Say i have 2 grayscale images.
IMAGE 1: 2 objects
IMAGE 2: 1 object
Now I have worked out the position of the objects.
How could i check in image2 whether any of the objects have been seen in image1?
Printable View
Say i have 2 grayscale images.
IMAGE 1: 2 objects
IMAGE 2: 1 object
Now I have worked out the position of the objects.
How could i check in image2 whether any of the objects have been seen in image1?
Classify the objects in Image 1, and keep a time/pattern history of the objects seen.
What do you mean by that? What pattern? and by time do you mean position?
Image ClassificationQuote:
Originally Posted by taurus
Keep track of the objects you have seen in Image 1 and the time they were seen.
After a set time limit discard the records.
For each object seen in Image 2, check the list of objects seen in Image 1 for matches.
How would you use a histogram to compare objects?
Maybe you need associative memory, it is very cool, similar to "handwriten letter recognizing system" that I built...?
Could be interesting, Do you have a simple version I could implement?
You need to fix your signature, more than about 3-5 lines is considered spammy. I's actually so bad it makes your post difficult to read.Quote:
Originally Posted by yann
Quote:
If all you know how to use is a hammer, every problem looks like a nail.
That depends on what data the histogram is mapping and how you want to compare the two. I wouldn't suggest a histogram for the problem you posted though, suggest a FIFO queue that keeps track of the objects seen in each picture over time. Keep separate lists for each picture, and compare the two lists to see if an object in picture 1 is latter seen in picture two, or if it was in picture 2 first.Quote:
Originally Posted by taurus
Yes, but with associative memory you could even compare two objects if they were rotated ^^, ANYTHING you want.
COuld you explain how I can do it then Yann please?
perceptrons cannot do that yann. Stop preaching hype that you read on some web page and perhaps pick up a serious text on the subject, here are some of the ones in my library that I found useful -Quote:
Originally Posted by yann
Artificial Intelligence, A Modern Approach ISBN 0-13-790395-2
Neural Networks, A Comprehensive Foundation, ISBN 0-13-273350-1
Neural Networks for Pattern Recognition, ISBN 978-0-19-853864-6
Biophysics of Computation, Information porcessing in single neurons, ISBN 978-0-19-518199-9
Theoretical Neuroscience, Computational and Mathematical Modelling of Neural Systems, ISBN 978-0-262-54185-5
C++ Neural Networks & Fuzzy Logic, ISBN 1-55851-552-6
Whops, sorry
so i could still do with a simple basic idea to compare two objects?
You should really post some kind of warning when you include terrible images in your threads.
Quzah.
Put a shirt on abachler :eek:
You should post your address so we can send you some clothes. Jeez. :p
Haha, is this some kind of warning that perceptrons will turn me into a lunatic? :D
I read about statistical pattern recognition but not sure how to perform it to compare images
I also have several images.
-------------------------------------
Please contact me.
[email protected]
[email protected]
[email protected]
[email protected]
[email protected]
Wearing a shirt with no pants is a fashion faux pa.Quote:
Originally Posted by Dae
It is otherwise known as wearing a very short dress.Quote:
Originally Posted by abachler
But ask yourself, do you really want to see pictures of me wearing a dress :DQuote:
Originally Posted by laserlight
Not the correct forum but i used matlab for a robotics problem similar to the one you are having
its image processing package would do the trick