Please use this identifier to cite or link to this item:
|Title:||In the shadows, shape priors shine: Using occlusion to improve multi-region segmentation|
|Publisher:||IEEE Computer Society|
|Citation:||Kihara Y., Soloviev M., Chen T. (2016). In the shadows, shape priors shine: Using occlusion to improve multi-region segmentation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2016-January : 392-401. ScholarBank@NUS Repository.|
|Abstract:||We present a new algorithm for multi-region segmentation of 2D images with objects that may partially occlude each other. Our algorithm is based on the observation that human performance on this task is based both on prior knowledge about plausible shapes and taking into account the presence of occluding objects whose shape is already known - once an occluded region is identified, the shape prior can be used to guess the shape of the missing part. We capture the former aspect using a deep learning model of shape; for the latter, we simultaneously minimize the energy of all regions and consider only unoccluded pixels for data agreement. Existing algorithms incorporating object shape priors consider every object separately in turn and can't distinguish genuine deviation from the expected shape from parts missing due to occlusion. We show that our method significantly improves on the performance of a representative algorithm, as evaluated on both preprocessed natural and synthetic images. Furthermore, on the synthetic images, we recover the ground truth segmentation with good accuracy.|
|Source Title:||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Aug 30, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.