Abstract
This paper reviews key attributes of neural processing essential to intelligent multimedia processing (IMP). The objective is to show why neural nertvorks (NN's) are a core technology for the following multimedia functionalities: I) efficient representations for audio/visual information, 2) detection and classification techniques, 3) fusion of inultimodal signals, and 4) multimodal conversion and synchronization. It also demonstrates how the adaptive NN technology presents a unified solution to a broad spectrum of multimedia applications. As substantiating evidence, representative examples where NN's are successfully applied to IMP applications are highlighted. The examples cover a broad range, including image visualization, tracking of moving objects, image/video segmentation, texture classification, face-object detection/recognition, audio classification, inultimodal recognition, and inultimodal lip reading.
Original language | English (US) |
---|---|
Pages (from-to) | 1244-1271 |
Number of pages | 28 |
Journal | Proceedings of the IEEE |
Volume | 86 |
Issue number | 6 |
DOIs | |
State | Published - 1998 |
All Science Journal Classification (ASJC) codes
- General Computer Science
- Electrical and Electronic Engineering
Keywords
- ACON/OCON nehvorks
- Access-control security
- Active contour model
- Adaptive expectation-maximization
- Audio classification
- Audio-to-visual conversion
- Audio/visual fusion
- Decision-based neural network
- Face recognition