شماره ركورد كنفرانس :
1730
عنوان مقاله :
A Long Term Learning Method in CBIR Systems by Defining Semantic Templates
عنوان به زبان ديگر :
A Long Term Learning Method in CBIR Systems by Defining Semantic Templates
پديدآورندگان :
Rashedi Esmat نويسنده , Nezamabadi-pour Hossein نويسنده
كليدواژه :
Content based image retrieval , Long term learning , Semantic template , semantic networks , content-based retrieval , Image retrieval
عنوان كنفرانس :
بيستمين كنفرانس مهندسي برق ايران
چكيده لاتين :
This paper provides a long term learning method in CBIR systems by defining a kind of semantic template to represent semantic concepts of images. Information, which isachieved in the short learning technique, is used in construction of semantic templates. A similarity function is introduced to findthe similarity between queries and semantic templates. The experimental results confirm the effectiveness of the proposed method.
شماره مدرك كنفرانس :
4460809
