- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 1 to 10 of 2783 (0.055 seconds)Spelling suggestions: "subject:"[een] COMPUTER VISION"" "subject:"[enn] COMPUTER VISION""
| 1 |
Hypothesis verification using iconic matchingBrisdon, Kay January 1990 (has links)
A new technique for iconic hypothesis verification in model-based vision systems has been developed, which enhances the resolution of the problem of three-dimensional object recognition in two-dimensional scenes. This thesis investigates an iconic feature-matching approach to verification, in which two-dimensional image features are predicted from a specific view of a three-dimensional geometric model, and these features are matched directly to the unprocessed image data. This solves the crucial image to model registration problem. The iconic matching approach solves two of the major disadvantages of the usual symbolic matching method; where symbolic image constructs are compared with symbolic model data. The symbolic description of image features is not robust, and detailed matches cannot be made, as much of the original data has been lost. The investigation of iconic verification has been split into two parts. Firstly individual features are matched. Secondly the results from these are aggregated into a model match score. For the first stage four iconic evaluators have been developed and compared. These predictive evaluators are designed to assess the "edge-ness" of a small patch of an image. The advantage of one of these techniques over its equivalent data-driven approach is shown. The complete verification procedure aggregates the image-specific iconic feature evaluation scores. The iconic matching technique has been tested in the domain of car recognition in outdoor scene images. Its sensitivity in images containing a great deal of distracting noise has been very encouraging. There are however many application areas for this research. Iconic matching can be used to track both individual features and entire objects, for example in successive frames of a sequence of images over time
|
| 2 |
Inexact graph matching using symbolic constraintsWilson, Richard Charles January 1996 (has links)
No description available.
|
| 3 |
Inferring surface shape from specular reflectionsBrelstaff, Gavin J. January 1988 (has links)
No description available.
|
| 4 |
Robot guidance using image features and fuzzy logicSonmez, Ahmet Coskun January 1992 (has links)
No description available.
|
| 5 |
Learning the visual dynamics of human body motionsOng, Eng-Jon January 2001 (has links)
No description available.
|
| 6 |
Investigation of the use of neural networks for computerised medical image analysisDickson, Shane January 1998 (has links)
No description available.
|
| 7 |
Natural image segmentationCraske, Simon January 1998 (has links)
No description available.
|
| 8 |
Recognizing objects using invariant image featuresReiss, T. H. January 1992 (has links)
No description available.
|
| 9 |
Computational texture analysis and segmentationWen, Wen January 1991 (has links)
No description available.
|
| 10 |
Optimization methods for relational matchingCross, Andrew David Jonathan January 1998 (has links)
No description available.
|
Page generated in 0.0597 seconds