Object Contour Completion by Combining Object Recognition and Local Edge Cues
Journal of Information and Communication Technology · 06.11.2017 · 16 (2) · 224-242
DOI: 10.32890/jict2017.16.2.2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Information and Communication Technology, online erschienen am 06.11.2017. Verfasst von Kar Seng Loke. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Loke, K. S. (2017). Object Contour Completion by Combining Object Recognition and Local Edge Cues. Journal of Information and Communication Technology, 16(2), 224-242. https://doi.org/10.32890/jict2017.16.2.2
Vancouver
Loke KS. Object Contour Completion by Combining Object Recognition and Local Edge Cues. Journal of Information and Communication Technology. 2017;16(2):224-242. doi:10.32890/jict2017.16.2.2
BibTeX
@article{Loke2017,
author = {Loke, Kar Seng},
title = {Object Contour Completion by Combining Object Recognition and Local Edge Cues},
journal = {Journal of Information and Communication Technology},
year = {2017},
volume = {16},
number = {2},
pages = {224--242},
doi = {10.32890/jict2017.16.2.2}
}
EUVIMED