Localized content-based image retrieval
Autor: | Sharath R. Cholleti, Jason E. Fritts, Rouhollah Rahmani, Sally A. Goldman, Hui Zhang |
---|---|
Rok vydání: | 2008 |
Předmět: |
Databases
Factual Computer science Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Relevance feedback Information Storage and Retrieval Documentation Similarity measure Content-based image retrieval Pattern Recognition Automated Artificial Intelligence Image Interpretation Computer-Assisted Segmentation Computer vision Image retrieval business.industry Applied Mathematics Pattern recognition Image segmentation Image Enhancement Object detection Automatic image annotation Radiology Information Systems Computational Theory and Mathematics Database Management Systems Computer Vision and Pattern Recognition Artificial intelligence business Software Algorithms |
Zdroj: | IEEE transactions on pattern analysis and machine intelligence. 30(11) |
ISSN: | 1939-3539 |
Popis: | We define localized content-based image retrieval as a CBIR task where the user is only interested in a portion of the image, and the rest of the image is irrelevant. In this paper we present a localized CBIR system, ACCIO, that uses labeled images in conjunction with a multiple-instance learning algorithm to first identify the desired object and weight the features accordingly, and then to rank images in the database using a similarity measure that is based upon only the relevant portions of the image. A challenge for localized CBIR is how to represent the image to capture the content. We present and compare two novel image representations, which extend traditional segmentation-based and salient point-based techniques respectively, to capture content in a localized CBIR setting. |
Databáze: | OpenAIRE |
Externí odkaz: |