Download presentation
Presentation is loading. Please wait.
Published byMerryl Hardy Modified over 6 years ago
1
Image Compression Using An Adaptation of the ART Algorithm
Craig Weidert December 12, 2006 CS152 - Neural Networks
2
Background I would like to use neural networks to compress images.
Used 48 by 48 pixel 8-bit grayscale bitmaps Implemented in Python I tried two methods
3
Attempt #1 (Failure) Standard NN w/ Backprop Gameplan:
Train network on image Save weights of network Restore network, run through co-ordinates to restore image Inputs: x and y co-ordinates of pixels Desired Output: grayscale value of pixels Used two hidden 10 wide logsig layers
4
Results / Problems Difficulty in training Not very faithful
Took a long time Grayout problem Inconsistent Not very faithful Lower right hand corner
5
Attempt #2 (Relative Success)
Use scheme similar to k-means and adaptive resonance theory Gameplan: Use network to cluster pixels into “prototypes” based on position, color Save prototypes Load prototypes, for each pixel find closest prototype and use that color
6
Algorithm For each pixel in the image, create sample (x, y, c)
Iterate through samples If there are no prototypes, make one If there is a prototype within a tolerable distance of the sample, lump in w/ closest If all prototypes are far away, make new prototype Save the prototypes, truncating as necessary
7
Results Ran much faster
At the point where you could tolerate the error, often no longer compression However, achieved a very cool mosaic effect
10
Future Work Differing image sizes
Scalability questions Different comparisons for samples, prototypes Different weightings Different metrics (MSE)? Changing Algorithm entirely
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.