Seam Carving for ContentAware Image Resizing （Seam雕刻ContentAware图像缩放）.pdfVIP

Seam Carving for Content-Aware Image Resizing Shai Avidan Ariel Shamir Mitsubishi Electric Research Labs The Interdisciplinary Center MERL Figure 1: A seam is a connected path of low energy pixels in an image. On the left is the original image with one horizontal and one vertical seam. In the middle the energy function used in this example is shown (the magnitude of the gradient), along with the vertical and horizontal path maps used to calculate the seams. By automatically carving out seams to reduce image size, and inserting seams to extend it, we achieve content-aware resizing. The example on the top right shows our result of extending in one dimension and reducing in the other, compared to standard scaling on the bottom right. Abstract 1 Introduction Effective resizing of images should not only use geometric con- The diversity and versatility of display devices today imposes new straints, but consider the image content as well. We present a sim- demands on digital media. For instance, designers must create dif- ple image operator called seam carving that supports content-aware ferent alternatives for web-content and design different layouts for image resizing for both reduction and expansion. A seam is an op- different devices. Moreover, HTML, as well as other standards, can timal 8-connected path of pixels on a single image from top to bot- support dynamic changes of page layout and text. Nevertheless, up tom, or left to right, where optimality is defined by an image energy to date, images, although being one of the key elements in digital function. By repeatedly carving out or inserting seams in one direc- media, typically remain rigid in size and cannot deform to fit differ-