Feature space optimization for content-based image retrieval
Feature space optimization for content-based image retrieval
复制标题
基于内容的图像检索的特征空间优化
DOI：
10.1145/2387358.2387359
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
C. Traina
中科院分区：
文献类型：
--
作者：
Letricia P. S. Avalhais;Sérgio F Da Silva;J. F. Rodrigues;A. Traina;C. Traina
在基于内容的图像检索中，有效的相关反馈技术可以带来很大的好处。然而，现有技术由于计算成本和/或由于被限制为对数据的线性变换而受到限制。在这项研究中，我们分析了非线性变换在相关反馈中的作用。我们提出了两个有前途的相关反馈方法的基础上遗传算法用于提高性能的图像检索任务，根据用户的兴趣。第一种方法通过加权函数调整相异性函数，第二种方法通过线性和非线性变换函数重新定义特征空间。在真实的数据集上的实验结果表明，该方法是有效的，结果表明，转换方法优于加权方法，实现了高达70%的精度增益。我们的研究结果表明，非线性变换有很大的潜力，在捕捉用户的兴趣在图像检索，并应进一步分析采用其他学习/优化机制。
Substantial benefits can be gained from effective Relevance Feedback techniques in content-based image retrieval. However, existing techniques are limited due to computational cost and/or by being restricted to linear transformations on the data. In this study we analyze the role of nonlinear transformations in relevance feedback. We present two promising Relevance Feedback methods based on Genetic Algorithms used to enhance the performance on the task of image retrieval according to the user's interests. The first method adjusts the dissimilarity function by using weighting functions while the second method redefines the features space by means of linear and nonlinear transformation functions. Experimental results on real data sets demonstrate that our methods are effective and the results show that the transformation approach outperforms the weighting approach, achieving a precision gain of up to 70%. Our results indicate that nonlinear transformations have a great potential in capturing the user's interests in image retrieval and should be further analyzed employing other learning/optimization mechanisms.