Image Wavelet Decomposition and Applications

Loading...
Thumbnail Image
Penn collection
Technical Reports (CIS)
General Robotics, Automation, Sensing and Perception Laboratory
Degree type
Discipline
Subject
GRASP
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Treil, Nicolas
Mallat, Stephane
Bajcsy, Ruzena
Contributor
Abstract

The general problem of computer vision has been investigated for more than twenty years and is still one of the most challenging fields in artificial intelligence. Indeed taking a look at the human visual system can give us an idea of the complexity of any solution to the problem of visual recognition. This general task can be decomposed into a whole hierarchy of problems ranging from pixel processing to high level segmentation and complex objects recognition. Contrasting an image at different representations provides useful information such as edges. First, we introduce an example of low level signal and image processing using the theory of wavelets which provides the basis for multiresolution representation. Like the human brain, we use a multiorientation process which detects features independently in different orientation sectors. So, we end up contrasting images of the same orientation but of different resolutions to gather information about an image. We then develop an interesting image representation using energy zero crossings. We show that this representation is experimentally complete and leads to some higher level applications such as edge and corner finding, which in turn provides two basic steps to image segmentation. We also discuss the possibilities of feedback between different levels of processing.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
1989-04-01
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-89-22.
Recommended citation
Collection