Please use this identifier to cite or link to this item:
|Title:||Image compression using a feedforward neural network|
|Authors:||Setiono, Rudy |
|Source:||Setiono, Rudy,Lu, Guojun (1994). Image compression using a feedforward neural network. IEEE International Conference on Neural Networks - Conference Proceedings 7 : 4761-4765. ScholarBank@NUS Repository.|
|Abstract:||We present an image compression technique using a feedforward neural network. The neural network has three layers: one input layer, one hidden layer and one output layer. The inputs of the neural network are original image data, while the outputs are reconstructed image data which are close to the inputs. If the amount of data required to store the hidden unit values and the connection weights to the output layer of the neural network is less than the original data, compression is achieved. In our experiments, we achieved a compression ratio of about 10 with good reconstructed image quality. The neural network construction algorithm we used has an attractive feature that each addition of a hidden unit to the network will always improve the image quality. Thus our compression scheme is flexible in the sense that the user can trade between image quality and compression ratio depending on the application requirements.|
|Source Title:||IEEE International Conference on Neural Networks - Conference Proceedings|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Mar 9, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.