Abstract
Image compression using neural networks has been attempted with some promise. Among the architectures, feedforward backpropagation networks (FFBPN) have been used in several attempts. We propose an architecture and an improved training method to attempt to solve the shortcomings of traditional data compression based on feedforward networks - the dynamic autoassociation neural network (DANN). The results of several tasks presented to DANN based compression are compared with the performance of FFBPN based system. These results indicate that DANN is superior to FFBPN for data compression.
| Original language | English |
|---|---|
| Title of host publication | Intelligent Engineering Systems Through Artificial Neural Networks |
| Editors | C.H. Dagli, L.I. Burke, Y.C. Shin |
| Place of Publication | Fairfield, NJ, United States |
| Publisher | ASME |
| Pages | 503-510 |
| Number of pages | 8 |
| Volume | 2 |
| State | Published - Dec 1 1992 |
| Event | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 - St.Louis, MO, USA Duration: Nov 15 1992 → Nov 18 1992 |
Other
| Other | Proceedings of the 1992 Artificial Neural Networks in Engineering, ANNIE'92 |
|---|---|
| City | St.Louis, MO, USA |
| Period | 11/15/92 → 11/18/92 |
Fingerprint
ASJC Scopus subject areas
- Software
Cite this
Image compression with a dynamic autoassociative neural network. / Rios, Andres; Kabuka, Mansur R.
Intelligent Engineering Systems Through Artificial Neural Networks. ed. / C.H. Dagli; L.I. Burke; Y.C. Shin. Vol. 2 Fairfield, NJ, United States : ASME, 1992. p. 503-510.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Image compression with a dynamic autoassociative neural network
AU - Rios, Andres
AU - Kabuka, Mansur R.
PY - 1992/12/1
Y1 - 1992/12/1
N2 - Image compression using neural networks has been attempted with some promise. Among the architectures, feedforward backpropagation networks (FFBPN) have been used in several attempts. We propose an architecture and an improved training method to attempt to solve the shortcomings of traditional data compression based on feedforward networks - the dynamic autoassociation neural network (DANN). The results of several tasks presented to DANN based compression are compared with the performance of FFBPN based system. These results indicate that DANN is superior to FFBPN for data compression.
AB - Image compression using neural networks has been attempted with some promise. Among the architectures, feedforward backpropagation networks (FFBPN) have been used in several attempts. We propose an architecture and an improved training method to attempt to solve the shortcomings of traditional data compression based on feedforward networks - the dynamic autoassociation neural network (DANN). The results of several tasks presented to DANN based compression are compared with the performance of FFBPN based system. These results indicate that DANN is superior to FFBPN for data compression.
UR - http://www.scopus.com/inward/record.url?scp=0027105465&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027105465&partnerID=8YFLogxK
M3 - Conference contribution
VL - 2
SP - 503
EP - 510
BT - Intelligent Engineering Systems Through Artificial Neural Networks
A2 - Dagli, C.H.
A2 - Burke, L.I.
A2 - Shin, Y.C.
PB - ASME
CY - Fairfield, NJ, United States
ER -