Document Type
Article
Publication Date
10-2015
Publication Source
IEEE Transactions on Circuits and Systems for Video Technology
Abstract
In this paper, we present an adaptive nonparametric solution to the image parsing task, namely, annotating each image pixel with its corresponding category label. For a given test image, first, a locality-aware retrieval set is extracted from the training data based on superpixel matching similarities, which are augmented with feature extraction for better differentiation of local superpixels. Then, the category of each superpixel is initialized by the majority vote of the k -nearest-neighbor superpixels in the retrieval set. Instead of fixing k as in traditional nonparametric approaches, here, we propose a novel adaptive nonparametric approach that determines the sample-specific k for each test image. In particular, k is adaptively set to be the number of the fewest nearest superpixels that the images in the retrieval set can use to get the best category prediction. Finally, the initial superpixel labels are further refined by contextual smoothing. Extensive experiments on challenging data sets demonstrate the superiority of the new solution over other state-of-the-art nonparametric solutions.
Inclusive pages
1565-1575
ISBN/ISSN
1051-8215
Document Version
Postprint
Copyright
Copyright © 2015, IEEE
Publisher
IEEE
Volume
25
Peer Reviewed
yes
Issue
10
eCommons Citation
Nguyen, Tam; Lu, Canyi; Sepulveda, Jose; and Yan, Shuicheng, "Adaptive Nonparametric Image Parsing" (2015). Computer Science Faculty Publications. 79.
https://ecommons.udayton.edu/cps_fac_pub/79
Comments
The document available for download is the authors' accepted manuscript, provided in compliance with the publisher's policy on self-archiving. Differences may exist between this document and the published version, which is available using the link provided. Permission documentation is on file.