基于变换域的显著性提取

Saliency Detection Based on Transform Domain

为增强图像显著特征的可靠性和鲁棒性,增加图像描述的准确度,提出了一种利用离散余弦变换(DCT:Discrete Cosine Transform)和Renyi熵提取自然图像显著性的方法。该方法充分利用了图像的频域信息,通过MSRA1000图像数据库进行性能测试。实验结果表明,该方法优于5种经典算法,提高了显著性检测的有效性。

In order to enhance the reliability and robustness of the image characteristic and increase the accuracy of the image description, the paper proposes a method which using DCT （Discrete Cosine Transform） and Renyi entropy extracts the saliency of natural images, it makes full use of the frequency information. Through the performance test of MSRA1000 image database, the results show that this method has good performance and is better than five classical algorithms on a number of indicators, which can effectively meet the requirements of significant testing.