应用对象语义进行图像检索的新方法  

A New Image Retrieval Method Using Object Semantics

作　　者：贾振超[1] 赵耀[1] 朱振峰[1] 

机构地区：[1]北京交通大学信息科学研究所,北京100044

出　　处：《铁道学报》2007年第4期111-114,共4页Journal of the China Railway Society

基　　金：教育部新世纪优秀人才支持计划;国家自然科学基金(60373028);高等学校博士学科点基金资助(20030004016);模式识别国家重点实验室开放基金

摘　　要：为了降低图像高层语义与低层视觉特征之间的语义差异,本文以对象描述模型为基础,提出利用机器转换模型获取图像高层语义的方法。本方法首先利用图像分割技术对图像进行分割,然后利用机器学习的方法,得到训练样本集中高层语义与分割后低层视觉特征之间的先验概率关系;在查询的过程中,利用得到的先验概率模型计算与高层语义所对应的最大概率视觉低层特征,最后利用该低层特征进行检索,达到缩短高层语义与低层特征之间的语义差异的目的。在一个拥有5000幅图像的图像库上所做的测试结果表明了该方法的有效性和可行性,同时该方法也为解决图像高层语义与视觉低层特征之间语义的矛盾开扩了思路。In order to narrow the semantics gap between high-level image semantics and low-level vision features, on the basis of the object description model, this paper proposes a method to utilize the machine transform model and get high-level image semantics. First, the proposed method uses a traditional arithmetic to segment training images and then , by machine learning, provides a strategy to obtain the prior probability of image semantics and low level vision features. During retrieval, the maximum posterior probability of the low level feature corresponding to the specified high-level semantics is computed. Thus the goal of retrieving image database by high-level image semantics can be met. The experiment on the image database including 5000 pictures shows the efficiency and feasibility of the method. The proposed method provides a new way to narrow the semantics gap between high-level image semantics and low-level vision features.

关 键 词：基于内容的图像检索 图像语义 机器学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]