Digital Safari Guidebook with Image Retrieval

  • Authors:
  • Toshiyuki Iwaoka;Hideyuki Kobayashi;Shunji Ota

  • Affiliations:
  • Omron Corporation;Omron Corporation;Omron Corporation

  • Venue:
  • ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

Digital Safari Guidebook will make it easy to file or search multimedia databases for educational and entertainment purposes. When a user takes a picture of an animal with a digital camera connected to the computer, similar images in the animal database will be retrieved simulating human preferences. The digital guidebook will then show information about the animal. This is a pursuit for the development of a new application with our KANSEI (feeling, impression or sensibility in Japanese) Image Retrieval technology which uses color and shape features of captured images. Our system extracts KANSEI features from each image, and sets adequate weights for combining those features. In the combining procedure, we introduce a new value called "adaptability". It judges how much of the features are extracted from the image. As a result, adaptability makes it possible to make a KANSEI model depending on each image and to calculate similarity between images.