Tianli Yu, Jiebo Luo, Amit Singhal, Narendra Ahuja
regularized active contour based on dynamic programming
Factor Graphs for Region-based Whole-scene Classification (2008)
Matthew R. Boutell, Jiebo Luo, Christopher M. Brown
Semantic scene classification is still a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the scene, our approach uses explicit...
Automatic image orientation detection for natural images is a useful, yet challenging research area. Humans use scene context and semantic object recognition to identify the correct image...
Universal Descreening Technique Via Wavelet Analysis (2008)
Jiebo Luo, Ricardo Queiroz, Zhigang Fan
In this paper, a novel wavelet-based approach to recover continuous tone images from halftone images is presented. Wavelet decomposition of the halftone image facilitates a series of spatial and...
Correspondence Information: (2008)
Matthew Boutell, Jiebo Luo, Dr. Jiebo Luo
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture conditions provides cues...
Matthew R. Boutell, Co-advisors Prof, Christopher M. Brown, Dr. Jiebo Luo
Computer vision, machine learning, multimedia content understanding, image databases, pattern recognition.
A Hierarchical Compositional Model for Face Representation and Sketching (2008)
Zijian Xu, Hong Chen, Song-chun Zhu, Jiebo Luo
This paper presents a hierarchical-compositional model of human faces, as a three-layer And-Or graph to account for the structural variabilities over multiple resolutions. In the And-Or graph, an...
Discovery of social relationships in consumer photo collections using markov logic (2008)
Parag Singla, Henry Kautz, Andrew Gallagher, Jiebo Luo
We identify the social relationships between individuals in consumer photos. Consumer photos generally do not contain a random gathering of strangers but rather groups of friends and families....
Large-scale multimodal semantic concept detection for consumer video (2007)
Shih-fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Er C. Loui, ...
In this paper we present a systematic study of automatic classification of consumer videos into a large set of diverse semantic concept classes, which have been carefully selected based on user...
Large-scale multimodal semantic concept detection for consumer video (2007)
Shih-fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Er C. Loui, ...
In this paper we present a systematic study of automatic classification of consumer videos into a large set of diverse semantic concept classes, which have been carefully selected based on user...
Bayesian fusion of camera metadata cues in semantic scene classification (2004)
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture conditions provides cues...
Incorporating temporal context with content for classifying image collections (2004)
Semantic scene classification is an open problem in image understanding, especially when information purely from image content (i.e., pixels) is employed. However, in applications involving image...
Multi-Label Machine Learning and Its Application to Semantic Scene Cassification (2004)
Xipeng Shen, Matthew Boutell, Jiebo Luo, Christopher Brown
In classic pattern recognition problems, classes are mutually exclusive by definition. Classification errors occur when the classes overlap in the feature space. We examine a different situation,...
Learning spatial configuration models using modified Dirichlet priors (2004)
Matthew Boutell, Christopher Brown, Jiebo Luo
Semantic scene classification is a challenging problem in computer vision. Special-purpose semantic object and material (e.g., sky and grass) detectors help, but are faulty in practice. In this...
Multi-label Semantic Scene Classfication (2003)
Boutell, Matthew R., Shen, Xipeng, Luo, Jiebo, Brown, Christopher M.
In classic pattern recognition problems, classes are mutually exclusive by definition. Classification errors occur when the classes overlap in the feature space. We examine a different situation,...
Efficient mobile imaging using emphasis image selection (2003)
Luo, Jiebo, Singhal, Amit, Savakis, Andreas
"Efficient mobile imaging using emphasis image selection," PICS 2003: The PICS Conference, An International Technical Conference on The Science and Systems of Digital Photography, including the Fifth...
Multi-label semantic scene classification (2003)
Matthew Boutell, Xipeng Shen, Jiebo Luo, Chris Brown
In classic pattern recognition problems, classes are mutually exclusive by definition. Classification errors occur when the classes overlap in the feature space. We examine a different situation,...
Jiebo Luo, David Crandall, Amit Singhal, Matthew Boutell, Robert T. Gray
Abstract—The experiment reported here investigates the perception of orientation of color photographic images. A collection of 1000 images (mix of professional photos and consumer snapshots) was...
Sunset scene classification using simulated image recomposition (2003)
Matthew Boutell, Jiebo Luo, Robert T. Gray
Knowledge of the semantic classification of an image can be used to improve the accuracy of queries in content-based image organization and retrieval and to provide customized image enhancement. We...
Review of the State of the Art in Semantic Scene Classification (2002)
Boutell, Matthew R., Brown, Christopher M., Luo, Jiebo
We would also like to thank Amit Singhal, Bob Gray, Zhao-hui Sun, and Navid Serrano, all of Eastman Kodak Company, for their support and advice throughout the course of this research.
A computationally efficient approach to indoor/outdoor scene classification (2002)
Serrano, Navid, Savakis, Andreas, Luo, Jiebo
"A computationally efficient approach to indoor/outdoor scene classification," Proceedings of the 16th International Conference on Pattern Recognition, vol. 4. Institute of Electrical and Electronics...
Self-supervised texture segmentation using complementary types of features (2001)
The Pattern Recognition Journal homepage may be accessed at: http://www.elsevier.com/wps/find/journaldescription.cws_home/328/description#description
"Indoor vs outdoor classification of consumer photographs using low-level and semantic features," Proceedings of the 2001 International Conference on Image Processing, vol. 2. The Institute of...
Evaluation of texture features for image segmentation (2001)
Serrano, Navid, Luo, Jiebo, Savakis, Andreas
"Evaluation of texture features for image segmentation," Presented at the IEEE Western New York Image Processing Workshop 2001. The Institute of Electrical and Electronics Engineers. Held at the...
On the application of Bayes networks to semantic understanding of consumer photographs (2000)
Luo, Jiebo, Savakis, Andreas, Etz, Stephen, Singhal, Amit
"On the application of Bayes networks to semantic understanding of consumer photographs," Proceedings of the 2000 International Conference on Image Processing, vol. 3. The Institute of Electrical and...
Two-stage texture segmentation using complementary features (2000)
"Two-stage texture segmentation using complementary features," Proceedings of the 2000 International Conference on Image Processing (ICIP '00). The Institute for Electrical and Electronics Engineers....
Texture-based segmentation of natural images using multiresolution autoregressive models (1998)
"Texture-based segmentation of natural images using multiresolution autoregressive models," Presented at the 1998 IEEE Western New York Image Processing Workshop. The Institute of Electrical and...