arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1612.02493cs.CV
收藏

基于纹理特征和粗糙集理论的多特征融合图像检索算法研究

Research on the Multiple Feature Fusion Image Retrieval Algorithm based on Texture Feature and Rough Set Theory

East China Normal University(华东师范大学);Dickinson College(狄金森学院)

Xiaojie Shi, Yijun Shao

摘要:

最近,我们目睹了具有复杂信息和内容的图像的爆炸性增长。为了从大规模图像数据库中高效、准确地检索出所需图像,提出了一种基于纹理特征和粗糙集理论的多特征融合图像检索算法。与传统的只使用单一特征或标准的方法不同,我们通过归一化操作融合不同的特征。粗糙集理论将有助于提高检索系统面对不完备数据仓库的鲁棒性。为了增强纹理提取的范例,我们使用小波Gabor函数,具有更好的鲁棒性。此外,从内、外归一化的角度,对提取的特征进行了重新组织,使其具有更好的组合。数值实验验证了该方法的可行性。与其他最先进的算法相比,我们提高了整体的准确性。

英文摘要:

Recently, we have witnessed the explosive growth of images with complex information and content. In order to effectively and precisely retrieve desired images from a large-scale image database with low time-consuming, we propose the multiple feature fusion image retrieval algorithm based on the texture feature and rough set theory in this paper. In contrast to the conventional approaches that only use the single feature or standard, we fuse the different features with operation of normalization. The rough set theory will assist us to enhance the robustness of retrieval system when facing with incomplete data warehouse. To enhance the texture extraction paradigm, we use the wavelet Gabor function that holds better robustness. In addition, from the perspectives of the internal and external normalization, we re-organize extracted feature with the better combination. The numerical experiment has verified general feasibility of our methodology. We enhance the overall accuracy compared with the other state-of-the-art algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑