Conditional Random Fields for Image Region Labeling with Global Observation

Lin, Zhe; Chan, Wen; He, Kai; Zhou, Xiangdong; Wang, Mei

doi:10.1007/978-3-319-03731-8_54

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the difficulty of only exploiting the local visual observation for region labeling, Toyoda et al [17] propose to employ the observation of multi-scales to reduce the inaccuracy produced by classifying the regions just based on the simple local evidence. Lin et al [9] proposed a method based on CRFs to solve the region labeling problem by utilizing visual features of both the local region and the whole image while there is no semantic context in their model.…”

Section: Related Workmentioning

confidence: 99%

Image Region Labeling by Exploring Contextual Information of Visual Spatial and Semantic Concepts

Chan

Zhu

et al. 2014

Advances in Multimedia Information Processing – PCM 2014

Self Cite

View full text Add to dashboard Cite

Abstract. Region Labeling is to automatically assign semantic labels to the corresponding image regions. Most of the previous works focus on exploiting low level visual features, particularly visual spatial contextual information, to address the problem. However, very few work explore high level semantic information of the whole image to deal with the problem. In this paper, we propose a new region labeling approach by integrating both visual spatial and semantic contextual information into a unified model. In our method, region labeling is regarded as a multi-class classification problem. For each semantic concept, we train a Conditional Random Field (CRF) model respectively. It consists of both the region grid sub-graph and the co-occurred semantic label sub-graph. In our model, the integration of the two kinds of contextual information brings reinforcement effect on the improvement of region labeling. The experiments are conducted on two commonly used benchmark datasets and the experimental results show that our method achieves the best performance compared with the strong baselines and the state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%