Content Based Image Retrieval Using ResNetV2

Abstract

The way or method in which an image is stored improves the retrieval process.  Building effective content-based image retrieval (CBIR) systems involves the combination of image creation, storage, security, transmission, analysis, evaluation feature extraction, and feature combination in order to store and retrieve images effectively. CBIR system focuses on retrieving images from the database and depends on the way the indexing is being implemented. In this paper the CBIR model is developed using ResNetV2 and vector distance is evaluated to match features and the query. Accuracy of the image retrieval process is high compared to colour histogram and was found to be more than 99% in each test.