基于层次匹配下多种特征融合的蕾丝花边检索方法

A lace retrieval method based on hierarchical matching and multiple features

针对基于图像纹理特征的蕾丝花边检索方法效率低下问题,为提高蕾丝花边检索效率,提出一种基于层次匹配下多种特征融合的蕾丝花边检索方法。通过运用图像纹理特征标识图像,利用Canny算子处理纹理图像,得到彩色Canny图像及其灰度梯度共生矩阵GGCM,采用能量、梯度平均、灰度平均、相关等二次统计特征参数描述图像的纹理特征,将上述提取纹理特征结合形状特征和SURF特征进行逐层匹配,实现层次匹配下多种特征的融合,弥补单个匹配方法的不足,同时在蕾丝花边库中验证所提检索方法的正确率。实验结果表明,与其他匹配方法相比,该方法提取的纹理特征具有更强的纹理鉴别能力,能较好地实现蕾丝花边检索,有效地提高了检索方法的速率和准确率。

Since the efficiency of the lace retrieval method based on image texture features is low, and in order to extract the effective texture features for lace identification, we propose a lace retrieval algorithm containing multiple features fusion through hierarchical matching. Firstly, we process the texture image by the Canny operator and obtain the Canny color image and the gray level-gradient co-occurrence matrix （GGCM）. Secondly, energy, average gradient, average grayscale, correlation and other statistical characteristics are used for texture description. Finally, the extracted texture features are matched with geometry features and speeded up robust features （SURF） hierarchically, so the fusion of multiple features under hierarchical matching is realized to compensate for the deficiency of any single matching method and verify the correct rate of the retieval method used in the lace library. Experimental results indicate that the performance of the proposed method is better than other methods, which has a stronger ability of texture identification, and can achieve lace retrieval effectively and improve the reliability and accuracy of image retrieval.