An Architecture for Retrieval and Annotation of Images from Big Image Datasets

Abstract

Rapid advancements in mobile devices and communication technologies have resulted in the daily production of enormous quantities of visual data at both personal and business settings. These developments have stoked a need for improved methods of storing, annotating, and retrieving digital photographs. Images need to be well annotated and indexed for precise retrieval from large-scale picture classes. As a result, there is a growing need for sophisticated strategies for indexing, annotating, and retrieving images. In response to problems discovered during research into existing Image annotation and retrieval systems, the suggested system was developed. The Autoencoder is built with three levels of complexity: an encoder, a decoder, and a single layer of code. Dimensionality reduction is accomplished by extracting the Micro-Structure Descriptor (MSD) of the training picture, which has 72 dimensions. Dimensionality reduction is the focus of a new Autoencoder technique. To organise the wide variety of picture types, a unique Autoencoder Hashing method has been developed.