CVJan 16, 2012

Image Labeling and Segmentation using Hierarchical Conditional Random Field Model

arXiv:1201.3803v11 citations
Originality Synthesis-oriented
AI Analysis

This addresses image analysis tasks for computer vision applications, but it appears incremental as it builds on existing CRF methods with a clustering step.

The paper tackles image labeling and segmentation by using a hierarchical Conditional Random Field model that first labels pixels, finds the most similar image cluster, and then relabels using that cluster's CRF model, achieving correct information for specific images.

The use of hierarchical Conditional Random Field model deal with the problem of labeling images . At the time of labeling a new image, selection of the nearest cluster and using the related CRF model to label this image. When one give input image, one first use the CRF model to get initial pixel labels then finding the cluster with most similar images. Then at last relabeling the input image by the CRF model associated with this cluster. This paper presents a approach to label and segment specific image having correct information.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes