Details

Autor(en) / Beteiligte

• Ou, Yang Jia

Titel

Design and implementation of image semantic automatic annotation algorithm based on multi-label learning

Ort / Verlag

ProQuest Dissertations & Theses

Erscheinungsjahr

2011

Quelle

ProQuest Dissertations & Theses A&I

Beschreibungen/Notizen

• Translation from original language as provided by authorThe popularity of high resolution digital camera and the development of broadband communication networks resulted in a huge amount of image data, which makes information retrieval and management in large image database become an import topic- Due to the underlying features can not describe the high-level semantic accurately, traditional content-based image retrieval techniques could not provide sufficient semantic-based retrieval- The image semantic-based retrieval which can eradicate the "Semantic Gap" between the high-level semantic and the underlying feature of the image by building indexes for images is becoming a research hotspot- The key problem of image semantic-based retrieval is automatic annotation of image semantics, which is the bridge between the high-level semantic and the underlying feature of the image- The nature of automatic annotation of image semantics is a process of "learning", in which the labeled image set or other available infor