Annotation of images using local binary pattern and local derivative pattern after salient object detection using minimum directional contrast and gradient vector flow

Abstract

Automatic image annotation is the process of providing tags to salient objects in the image. The aim is achieved by first identifying salient objects. For this, the traditional gradient vector flow (GVF) model is modified to incorporate saliency by adding minimum directional contrast to the data part in the energy functional of GVF. To provide tags, three features: color, local binary pattern and local direction pattern are used. Classification is done by modifying cluster-based multi-label learning with feature-induced labeling information enrichment (C-MLFE) and is termed as C’-MLFE. This involves clustering the training data into two sets. For each cluster, a squared weight matrix records the influence of each instance on the other. This relationship among the training instance is used to enrich the labeling information of the test set. The result is compared with six state-of-the-art algorithms. © 2020, Springer-Verlag London Ltd., part of Springer Nature.