1 / 32

Seam Carving for Content-aware Image Resizing

Seam Carving for Content-aware Image Resizing. 資訊碩一 10077034 蔡勇儀 Date : 2012/01/03 @LAB 603. Outline. Introduction Basic Theory Application & Implementation Aspect Ratio Change Retargeting with Optimal Seams-Order Enlarging Content Amplification

bryony
Télécharger la présentation

Seam Carving for Content-aware Image Resizing

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Seam Carving for Content-aware Image Resizing 資訊碩一 10077034 蔡勇儀 Date:2012/01/03 @LAB 603

  2. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  3. Introduction(1/2) • Muti-Media and Embedding System(e.g.Cell Phone) grow fast,Resize or Multi-Size scalingare more important than past. • Standard image scaling is not sufficient since it is oblivious to the image content and typically can be applied only uniformly. • For improve the problem, many researcher prove some good idea.

  4. Introduction(2/2) • The following is main methods for scaling: • Corp (figure2(b)) • Column orRow removal (figure2(c)) • Pixel energy removal (figure2(e)) • Optimal Pixel energy removal (figure2(f)) • Object detection • Seam Craving (figure2(d)) • We can found the seam method have better result!

  5. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  6. Basic Theory • Step1 – Find seam • Find a path which have the minimum energy sum from image top to bottom. • Step2 – Remove the Min. seam • When found all seam, select the Min. seam remove. • Step3 – Repeat above step until get the demand size

  7. Basic Theory – Step1 • Give an energy function • Define Seam • Define the Seam Cost

  8. Basic Theory – Step2 • Find the minimum seam • Remove S* form image and lnsteadof neighbors

  9. Basic Theory – Step3 • Repeat above step until get the demand size

  10. Basic Theory – Energy Function • What’s energy function is the best? • e1 • Entropy • 9*9 Windows add to e1 • Segmentation ( add to e1) • Histogram of Gradients • 11*11cell around a pixel, 8-bins

  11. Basic Theory – Energy Function • They all accommodate a similar range for resizing. • We found either e1 or eHoG to work quite well.

  12. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  13. Aspect Ratio Change • Only one axis adjust • A picture size n*m  n*m’ or n’*m • n >= n’ m >= m’ • Remove n-n’ or m-m’ seams • Enlarge at other page

  14. Retarget with Optimal Seam-Order(1/3) • What’s the optimal order for remove seams? Column or Row or Other? How could decide? • Using dynamic programming • where k = r+c, c = (m−m’), r = (n−n’) • αi is used as a parameter • that determine if at step i we remove a horizontal or vertical seam:

  15. Retarget with Optimal Seam-Order(2/3) • Define transport map T • T(r,c)=min(T(r-1,c)+E(sy(In-r+1*m-c)), T(r,c-1)+E(sx(In-r*m-c+1)) ) • where In-r*m-c • denotes an image of size (n−r)×(m−c), • E(sx(I)) and E(sy(I)) • are the cost of the respective seam removal operation. • Build the 1 bit map for record the direction

  16. Retarget with Optimal Seam-Order(3/3)

  17. Enlarge(1/3) • When m’ > m or n’ > n, we should insert seams to the picture. • Find the smallest energy seam for copy and insert, repeat until equal the demand scale. • But…

  18. Enlarge(2/3) • Every time found the same seam, so we should decide all seams which need copy at first. • If m’ > m then we need insert (m’-m) seams. Find them and copy it for insertation.

  19. Enlarge(3/3) The origin picture Scalar Seam

  20. Content Amplification • Using same scalar enlarge then use seams-carving for recover to the origin size.

  21. Seam Carving in the gradient domain • If energy funciton use the gradient, then color show at remove place will be more nature after seam carving.

  22. Object remove • User mark the part which want to remove. • Decrease the energy on the part is removed. • Insert seams for keeping origin size.

  23. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  24. Multi-size Images(1/3) • User want find the optimal picture scalar for their demand, so we need the real time opreation. • But the picture’s size 400*500 to 100*100 in about 2.2 seconds, it is too long to real time. How could do for real time?

  25. Multi-size Images(2/3) • Make the index map for seams before user operation. • Build the horizontal & vertical index map (H&V) • But there will a big problem for operation that is H & V will be collided. • The sample solution is decide one just do one direction and then other direction need degenerate the index and redo the select seams operation

  26. Multi-size Images(3/3)

  27. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  28. Limitation(1/2) • this method • does not work automatically on all images. • can be corrected by adding higher level cues, either manual or automatic. Figure 14, Figure 15 • Other times, • not even high level information can solve the problem. • two major factors that limit this seam carving approach. • The first • is the amount of content in an image. • If the image is too condensed, • it does not contain ‘less important’ areas, • then any type of content-aware resizing strategy will not succeed. • The second type of limitation • is the layout of the image content. • In certain types of images, albeit not being condensed,the content is laid out in a manner that prevents the seams to bypass important

  29. Limitation(2/2)

  30. Outline • Introduction • Basic Theory • Application & Implementation • Aspect Ratio Change • Retargeting with Optimal Seams-Order • Enlarging • Content Amplification • Seam Carving in the gradient domain • Object Removal • Multi-size Images • Limitation • Conclusions and Future Work

  31. Conclusions and Future Work • to extend this approach to other domains, • the first of which would be resizing of video. • Since there are cases • when scaling can achieve better results for resizing, • would like to investigate the possibility • to combine the two approaches, • Specifically to define more robust multi-size images. • would also like to find a better way • to combine horizontal and vertical seams in multi-size images.

  32. Thank for your listening • Q&A

More Related