A conditional random field model for image parsing
Pages 135 - 138
Abstract
The paper presented a novel discriminative model for efficient and effective recognition and simultaneous semantic segmentation of objects in images. The images are first segmented to give 'super-pixels'. Then the super-pixels are merged together and semantically labeled using a Condition Random Field (CRF) model. The use of a conditional random field allows us to incorporate different cues in a single unified model. The test on the standard dataset shows that compared with existing systems, the proposed system produces a detailed segmentation of a test image into coherent regions, with a semantic label associated with each region in the image.
References
[1]
Han F and Zhu S C. Bottom-up/Top-down image parsing with attribute graph grammar. IEEE Transaction on Pattern Analysis and Machine Intelligence, 31(1):59--73, 2009.
[2]
Carbonetto P, Dork'o G, and Schmid C, et al. A semi-supervised learning approach to object recognition with spatial integration of local features and segmentation cues. Toward Category-Level Object Recognition, 277--300, 2006.
[3]
Verbeek J and Triggs B. Region classification with Markov field aspect models. IEEE Conference on Computer Vision and Pattern Recognition, 1--8, 2007.
[4]
He X, Zemel R S, et al. Multiscale conditional random fields for image labeling. IEEE Conference of Computer Vision and Pattern Recognition, 695--702. 2004.
[5]
He X, Zemel R S, et al, Learning and incorporating Top-Down cues in image segmentation. European Conference on Computer Vision. 338--351, 2006.
[6]
Shotton J, Winn J and Rother C, et al. Textonboost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. The European Conference on Computer Vision, 1--15, 2006.
[7]
Vedaldi A and Soatto S. Quick shift and kernel methods for mode seeking. European Conference on Computer Vision, 705--718, 2008.
[8]
Ma J W, Wang T J. A cost-function approach to rival penalized competitive learning. IEEE Transactions on Systems Man and Cybernetics. 36(4):722--737, 2006.
[9]
Greene M R, Oliva A. Recognition of natural scenes from global properties: seeing the forest without representing the trees. Cognitive Psychology, 58(2):137--179, 2009.
[10]
Torralba A., Murphy K, Freeman W. Sharing features: efficient boosting procedures for multiclass object detection. IEEE Conference on Computer Vision and Pattern Recognition, 762--769, 2004.
[11]
Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. International Conference on Computer Vision, 105--112. 2001.
[12]
Kumar S, Hebert M. Discriminative random fields: a discriminative framework for contextual interaction in classification. International Conference on Computer Vision, 1150--1157, 2003.
[13]
Sutton C, McCallum A. Piecewise training of undirected models. The 21st Conference on Uncertainty in Artificial Intelligence, 568--575, 2005.
[14]
Rother C, Kolmogorov V, Blake A. Interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics, 23(3):309--314, 2004.
Index Terms
- A conditional random field model for image parsing
Recommendations
A Conditional Random Field with Loop and Its Inference Algorithm
ISDEA '12: Proceedings of the 2012 Second International Conference on Intelligent System Design and Engineering ApplicationA new algorithm for human motion Recognition based on Conditional Random Fields (CRFs) and Hidden Markov Models (HMM) -- HMCRF is proposed. Most existing approaches to human motion recognition with hidden states employ a Hidden Markov Model or suitable ...
A conditional random field-based model for joint sequence segmentation and classification
In this paper, we consider the problem of joint segmentation and classification of sequences in the framework of conditional random field (CRF) models. To effect this goal, we introduce a novel dual-functionality CRF model: on the first level, the ...
Enhanced Reweighted MRFs for Efficient Fashion Image Parsing
Previous image parsing methods usually model the problem in a conditional random field which describes a statistical model learned from a training dataset and then processes a query image using the conditional probability. However, for clothing images, ...
Comments
Information & Contributors
Information
Published In
December 2010
218 pages
ISBN:9781450304603
DOI:10.1145/1937728
- General Chairs:
- Yong Rui,
- Klara Nahrstedt,
- Xiaofei Xu,
- Program Chairs:
- Hongxun Yao,
- Shuqiang Jiang,
- Jian Cheng
Copyright © 2010 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 30 December 2010
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- Technological Innovation Cultivate Program of Zhengzhou City
- Aeronautical Science Foundation of China
- Basic and Frontier Technology Research Programs of the Department of Science & Technology of Henan Province
- National Natural Science Foundation of China
Conference
ICIMCS '10
ICIMCS '10: The Second International Conference on Internet Multimedia Computing and Service
December 30 - 31, 2010
Harbin, China
Acceptance Rates
Overall Acceptance Rate 163 of 456 submissions, 36%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 71Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Jan 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in