A probabilistic topic-connection model for automatic image annotation

  • Authors:

  • Xin Chen;Xiaohua Hu;Zhongna Zhou;Caimei Lu;Gail Rosen;Tingting He;E. K. Park

  • Affiliations:

  • Drexel University, Philadelphia, PA, USA;Drexel University, Philadelphia, PA, USA;University of Missouri - Columbia, Columbia, MO, USA;Drexel University, Philadelphia, PA, USA;Drexel University, Philadelphia, PA, USA;Central China Normal University, Wuhan, China;City University of New York, Staten Island, NY, USA

  • Venue:
  • CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

The explosive increase of image data on Internet has made it an important, yet very challenging task to index and automatically annotate image data. To achieve that end, sophisticated algorithms and models have been proposed to study the correlation between image content and corresponding text description. Despite the success of previous works, however, researchers are still facing two major difficulties that may undermine their effort of providing reliable and accurate annotations for images. The first difficulty is lacking of comprehensive benchmark image dataset with high quality text descriptions. The second difficulty is lacking of effective way to represent the image content and make it associate with the text descriptions. In our paper, we aim to deal with both problems. To deal with the first problem, we utilize Wikipedia as external knowledge source and enrich the ontology structure of ImageNet database with comprehensive and highly-reliable text descriptions from Wikipedia articles. To address the second problem, we develop a Probabilistic Topic-Connection (PTC) model to represent the connection between latent semantic topic in text description and latent patterns from image feature space. We compare the performance of our model with the currently popular Correspondence LDA (Corr-LDA) model under the same automatic image annotation scenario using cross-validation. Experimental results demonstrate that our model is able to well represent the connection between latent semantic topics and latent patterns in image feature space, thus facilitates knowledge organization and understanding of both image and text descriptions.