On a shape adaptive image ray transform
On a shape adaptive image ray transform
A conventional approach to image analysis is to perform separately feature extraction at a low level (such as edge detection) and follow this with high level feature extraction to determine structure (e.g. by collecting edge points using the Hough transform. The original image Ray Transform (IRT) demonstrated capability to extract structures at a low level. Here we extend the IRT to add shape specificity that makes it select specific shapes rather than just edges, the new capability is achieved by addition of a single parameter that controls which shape is elected by the extended IRT. The extended approach can then perform low-and high-level feature extraction simultaneously. We show how the IRT process can be extended to focus on chosen shapes such as lines and circles. We confirm the new capability by application of conventional methods for exact shape location. We analyze performance with images from the Caltech-256 dataset and show that the new approach can indeed select chosen shapes. Further research could capitalize on the new extraction ability to extend descriptive capability.
100-105
Ah Reum, Oh
a6c43beb-1d6e-411f-806f-7bb48501040b
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
2013
Ah Reum, Oh
a6c43beb-1d6e-411f-806f-7bb48501040b
Nixon, Mark S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Ah Reum, Oh and Nixon, Mark S.
(2013)
On a shape adaptive image ray transform.
2013 International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Kyoto, Japan.
02 - 05 Dec 2013.
.
(doi:10.1109/SITIS.2013.27).
Record type:
Conference or Workshop Item
(Paper)
Abstract
A conventional approach to image analysis is to perform separately feature extraction at a low level (such as edge detection) and follow this with high level feature extraction to determine structure (e.g. by collecting edge points using the Hough transform. The original image Ray Transform (IRT) demonstrated capability to extract structures at a low level. Here we extend the IRT to add shape specificity that makes it select specific shapes rather than just edges, the new capability is achieved by addition of a single parameter that controls which shape is elected by the extended IRT. The extended approach can then perform low-and high-level feature extraction simultaneously. We show how the IRT process can be extended to focus on chosen shapes such as lines and circles. We confirm the new capability by application of conventional methods for exact shape location. We analyze performance with images from the Caltech-256 dataset and show that the new approach can indeed select chosen shapes. Further research could capitalize on the new extraction ability to extend descriptive capability.
Text
On a Shape Adaptive Image Ray Transform.pdf
- Other
More information
Published date: 2013
Venue - Dates:
2013 International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Kyoto, Japan, 2013-12-02 - 2013-12-05
Organisations:
Vision, Learning and Control
Identifiers
Local EPrints ID: 363305
URI: http://eprints.soton.ac.uk/id/eprint/363305
PURE UUID: a5676578-0f0b-4f50-b9cc-d3d465100245
Catalogue record
Date deposited: 20 Mar 2014 16:28
Last modified: 15 Mar 2024 02:35
Export record
Altmetrics
Contributors
Author:
Oh Ah Reum
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
