1 / 24

We are TEAM 01

We are TEAM 01. YI-HAN CHIANG Junior student PEI-YUN HSU Senior student HUI-YU LEE F irst-year graduated student. I ntroduction. Collage Collage photos into a frame Smart Automatically importance semantic meanings. Motivation - 1. Recent mobile apps. Motivation - 1. We want to

shaman
Télécharger la présentation

We are TEAM 01

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. We are TEAM 01 • YI-HAN CHIANG • Junior student • PEI-YUN HSU • Senior student • HUI-YU LEE • First-year graduated student

  2. Introduction • Collage • Collage photos into a frame • Smart • Automatically • importance • semantic meanings

  3. Motivation - 1 • Recent mobile apps

  4. Motivation - 1 • We want to • collage photos automatically! • Put into appropriate frames !

  5. Motivation - 2 • Too many photos to pick

  6. Motivation - 2 • We want to • Pick representative photos ! • Collage them !

  7. can… • Select photos • Fit the best template • Pick semantic combinations • Output result

  8. can… • Select photos • Fit the best template • Pick semantic combinations • Output result

  9. Select photosRemove similar photos • Color histogram feature (YIQ) • Randomly pick one

  10. Select photosChoose importance photos • score = 0.6*Num of People +0.2*mean_Value +0.2*mean_Saturation • Sort&Random

  11. can… • Select photos • Fit the best template • Pick semantic combinations • Output result

  12. Fit the best templateEnumerate templates • for each case (4 – 7 )

  13. Fit the best templateFit the best template 0.2 0.1 0.4 0.3 0.7 Sum = |2 – 0.7| + | 1 – 0.4| +| 1 – 0.3| + |3 – 0.2| +|2 – 0.1| Find the template who has min Sum. 2 3 2 1 1

  14. can… • Select photos • Fit the best template • Pick semantic combinations • Output result

  15. Pick semantic combinationsEnumerate combinations • for example

  16. Pick semantic combinationsGood looking? • Consider completeness • Sky on the top(grayscale) • Symmetric(balance human #)

  17. can… • Select photos • Fit the best template • Pick semantic combinations • Output result

  18. Output resultLive demo time

  19. Output resultexample 1 - NTU

  20. Output resultexample 2 – birthday time

  21. Output resultexample 3 – basketball time

  22. Q&A

  23. The end

More Related