This paper presents an automatic visual salience preserving content-aware image resizing method for image representation. The method computes a saliency map which describes the attractive regions in an image by the saliency-based visual attention model and a segmented image which consists of uniform color regions performed by the mean shift algorithm. Then a thresholding technique is applied to detect important target regions on the saliency map. These regions combined with the segmentation results construct the important joint regions. The method uses cropping and seam carving strategies to resize the image to its target size. Experimental results show that the proposed image resizing method is capable of preserving important target without deformation.
