Adaptive Learning of Region-based pLSA Model for Total Scene Annotation

TL;DR

This paper introduces an adaptive, region-based pLSA model for total scene annotation that combines segmentation, semantic modeling, and automatic padding to improve accuracy and localize tags within images.

Contribution

It proposes a novel adaptive padding mechanism and integrates region segmentation with pLSA for enhanced scene annotation and localization.

Findings

Effective scene annotation on Corel database

Improved localization accuracy of image regions

Enhanced semantic understanding of image content

Abstract

In this paper, we present a region-based pLSA model to accomplish the task of total scene annotation. To be more specific, we not only properly generate a list of tags for each image, but also localizing each region with its corresponding tag. We integrate advantages of different existing region-based works: employ efficient and powerful JSEG algorithm for segmentation so that each region can easily express meaningful object information; the introduction of pLSA model can help better capturing semantic information behind the low-level features. Moreover, we also propose an adaptive padding mechanism to automatically choose the optimal padding strategy for each region, which directly increases the overall system performance. Finally we conduct 3 experiments to verify our ideas on Corel database and demonstrate the effectiveness and accuracy of our system.