Semantic-visual concept relatedness and co-occurrences for image retrieval

Abstract

This paper introduces a novel approach that allows the retrieval of complex images by integrating visual and semantic concepts. The basic idea consists of three aspects. First, we measure the relatedness of semantic and visual concepts and select the visually separable semantic concepts as elements in the proposed image signature representation. Second, we demonstrate the existence of concept co-occurrence patterns. We propose to uncover those underlying patterns by detecting the communities in a network structure. Third, we leverage the visual and semantic correspondence and the co-occurrence patterns to improve the accuracy and efficiency for image retrieval. We perform experiments on two popular datasets that confirm the effectiveness of our approach.

A Semantic Image Retrieval Technique Through Concept Co-occurrence Based Database Organization and DeepLab Segmentation

“…One of the vital attribute which must be considered in the retrieval tasks associated with natural scene database is the co-occurrence information of concepts. Linan and Bhanu (2012; utilized the cooccurrence information of concepts along with semantic visual concept relatedness to perform image annotation and retrieval tasks. The application of cooccurrence information is limited to pairs of concepts and did not extend to higher levels.…”