Title :
A hierarchical field framework for unified context-based classification
Author :
Kumar, Sanjiv ; Hebert, Martial
Author_Institution :
Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA
Abstract :
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional field that allows one to capture arbitrary observation-dependent label interactions. The proposed framework has two main advantages. First, it encodes both the short-range interactions (e.g., pixelwise label smoothing) as well as the long-range interactions (e.g., relative configurations of objects or regions) in a tractable manner. Second, the formulation is general enough to be applied to different domains ranging from pixelwise image labeling to contextual object detection. The parameters of the model are learned using a sequential maximum-likelihood approximation. The benefits of the proposed framework are demonstrated on four different datasets and comparison results are presented
Keywords :
image classification; maximum likelihood estimation; object detection; contextual object detection; observation-dependent label interaction; pixelwise image labeling; pixelwise label smoothing; sequential maximum-likelihood approximation; unified context-based classification; Context modeling; Keyboards; Labeling; Layout; Mice; Object detection; Pixel; Robots; Robustness; Smoothing methods;
Conference_Titel :
Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7695-2334-X
DOI :
10.1109/ICCV.2005.9