Performance Analysis of Query-Based Image Tagging Model in CBIR

Content-Based Image Retrieval (CBIR) is essential in multimedia search engine optimization. The most useful feature extraction techniques are Related Edge clustered Pixel Extraction (RECPE-WFVS), Octagonal pixel divergence edge detection (OPDED), and Interlinked Feature Query Image retrieval model (IFQ-IRM). These techniques are used to extract the essential features from a query image. Here, the Query-based image tagging model with ensemble classifiers Support Vector Machine (SVM) and Decision trees (DC) techniques with optimization technique enhanced Artificial Bee Colony algorithm (QbITM-ELEABC) is used in CBIR. This model is run on three datasets, PatternNet, MLRSNet, and UC MERCED LAND USE, and the results are evaluated using three measures: Precision, Recall, and F-measure.