基于感知意象的图像检索技术  

Image Retrieval Technigue Based on Perception Imagery

作　　者：李柳柏[1] 

机构地区：[1]长江师范学院,重庆涪陵408100

出　　处：《西南师范大学学报（自然科学版）》2010年第6期110-114,共5页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：教育部"春晖计划"科研项目(Z2005-1-55003)

摘　　要：鉴于用户在图像检索过程中具有对检索结果的感知意向需求,构建了感知意象模型,并设计了基于该模型的检索系统.该系统运用距离直方图提取和表示图像形态特征,采用傅里叶变换的纹理特征方法提取图像的纹理特征,并运用相似性度量和图像意象的相关度标注技术进行系统的扩充和标注.该系统充分体现了用户意象需求,用户利用意象词汇能够检索符合其意象认知的图像.实验证明,利用感知意向模型进行图像检索具有较好的效果.As the user has owned requirement among the image retrieval,perception imagery model was designed,and image retrieval system was built based on perception imagery.The distance distribution histogram were used to extract and express the products＇ image shape characteristics.And the texture characteristics were obtained and described by Fourier transform.Comparability measurement and imagery correlation label techniques were combined to expand and label the system database.This technique satisfies the designers＇ requirements to retrieve image by imagery words in consistence with users＇ imagery cognition model,and it conquers the shortcoming in the traditional retrieval model which cannot describe users＇ imagery.The test demonstrates that image retrieval based on perception imagery has a very good effect.

关 键 词：图像检索 感知意向 特征提取 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]