AI Article Synopsis
- Natural images are intricate yet structured, and mammalian neocortex learns to encode them efficiently despite their complexity.
- A multiscaling approach is discussed, which leads to a redundancy-reducing wavelet basis optimal for image coding and learned directly from data.
- The introduction of oriented wavelets is essential for a comprehensive description of images, highlighting their function as edge detectors.
Article Abstract
Natural images are complex but very structured objects and, in spite of its complexity, the sensory areas in the neocortex in mammals are able to devise learned strategies to encode them efficiently. How is this goal achieved? In this paper, we will discuss the multiscaling approach, which has been recently used to derive a redundancy reducing wavelet basis. This kind of representation can be statistically learned from the data and is optimally adapted for image coding; besides, it presents some remarkable features found in the visual pathway. We will show that the introduction of oriented wavelets is necessary to provide a complete description, which stresses the role of the wavelets as edge detectors.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/s0042-6989(03)00012-9 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!