Effective term weighting in ALT text prediction for web image retrieval

  • Authors:
  • Vundavalli Srinivasarao;Prasad Pingali;Vasudeva Varma

  • Affiliations:
  • Search and Information Extraction Lab, International Institute of Information Technology, Hyderabad, India;Search and Information Extraction Lab, International Institute of Information Technology, Hyderabad, India;Search and Information Extraction Lab, International Institute of Information Technology, Hyderabad, India

  • Venue:
  • APWeb'11 Proceedings of the 13th Asia-Pacific web conference on Web technologies and applications
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The number of images on the World Wide Web has been increasing tremendously. Providing search services for images on the web has been an active research area.Web images are often surrounded by different associated texts like ALT text, surrounding text, image filename, html page title etc. Many popular internet search engines make use of these associated texts while indexing images and give higher importance to the terms present in ALT text. But, a recent study has shown that around half of the images on the web have no ALT text. So, predicting the ALT text of an image in a web page would be of great use in web image retrieval. We treat the prediction of ALT text as the problem of automatic image annotation based on the associated texts. We propose a term weighting model that makes use of term co-occurrences in associated texts and predicts the ALT text of an image. Using our approach, we achieved a good improvement in performance over baseline.