基于变换域中的自适应纹理图像检索  

Adaptive texture image retrieval based on transform domain

作　　者：秦智康 张衡阳[1] QIN Zhi-kang;ZHANG Heng-yang(Information and Navigation College, Air Force Engineering University, Xi′an 710077, China)

机构地区：[1]空军工程大学信息与导航学院

出　　处：《液晶与显示》2020年第3期281-286,共6页Chinese Journal of Liquid Crystals and Displays

摘　　要：为了提升图像检索效率,本文提出了基于变换域的自适应纹理图像检索算法。该算法首先使用二维离散小波变换来减小测试图像和训练的图像的尺寸,并进一步在灰度共生矩阵应用2级分解图像的LL分量来进行训练和测试,从而提取图像的纹理特征。最后结合形状特征和颜色特征通过融合不同的距离分类器来检索相似的图像。为了提升算法的自适应能力,本文引入了交互式遗传算法来动态调整参数。实验结果表明,在训练迭代次数为30,60,100的情况下,本文算法的准确率达67%以上,在图像检索领域有较高的应用价值,具有性能稳定可靠、精度高等优点。In order to improve the efficiency of image retrieval,an adaptive texture image retrieval algorithm based on transform domain is proposed.The algorithm uses two-dimensional discrete wavelet transform to reduce the size of the test image and the trained image,and further applies the LL component of the 2-level decomposition image in the gray level co-occurrence matrix to train and test to extract the texture features of the image,and finally combine shape features and color features retrieve similar images by fusing different distance classifiers.In order to improve the adaptive ability of the algorithm,an interactive genetic algorithm is introduced to dynamically adjust the parameters.The experimental results show that the accuracy of the proposed algorithm is above 67%when the number of training iterations is 30,60,and 100.The algorithm has high application value in the field of image retrieval,and has the advantages of stable and reliable performance and high precision.

关 键 词：图像纹理 图像检索 二维离散小波变换 距离分类器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]