Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Cellular Edge Detection
Search
Kath
October 25, 2017
0
43
Cellular Edge Detection
Kath
October 25, 2017
Tweet
Share
More Decks by Kath
See All by Kath
Inn Lab
kathsaz
0
54
Click & Collect
kathsaz
0
37
Foodie.me
kathsaz
0
37
Innovation Lab
kathsaz
0
35
Innovation Lab
kathsaz
0
57
Design Thinking
kathsaz
0
51
Innovation Lab
kathsaz
0
96
Smart Campus - Re-imagining the user experience
kathsaz
0
54
Big Data
kathsaz
0
46
Featured
See All Featured
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Code Reviewing Like a Champion
maltzj
524
40k
Reflections from 52 weeks, 52 projects
jeffersonlam
351
20k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
138
34k
Gamification - CAS2011
davidbonilla
81
5.4k
Code Review Best Practice
trishagee
69
19k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.3k
A better future with KSS
kneath
238
17k
Statistics for Hackers
jakevdp
799
220k
Designing Experiences People Love
moore
142
24k
Site-Speed That Sticks
csswizardry
10
690
Transcript
CELLULAR EDGE DETECTION FOR GRAYSCALE & BINARY IMAGES
None
None
CELLULAR AUTOMATON BINARY IMAGE
CELLULAR AUTOMATON GREYSCALE IMAGE
LEARNING AUTOMATON Von-neumann Moore
50% 50% LEARNING AUTOMATON Von-neumann Moore
10% 90% LEARNING AUTOMATON Von-neumann Moore
None
1200x800 Original 1200x800 Output image Cellular automata 1200x800 Learning automata
1200x800
1200x800 Output image Cellular automata 1200x800 Learning automata 1200x800 ..update
output image every generation Execute rules for N generations..
Final 1200x800 1200x800 Output image
EXPERIMENTS
None
None
CED CANNY PREWITT
None
CED CANNY PREWITT
CED CANNY PREWITT MSE PSNR (dB) MSE PSNR (dB) MSE
PSNR (dB) 1.368 6.8011 1.369 6.8075 1.367 6. 8017 3.493 6.7320 3.491 6.7346 3.488 6.7382 1.804 5.6016 1.802 5.6056 1.800 5.6120
LIMITATIONS
Manual adjustment of threshold Defeats the purpose (maybe) Slow for
big images
None
SUPPORTING SLIDES
Pseudocode
Reinforcement signal