| dc.contributor.author |
Yu, Jiajie |
|
| dc.contributor.author |
Henry, Christopher J. |
|
| dc.date.accessioned |
2021-10-25T18:13:47Z |
|
| dc.date.available |
2021-10-25T18:13:47Z |
|
| dc.date.issued |
2019-02-02 |
|
| dc.identifier.citation |
Yu, Jiajie, and Christopher J. Henry, "Descriptive Topological Spaces for Performing Visual Search." In: Peters J., Skowron A. (eds.), Transactions on Rough Sets XXI. Lecture Notes in Computer Science, vol. 10810 (Berlin & Heidelberg: Springer, 2019). DOI: 10.1007/978-3-662-58768-3_2. |
en_US |
| dc.identifier.uri |
https://hdl.handle.net/10680/1973 |
|
| dc.description |
Accepted version |
en_US |
| dc.description.abstract |
This article presents an approach to performing the task of visual search in the context of descriptive topological spaces. The presented algorithm forms the basis of a descriptive visual search system (DVSS) that is based on the guided search model (GSM) that is motivated by human visual search. This model, in turn, consists of the bottom-up and top-down attention models and is implemented within the DVSS in three distinct stages. First, the bottom-up activation process is used to generate saliency maps and to identify salient objects. Second, perceptual objects, defined in the context of descriptive topological spaces, are identified and associated with feature vectors obtained from a VGG deep learning convolutional neural network. Lastly, the top-down activation process makes decisions on whether the object of interest is present in a given image through the use of descriptive patterns within the context of a descriptive topological space. The presented approach is tested with images from the ImageNet ILSVRC2012 and SIMPLIcity datasets. The contribution of this article is a descriptive pattern-based visual search algorithm. |
en_US |
| dc.description.sponsorship |
"This research has been supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant 418413, and the Faculty of Graduate Studies at the University of Winnipeg." |
en_US |
| dc.description.uri |
https://link.springer.com/chapter/10.1007/978-3-662-58768-3_2 |
en_US |
| dc.language.iso |
en |
en_US |
| dc.publisher |
Springer |
en_US |
| dc.relation.ispartofseries |
Transactions on Rough Sets;21 |
|
| dc.relation.ispartofseries |
Lecture Notes in Computer Science;10810 |
|
| dc.rights |
info:eu-repo/semantics/openAccess |
en_US |
| dc.subject |
Human visual search |
en_US |
| dc.subject |
Guided search model |
en_US |
| dc.subject |
Bottom-up attention |
en_US |
| dc.subject |
Top-down attention |
en_US |
| dc.subject |
Salient objects |
en_US |
| dc.subject |
Visual field |
en_US |
| dc.subject |
描述性的拓扑空间 |
en_US |
| dc.subject |
Descriptive proximity |
en_US |
| dc.subject |
Descriptive set intersection |
en_US |
| dc.subject |
Convolutional neural network |
en_US |
| dc.title |
Descriptive Topological Spaces for Performing Visual Search |
en_US |
| dc.type |
Book chapter |
en_US |
| dc.identifier.doi |
https://doi.org/10.1007/978-3-662-58768-3_2 |
en_US |
