IRCVJun 20, 2013

Analysing Word Importance for Image Annotation

arXiv:1306.4758v1
Originality Synthesis-oriented
AI Analysis

This work tackles the issue of word importance in image annotation for image retrieval, but it appears incremental as it builds on existing frequency-based methods.

The paper addresses the problem of treating all annotation words equally in traditional image annotation by proposing a method to compute importance scores for keywords based on frequency count and word correlation, aiming to improve annotation relevance.

Image annotation provides several keywords automatically for a given image based on various tags to describe its contents which is useful in Image retrieval. Various researchers are working on text based and content based image annotations [7,9]. It is seen, in traditional Image annotation approaches, annotation words are treated equally without considering the importance of each word in real world. In context of this, in this work, images are annotated with keywords based on their frequency count and word correlation. Moreover this work proposes an approach to compute importance score of candidate keywords, having same frequency count.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes