OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES
We developed a top-down and bottom-up segmentation ofobjects using shape contours through a two-stage procedure. First, the object was identified using an edge-based contour feature and then the object contour was obtained using a constraint optimization procedure based on the results from the earli...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
UUM Press
2017-11-01
|
Series: | Journal of ICT |
Subjects: | |
Online Access: | https://e-journal.uum.edu.my/index.php/jict/article/view/8230 |
_version_ | 1798040930787262464 |
---|---|
author | Kar Seng Loke |
author_facet | Kar Seng Loke |
author_sort | Kar Seng Loke |
collection | DOAJ |
description | We developed a top-down and bottom-up segmentation ofobjects using shape contours through a two-stage procedure. First, the object was identified using an edge-based contour feature and then the object contour was obtained using a constraint optimization procedure based on the results from the earlier identified contours. The initial object detection provides object category specific information for the contour completion to be effected. We argue that top-down bottom-up interaction architecture has plausible neurological correlates. This method has an advantage in that it does not require learning boundaries with large datasets.
|
first_indexed | 2024-04-11T22:14:28Z |
format | Article |
id | doaj.art-37feadd495144003bd36bc51c5e24381 |
institution | Directory Open Access Journal |
issn | 1675-414X 2180-3862 |
language | English |
last_indexed | 2024-04-11T22:14:28Z |
publishDate | 2017-11-01 |
publisher | UUM Press |
record_format | Article |
series | Journal of ICT |
spelling | doaj.art-37feadd495144003bd36bc51c5e243812022-12-22T04:00:28ZengUUM PressJournal of ICT1675-414X2180-38622017-11-01162OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUESKar Seng Loke0School of Information Technology Swinburne University of Technology Sarawak Campus, MalaysiaWe developed a top-down and bottom-up segmentation ofobjects using shape contours through a two-stage procedure. First, the object was identified using an edge-based contour feature and then the object contour was obtained using a constraint optimization procedure based on the results from the earlier identified contours. The initial object detection provides object category specific information for the contour completion to be effected. We argue that top-down bottom-up interaction architecture has plausible neurological correlates. This method has an advantage in that it does not require learning boundaries with large datasets. https://e-journal.uum.edu.my/index.php/jict/article/view/8230Computer visionobject segmentationobject detectioncontour extractionscene interpretationimage understanding |
spellingShingle | Kar Seng Loke OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES Journal of ICT Computer vision object segmentation object detection contour extraction scene interpretation image understanding |
title | OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES |
title_full | OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES |
title_fullStr | OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES |
title_full_unstemmed | OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES |
title_short | OBJECT CONTOUR COMPLETION BY COMBINING OBJECT RECOGNITION AND LOCAL EDGE CUES |
title_sort | object contour completion by combining object recognition and local edge cues |
topic | Computer vision object segmentation object detection contour extraction scene interpretation image understanding |
url | https://e-journal.uum.edu.my/index.php/jict/article/view/8230 |
work_keys_str_mv | AT karsengloke objectcontourcompletionbycombiningobjectrecognitionandlocaledgecues |