Author Topic: image detection at different brightness  (Read 202 times)

yotamarker

  • *******
  • Starship Trooper
  • Posts: 370
image detection at different brightness
« on: February 13, 2017, 01:51:28 PM »
darker image would produce more outline pixel
so my questions is for the case of 2 exact images with one brighter and one darker
how do you make the program know they are the same ?

LOCKSUIT

  • *********
  • Terminator
  • Posts: 792
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: image detection at different brightness
« Reply #1 on: February 13, 2017, 03:59:03 PM »
You can duplicate the input image, and then make each one a different brightness to see which will match the suspected memory image.

Or you can develop a really good Pattern Recognizer.

What about when your girlfriend takes your favorite anime picture, draws on it, makes it black and white, thresholds it, brightens it, rotates it, diaganolly stretches it, switches spectrum colors, shrinks it, blurs it, adds motion blur, and FLIPSSSSSSSS IT? you still recognize it

Anyone wanna do this to eachothers favorite picture and see if you recognize it as your favorite picture OR as the fake image?

yotamarker

  • *******
  • Starship Trooper
  • Posts: 370
Re: image detection at different brightness
« Reply #2 on: February 13, 2017, 05:44:25 PM »
if it is being destroyed you can track it so you know it was the same
but I'm talking about 2 same images the darker it gets the more outline pixels pop out.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 370
Re: image detection at different brightness
« Reply #3 on: February 13, 2017, 05:45:53 PM »
and how can I make the duplicate brighter ? the brightness comes from outside the sun
the light bulb.

gigidi

LOCKSUIT

  • *********
  • Terminator
  • Posts: 792
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: image detection at different brightness
« Reply #4 on: February 13, 2017, 05:50:31 PM »
In an image editor you can make the picture brighter/ darker.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 370
Re: image detection at different brightness
« Reply #5 on: February 13, 2017, 08:33:14 PM »
I tried something similar I tried to increase the threshold of the outline
pixels in D darker images  but I didn't know by how much to do it
so the images didn't match they got closer in similarity but no match.

gigidi gigidi goo

LOCKSUIT

  • *********
  • Terminator
  • Posts: 792
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: image detection at different brightness
« Reply #6 on: February 13, 2017, 09:06:32 PM »
You can do the like 20 things (I mentioned some) BUT just a bit not too much, and still recognize it after all that!

yotamarker

  • *******
  • Starship Trooper
  • Posts: 370
Re: image detection at different brightness
« Reply #7 on: February 14, 2017, 05:52:20 AM »
what 20 things ? link please

Don Patrick

  • *
  • Starship Trooper
  • *******
  • Posts: 369
    • Artificial Detective
Re: image detection at different brightness
« Reply #8 on: February 14, 2017, 01:48:29 PM »
If you convert the RGB values to HSV values (Hue-Saturation-Brightness), you can compare the hue and saturation values of the pixels and ignore the brightness.
Personal project: NLP -> learning -> knowledge -> logical inference -> A.I.

LOCKSUIT

  • *********
  • Terminator
  • Posts: 792
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: image detection at different brightness
« Reply #9 on: February 14, 2017, 05:28:21 PM »
20 things:

hue
saturate
brighten
adjust levels
threshold
contrast
black n white
opacity
cross-fade
collage
scribble-on
rotate
translate
diagonally stretch
scale
flip
burn
highlight edges
highlight regions
relief them
outline
adjust curves
weight
angle
pull
invert colors
add noise
median
glow
sharpen
add blur
add motion blur
fragment
radial blur
Gaussian blur
zoom blur
zoom
surface blur
unfocus
crystallize
dents
ink sketch
oil painting
pencil sketch
twist
polar inversion
posterize
frosted glass
bulge
pixelate
sepia
SUPER RESOLUTION

BONUS: 3D-IZE IT WITH A 3D MOMA ON A BACKGROUND PLANE SEPIA-ED, FILM IT, AND COMBINE FRAMES FOR CLEAREST IMAGE!

 

Welcome

Please login or register.



Login with username, password and session length
Friday Funny
by kei10 (General Chat)
Today at 02:54:18 AM
mini a.i puzzles
by Freddy (General AI Discussion)
February 26, 2017, 09:01:05 PM
How to Predict Stock Prices Easily - Intro to Deep Learning #7 Siraj Raval
by keghn (General AI Discussion)
February 26, 2017, 04:21:26 PM
trivia questions
by yotamarker (General AI Discussion)
February 26, 2017, 03:05:54 PM
Life
by Art (AI in Film and Literature.)
February 26, 2017, 03:14:36 AM
Robot Message in a Bottle
by 8pla.net (Home Made Robots)
February 25, 2017, 04:04:21 AM
La-Masterpiece
by LOCKSUIT (Graphics)
February 24, 2017, 10:26:32 PM
Auto-Food-Drone type delivery
by Art (General Chat)
February 24, 2017, 06:52:28 PM
Robust bipedal Cassie to transform robot mobility
by Tyler (Robotics News)
February 24, 2017, 04:48:44 PM
Artificial intelligence: Understanding how machines learn
by Tyler (Robotics News)
February 24, 2017, 10:49:13 AM
Hard at work: A review of the Laevo Exoskeleton
by Tyler (Robotics News)
February 23, 2017, 04:48:12 PM
Shell Ocean Discovery XPRIZE: Semi-finalists set sail on a journey to illuminate the ocean
by Tyler (Robotics News)
February 22, 2017, 10:48:25 PM
Drones for good 2.0: How WeRobotics is redefining the use of unmanned systems in developing countries
by Tyler (Robotics News)
February 22, 2017, 04:48:07 PM
At what point should an intelligent machine be considered a person?
by Tyler (Robotics News)
February 22, 2017, 10:48:24 AM
Ocado evaluating robotic manipulation for online shopping orders
by Tyler (Robotics News)
February 21, 2017, 10:50:46 PM
Motor control systems: Bode plots and stability
by Tyler (Robotics News)
February 21, 2017, 04:48:52 PM

Users Online

20 Guests, 0 Users

Most Online Today: 33. Most Online Ever: 208 (August 27, 2008, 08:24:30 AM)

Articles