基于主成分分析的图像显著性检测及应用

Image saliency detection based on principal component analysis and application

针对图像显著性检测这项重要的图像预处理技术,提出了一种基于主成分分析的显著性区域检测方法。首先,将每个像素与周围8领域点的均值作为其特征维度,采用主成分分析法对特征维度进行特征提取,计算其显著得分得到显著图,再将其应用于基于内容感知的图像缩放技术中。相比传统的缩放算法,该方法不仅能够保持图像在缩放过程中的重要内容,还保证了图像的完整概貌。与Seam Carving算法相比,该方法也理论简洁、运行高效。

A saliency region detection method based on principal component analysis(PCA)is proposed for image saliency detection,an important image preprocessing technology.First of all,the average value of each pixel and the points in the surrounding eight fields are taken as the feature dimension of the point,and the feature of each pixel is extracted by principal component analysis,and the saliency score is calculated to obtain the significant graph.Then the content-aware image scaling technique is applied.The experimental results show that this method can not only maintain the important content of images in the scaling process,but also guarantee the complete image summary compared with traditional scaling algorithms.Compared with Seam Carving algorithm,this method is concise and the operation is efficient.