31 January 1995 Image retrieval using image context vectors
Author Affiliations +
Proceedings Volume 2368, 23rd AIPR Workshop: Image and Information Systems: Applications and Opportunities; (1995) https://doi.org/10.1117/12.200783
Event: 23 Annual AIPR Workshop: Image and Information Systems: Applications and Opportunities, 1994, Washington, DC, United States
Abstract
Searching image databases using image queries is a challenging problem. For the analogous problem with text, those document retrieval methods that use `superficial' information, such as word count statistics, generally outperform natural language understanding approaches. This motivates an exploration of `superficial' feature-based methods for image retrieval. The main strategy is to avoid full image understanding, or even segmentation. The key question for any image retrieval approach is how to represent the images. We are exploring a new image context vector representation. A context vector is a high (approximately 300) dimensional vector that can represent images, sub-images, or image queries. The image is first represented as a collection of pairs of features with relative orientations defined by the feature pairs. Each feature pair is transformed into a context vector, and then all the vectors for pairs are added together to form the 300-dimensional image context vector for the entire image. This paper examines the image context vector approach and its expected strengths and weaknesses.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Steve Gallant, David M. Fram, "Image retrieval using image context vectors", Proc. SPIE 2368, 23rd AIPR Workshop: Image and Information Systems: Applications and Opportunities, (31 January 1995); doi: 10.1117/12.200783; https://doi.org/10.1117/12.200783
PROCEEDINGS
11 PAGES


SHARE
RELATED CONTENT


Back to Top