作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2013, Vol. 39 ›› Issue (2): 233-236. doi: 10.3969/j.issn.1000-3428.2013.02.048

• 图形图像处理 • 上一篇    下一篇

结合LBP和Brushlet的自适应图像检索

杨晓慧 1,2,姚雪彦 1   

  1. (1. 河南大学数学与信息科学学院应用数学研究所,河南 开封 475004;2. 西安电子科技大学智能感知与图像理解教育部重点实验室,西安 710071)
  • 收稿日期:2011-11-23 修回日期:2012-01-26 出版日期:2013-02-15 发布日期:2013-02-13
  • 作者简介:杨晓慧(1978-),女,副教授,主研方向:图像检索,模式识别;姚雪彦,硕士研究生
  • 基金资助:
    国家自然科学基金资助项目(60802061);智能感知与图像理解教育部重点实验室开放基金资助项目“图像检索中相关反馈技术研究”(IPIU012011004)

Adaptive Image Retrieval Combined with LBP and Brushlet

YANG Xiao-hui 1,2, YAO Xue-yan 1   

  1. (1. Institute of Applied Mathematics, School of Mathematics and Information Sciences, Henan University, Kaifeng 475004, China; 2. Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education, Xidian University, Xi’an 710071, China)
  • Received:2011-11-23 Revised:2012-01-26 Online:2013-02-15 Published:2013-02-13

摘要: 针对时域和频域纹理特征的优点和互补性,提出一种结合局部二值模式(LBP)和Brushlet域系数统计特征的自适应纹理图像检索方法。利用Brushlet变换得到各个子带的能量作为频域特征,提取图像的LBP直方图作为空域特征,并采用改进的Canberra距离进行度量,使用闭环反馈实现图像的自适应检索。实验结果表明,与LBP方法和Brushlet方法相比,该方法的平均检索率分别提高8.93%和18.66%。

关键词: 图像检索, Brushlet变换, 局部二值模式, 闭环反馈, 空域特征, 变换域特征

Abstract: By considering advantages and complementary of spatial and frequency textures features, an adaptive texture image retrieval method is presented combined with Local Binary Pattern(LBP) feature and Brushlet domain coefficient statistical feature. Frequency feature is described as energy feature of every Brushlet subband. Spatial feature is LBP histogram. Similarity between images is measured by improved Canberra distance. Further, closed-loop feedback is introduced to adjust weights adaptively for image retrieval. Experimental results show that average recall rate of this method based on fused features is 8.93% and 18.66% higher than LBP method and Brushlet domain method respectively.

Key words: image retrieval, Brushlet transform, Local Binary Pattern(LBP), closed-loop feedback, spatial domain feature, transform domain feature

中图分类号: