Word2Image: Towards visual interpreting of words

Abstract

Besides the traditional textual semantic description to convey the meanings of a certain concept or word, visual illustration is a complementary, yet important and more intuitive way to interpret the word. Thus the technique that converts word to image is desirable though it is very difficult. Since a word usually has different semantic aspects, we need several correct and semanticrich images to represent the word. In this paper, we explore how to leverage the web image collections to fulfill such task and develop a novel multimedia application system, Word2Image. Various techniques, including the correlation analysis, semantic and visual clustering are adapted into our system to produce sets of high quality, precise, diverse and representative images to visually translate a given word. The objective and subjective evaluations show the feasibility and effectiveness of our approach.Copyright 2008 ACM.