基于感兴趣区域特征提取技术的情感语义研究  

Research of image affection based on feature extraction technology of ROI

作　　者：吕进来[1] 相洁[1] 陈俊杰[1] 成琳[1] 

机构地区：[1]太原理工大学计算机与软件学院,山西太原030024

出　　处：《计算机工程与设计》2010年第3期660-662,666,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(60773004);山西省自然科学基金项目(2006011030)

摘　　要：提出一种基于感兴趣区域特征提取技术的图像情感语义识别模型。着重论述了感兴趣区域的获取、感兴趣区域与非感兴趣区域权重的确定、从RGB颜色空间到HSV颜色空间的转换算法、加权颜色直方图的统计算法以及最终情感聚类的方法。仿真实验结果表明,该模型所实现的底层特征到高层情感语义映射准确率比传统的颜色特征提取技术的图像情感语义识别模型有很大的提高。Image affective semantic recognition model is a model based on ROI feature extraction techniques.It discusses the acquisition ROI determination of the weight of ROI and Not-ROI,conversion algorithm of from the RGB color space to HSV color space,statistical clustering algorithm of the weighted color histogram,as well as the ultimate affective approach.Simulation results show that the model of the underlying characteristics of the realization of high-level affective semantic mapping accuracy than the traditional colors of the image feature extraction techniques to identify semantic model of emotion has greatly improved.

关 键 词：感兴趣区域 情感语义 颜色特征提取 颜色直方图 自组织映射 情感聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]