Dumitru Dan Burdescu, Liana Stanescu and Marius Brezovan

9 Information extraction from medical images: evaluating a novel automatic image annotation system using semantic-based visual information retrieval

Abstract: Today, in the medical field there are huge amounts of non-textual information, such as radiographic images, generated on a daily basis. Given the substantial increase of medical data stored in digital libraries, it is becoming more and more difficult to perform search and information retrieval tasks. Image annotation remains a difficult task for two reasons: (1) the semantic gap problem –it is hard to extract semantically meaningful entities when using low-level image features; and (2) the lack of correspondence between the keywords ...

Get Text Mining of Web-Based Medical Content now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.