Automatic multi-label image annotation for smart cities

Abstract

Automatic image annotation is a technique by which computer systems automatically assigns appropriate Keywords to input digital image. Smart cities are characterized by large volume of data, one of the prominent data types are images. In present research, images of smart cities are collected and then using automatic image annotation, several relevant indexing terms are proposed for every image. Using these terms, images may be categorized and further can be used in appropriate applications. Image annotation is also used in keyword based search applications. Here, the goal is to obtain images according to the input keyword given by the user. To accomplish this, Multi-label image annotation using K-nearest Neighbor (ML-KNN) is used. In this approach, images in the database need to be indexed with the terms in annotation vocabulary. Automatically annotated images of the image database prior to the search may thus be helpful in many situations such as distribution of land, water and residential areas which can aid in effective urban planning and governance.