we are team 01
DESCRIPTION
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 - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/1.jpg)
![Page 2: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/2.jpg)
We are TEAM 01
• YI-HAN CHIANG– Junior student
• PEI-YUN HSU – Senior student
• HUI-YU LEE– First-year graduated student
![Page 3: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/3.jpg)
• Collage– Collage photos into a frame
• Smart– Automatically– importance– semantic meanings
Introduction
![Page 4: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/4.jpg)
Motivation - 1
• Recent mobile apps–
![Page 5: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/5.jpg)
Motivation - 1
• We want to – collage photos automatically !– Put into appropriate frames !
![Page 6: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/6.jpg)
Motivation - 2
• Too many photos to pick
![Page 7: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/7.jpg)
Motivation - 2
• We want to – Pick representative photos !– Collage them !
![Page 8: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/8.jpg)
can…
• Select photos• Fit the best template • Pick semantic combinations• Output result
![Page 9: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/9.jpg)
can…
• Select photos• Fit the best template • Pick semantic combinations• Output result
![Page 10: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/10.jpg)
Select photos
Remove similar photos• Color histogram feature (YIQ)• Randomly pick one
![Page 11: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/11.jpg)
Select photos
Choose importance photos
• score = 0.6*Num of People+0.2*mean_Value+0.2*mean_Saturation
• Sort & Random
![Page 12: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/12.jpg)
can…
• Select photos• Fit the best template • Pick semantic combinations• Output result
![Page 13: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/13.jpg)
Fit the best template
Enumerate templates• for each case (4 – 7 )
![Page 14: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/14.jpg)
Fit the best template
Fit the best template
Sum = |2 – 0.7| + | 1 – 0.4| +| 1 – 0.3| + |3 – 0.2|
+|2 – 0.1|
Find the template who has min Sum.
32
21
1
0.7 0.4 0.3 0.2 0.1
![Page 15: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/15.jpg)
can…
• Select photos• Fit the best template • Pick semantic combinations• Output result
![Page 16: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/16.jpg)
Pick semantic combinations
Enumerate combinations• for example
![Page 17: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/17.jpg)
Pick semantic combinations
Good looking?• Consider completeness– Sky on the top (grayscale)– Symmetric (balance human #)
![Page 18: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/18.jpg)
can…
• Select photos• Fit the best template • Pick semantic combinations• Output result
![Page 19: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/19.jpg)
Output result
Live demo time
![Page 20: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/20.jpg)
Output result
example 1 - NTU
![Page 21: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/21.jpg)
Output result
example 2 – birthday time
![Page 22: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/22.jpg)
Output result
example 3 – basketball time
![Page 23: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/23.jpg)
Q&A
![Page 24: We are TEAM 01](https://reader035.vdocuments.pub/reader035/viewer/2022070407/56814327550346895daf96f9/html5/thumbnails/24.jpg)
The end