Local Label Descriptor for Example Based Semantic Image Labeling

Yiqing Yang¹, Zhouyuan Li¹, Li Zhang¹, Christopher Murphy², Jim Ver Hoeve¹, and Hongrui Jiang¹

¹University of Wisconsin-Madison, USA

²University of California, Davis, USA

Abstract. In this paper we introduce the concept of local label descriptor, which is a concatenation of label histograms for each cell in a patch. Local label descriptors alleviate the label patch misalignment issue in combining structured label predictions for semantic image labeling. Given an input image, we solve for a label map whose local label descriptors can be approximated as a sparse convex combination of exemplar label descriptors in the training data, where the sparsity is regularized by the similarity measure between the local feature descriptor of the input image and that of the exemplars in the training data set. Low-level image over-segmentation can be incorporated into our formulation to improve efficiency. Our formulation and algorithm compare favorably with the baseline method on the CamVid and Barcelona datasets.

LNCS 7578, p. 361 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer-Verlag Berlin Heidelberg 2012