Graph Laplace for Occluded Face Completion and Recognition

Deng, Yue; Dai, Qionghai; Zhang, Zengke

doi:10.1109/tip.2011.2109729

Cited by 70 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A large number of approaches [20], [21], [23], [25], [27], [28], [38], [45] have been developed to learn metric in machine learning and pattern recognition tasks. In future study, other distance metric learning approaches will be investigated with different type of segmentation methods, such as level set approach and atlas based method [59].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

et al. 2014

View full text Add to dashboard Cite

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The minimization of equation (11) can be written in another way aswhere is the normalized Laplacian matrix [45] of the constructed graph . The minimization problem is then turned to a quadratic programming problem.…”

Section: Methodsmentioning

confidence: 99%

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Unsupervised image segmentation often relies on clustering texture features by maximizing/minimizing some energy or cost function [22,23]. In this case, most pixel pairs should be considered, but that may be expensive.…”

Section: Introductionmentioning

confidence: 99%

“…Some methods model affinities and use graph cuts to group segments, obtaining the final image segmentation [22,23]. Alternatively, clustering algorithm may group adjacent segments using spatial constraints [27] [20].…”

Section: Introductionmentioning

confidence: 99%

Image segmentation via multi-scale stochastic regional texture appearance models

Medeiros

Scharcanski

Wong

2016

Computer Vision and Image Understanding

View full text Add to dashboard Cite

“…Over last decades, a large number of prominent works have been devoted to this challenging task from diverse ranges of perspectives including biological investigation [1]–[3], psychological research [4]–[6] and computational methods [7]–[10]. In this paper, we propose a computational approach to reveal the differences of various images and will interpret how the differences help computers to conduct visual recognition tasks.…”

Section: Introductionmentioning

confidence: 99%

Differences Help Recognition: A Probabilistic Interpretation

et al. 2013

View full text Add to dashboard Cite

This paper presents a computational model to address one prominent psychological behavior of human beings to recognize images. The basic pursuit of our method can be concluded as that differences among multiple images help visual recognition. Generally speaking, we propose a statistical framework to distinguish what kind of image features capture sufficient category information and what kind of image features are common ones shared in multiple classes. Mathematically, the whole formulation is subject to a generative probabilistic model. Meanwhile, a discriminative functionality is incorporated into the model to interpret the differences among all kinds of images. The whole Bayesian formulation is solved in an Expectation-Maximization paradigm. After finding those discriminative patterns among different images, we design an image categorization algorithm to interpret how these differences help visual recognition within the bag-of-feature framework. The proposed method is verified on a variety of image categorization tasks including outdoor scene images, indoor scene images as well as the airborne SAR images from different perspectives.

show abstract

Graph Laplace for Occluded Face Completion and Recognition

Cited by 70 publications

References 27 publications

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

Image segmentation via multi-scale stochastic regional texture appearance models

Differences Help Recognition: A Probabilistic Interpretation

Contact Info

Product

Resources

About