABC susceptible laziness convergence local optimums, just like other optimization methods. This study created an enhanced (EABC) model enhance precision. presents query-based tagging using ensemble learning with EABC (QbITM-ELEABC) CBIR appropriately on image. We examine a number convolutional neural network (CNNs) varying topologies that can be trained dataset degrees similarity. representations, each extracts class probability vectors from images. final representation combining ensemble's