融合主曲率与颜色信息的彩色图像检索算法  

Color Image Retrieval Method Fusing Principal Curvature and Color Information

作　　者：程德强 张皓翔 江曼 寇旗旗 Cheng Deqiang;Zhang Haoxiang;Jiang Man;Kou Qiqi(Engineering Research Center of Intelligent Control of Underground Space,Ministry of Education,Xuzhou 221116;School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221116;School of Computer Science and Technology,China University of Mining and Technology,Xuzhou 221116)

机构地区：[1]地下空间智能控制教育部工程研究中心,徐州221116 [2]中国矿业大学信息与控制工程学院,徐州221116 [3]中国矿业大学计算机科学与技术学院,徐州221116

出　　处：《计算机辅助设计与图形学学报》2021年第2期223-231,共9页Journal of Computer-Aided Design & Computer Graphics

基　　金：国家自然科学基金(51774281);国家重点研发计划(2018YFC0808302).

摘　　要：针对当前图像检索算法存在特征维度高、检索耗时久、精度低等问题,提出一种基于颜色信息和纹理信息相融合的图像检索算法.首先对彩色图像进行颜色量化和统计以获取其颜色直方图,利用海森矩阵提取彩色图像的表面几何结构曲率信息,并根据提取的曲率信息构建方向梯度加权联合直方图;然后对获得的颜色直方图和加权联合方向梯度直方图进行融合,得到最终检索结果.与其他算法在Corel-1k,FTVL和COIL-100数据库上的实验结果表明,该算法具有精度高、维度低的优点.Aiming at the problems of high feature dimensionality,long retrieval time,and low precision of existing algorithms in image retrieval system,an image retrieval algorithm based on the fusion of color information and texture information is proposed.Firstly,the color image is quantized and counted to obtain color histogram.Secondly,the Hessian matrix is used to extract curvature information of the color image,and the weighted joint histogram of oriented gradient based on curvature information is constructed.Then,the obtained color histogram and histogram of oriented gradient are fused to obtain the final joint histogram.And the experimental results on the Corel-1k,FTVL,and COIL-100 datasets show that the proposed algorithm has the advantages of high precision and low dimensionality.

关 键 词：图像检索 颜色直方图 几何结构曲率信息 加权联合直方图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]