Jay Taylor's notes

back to listing index

Seam Carving for Content-Aware Image Resizing

[web search]
Original source (www.faculty.idc.ac.il)
Tags: image-processing seam-carving www.faculty.idc.ac.il
Clipped on: 2018-05-27

Seam Carving for Content-Aware Image Resizing

Shai Avidan        Ariel Shamir

Presented @ Image (Asset 1/38) alt= Effective resizing of images should not only use geometric constraints, but consider the image content as well. We present a simple image operator called seam carving that supports content-aware image resizing for both reduction and expansion. A seam is an optimal 8-connected path of pixels on a single image from top to bottom, or left to right, where optimality is defined by an image energy function. By repeatedly carving out or inserting seams in one direction we can change the aspect ratio of an image. By applying these operators in both directions we can retarget the image to a new size. The selection and order of seams protect the content of the image, as defined by the energy function. Seam carving can also be used for image content enhancement and object removal. We support various visual saliency measures for defining the energy of an image, and can also include user input to guide the process. By storing the order of seams in an image we create multi-size images, that are able to continuously change in real time to fit a given size.



Acrobat PDF (~19 mb)

QuickTime (~18 mb)

   author = {Shai Avidan and Ariel Shamir},
   title = {Seam carving for content-aware image resizing},
   journal = {ACM Trans. Graph.},
   volume = {26},
   number = {3},
   year = {2007},
   pages = {10},
   publisher = {ACM},

* This work is patented, owned by Mitsubishi Electric Research Labs, Cambridge MA


Click on an image to view it in actual size.

Aspect Ratio Change

Image (Asset 2/38) alt= Content Enhancement
Image (Asset 3/38) alt=