基于显着性加权颜色和纹理的图像检索-南京航空航天大学理学院.pdf

基于显著性加权颜色和纹理的图像检索 1 1 2 3 邹国平 ，马儒宁 ，丁军娣 ，钟宝江 （1.南京航空航天大学理学院，江苏 南京 211100；2.南京理工大学计算机科学与技术学院，江苏 南京 210094；3.苏州大学 计算机科学与技术学院，江苏 苏州 215006） 摘要：显著性体现了图像中像素区域引起视觉注意的强弱程度,在图像检索中具有重要意义。本文提出的基于显著性加权的图像 检索方法不需要分割出显著性区域，而以显著性加权的方式建立了新的颜色特征和纹理特征，从而增加了显著性区域的颜色与 纹理特征的权重。通过对 4 种主要的显著图的实验比较发现该方法能有效地提高检索效果。 关键词：图像检索，显著性，颜色直方图，LBP 直方图 中图法分类号：TP391 文献标识码：A Image retrieval based on saliency weighted color and texture 1 1 2 3 ZOU Guo-ping MA Ru-ning DING Jun-di ZHONG Bao-jiang ( 1.College of Science, Nanjing University of Aeronautics and Astronautics, Nanjing 211100, Jiangsu,China;2. School of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094 Jiangsu,China;3. School of Computer Science Technology, Soochow University, Suzhou 215006,Jiangsu,China) Abstract The term `saliency that indicates the visual importance of pixels in an image has a significant effect in content-based image retrieval. A new image retrieval method was presented by exploring the saliency-weighted image features of color and texture ,which did not require to segment those salient regions from images, but only to weigh the original features of color and texture by saliency of pixels. In such a way, the color and texture features of salient regions were naturally enhanced. Four popular saliency maps on images were mainly tested and the experimental results showed the effectiveness of our method with higher retrieval accurac