Efficient Single Image Super-Resolution via Graph Embedding

Jiang, Junjun; Hu, Ruimin; Han, Zhen; Huang, Kebin; Lü, Tao

doi:10.1109/icme.2012.102

Cited by 15 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our another important goal is to encode the geometry of the HR patch manifold, which is much more credible and discriminated compared with that of the LR one [9], and preserve the geometry for the reconstructed HR patch space [12]. This will ensure that the local geometric structure of the reconstructed HR patch manifold is consistent with that of the original HR one.…”

Section: Lr-hr Pairwise Dictionarymentioning

confidence: 97%

Object Detection in Low-Resolution Image via Sparse Representation

Fang

Liang

Wang

et al. 2015

MultiMedia Modeling

Self Cite

View full text Add to dashboard Cite

Abstract. We propose a novel object detection framework in extreme Low-Resolution (LR) images via sparse representation. Object detection in extreme LR images is very important for some specific applications such as abnormal event detection, automatic criminal investigation from surveillance videos. Object detection has achieved much progress in computer vision, but it is still a challenging task in LR image, because traditional discriminative features in high resolution usually disappear in low resolution. The precision of the detector in LR will decrease by a large margin. Our model uses sparse coding of part filters to represent each filter as a sparse linear combination of shared dictionary elements. The main contribution of this paper: 1) the object detection framework in extreme LR is proposed by detecting objects in reconstructed HR image; 2) a mapping function from LR patches to High-Resolution (HR) patches will be learned by a local regression algorithm called sparse support regression, which can be constructed from the support based of the LR-HR dictionary; 3) a novel feature extraction method is proposed to accelerate by extracting visual features from HR dictionary atoms. Our approach has produced better performance for object detection than state-of-the-art methods. Testing our method from INRIA and PASCAL VOC 2007 datasets has revealed similar improvements, suggesting that our approach is suitable for general object detection applications.

show abstract

Section: Lr-hr Pairwise Dictionarymentioning

confidence: 97%

Object Detection in Low-Resolution Image via Sparse Representation

Fang

Liang

Wang

et al. 2015

MultiMedia Modeling

Self Cite

View full text Add to dashboard Cite

show abstract

“…Manifold Manifold based methods [151] (2004), [206], [207], [310], [311], [327], [329], [343], [382], [386], [403], [404], [469], [495], [521], [553], [561], [568], [569], [570] assume that the HR and LR images form manifolds with similar local geometries in two distinct feature spaces [343]. Similar to PCA, these methods are also usually used for dimensionality reduction.…”

Section: Learning Based Single Image Sr Algorithmsmentioning

confidence: 99%

“…In the first step, they are combined with a MAP method [310], [311], [495], [568], [569], [570] or a Markov based learning method [206] like those in [65], [66], [76], [102], [146], [203] to apply a global constraint over the super-resolved image. In the second step, they use a different technique like Kernel Ridge Regression (KRR) [343], [495], graph embedding [568], radial basis function and partial least squares (RBF-PLS) regression [569], [570] to apply local constraints to the super-resolved image by finding the transformation between low and HR residual patches.…”

Section: Learning Based Single Image Sr Algorithmsmentioning

confidence: 99%

Super-resolution: a comprehensive survey

Nasrollahi

Moeslund

2014

Machine Vision and Applications

600

292

View full text Add to dashboard Cite

Super-resolution, the process of obtaining one or more high-resolution images from one or more low-resolution observations, has been a very attractive research topic over the last two decades. It has found practical applications in many real world problems in different fields, from satellite and aerial imaging to medical image processing, to facial image analysis, text image analysis, sign and number plates reading, and biometrics recognition, to name a few. This has resulted in many research papers, each developing a new superresolution algorithm for a specific purpose. The current comprehensive survey provides an overview of most of these published works by grouping them in a broad taxonomy. For each of the groups in the taxonomy, the basic concepts of the algorithms are first explained and then the paths through which each of these groups have evolved are given in detail, by mentioning the contributions of different authors to the basic concepts of each group. Furthermore, common issues in super-resolution algorithms, such as imaging models and registration algorithms, optimization of the cost functions employed, dealing with color information, improvement factors, assessment of super-resolution algorithms, and the most commonly employed databases are discussed.

show abstract

“…While the samples in the HR face space can more practically reflect the neighbor relationship compared with the LR one [15], and thus we construct the similarity graphs in the original HR image space and then preserve geometry constraint for the reconstructed HR face space. is the set of b K neighbors of i y belonging to different persons.…”

Section: Similarity Graphs On Multi-manifoldmentioning

confidence: 99%

“…As a result, the manifold margin in the reconstructed HR face space is much larger and thus more discriminant for recognition purpose. Though the multi-manifold discriminant analysis has not been considered for image SR, it has been widely investigated in many aspects in other matching learning, pattern recognition and computer vision models [13,14,15]. We empirically show that, in combination with multi-manifold structural information, the reconstructed HR faces can result in considerable FR improvements.…”

Section: Introductionmentioning

confidence: 97%

Graph discriminant analysis on multi-manifold (GDAMM): A novel super-resolution method for face recognition

Jiang

Han

et al. 2012

2012 19th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

How to efficiently recognize low-resolution (LR) probe images of one face recognition system, in which high-resolution (HR) gallery of faces is enrolled, is still an open problem. In this paper, we develop a novel super-resolution method, namely Graph Discriminant Analysis on Multi-Manifold (GDAMM), to super-resolved the HR version of a LR probe image and then perform matching at the resolution of the HR gallery. Unlike classical super-resolution approaches considering only the data fidelity, GDAMM takes the advantages of both manifold learning and discriminant analysis to integrate the data constraint and discriminant constraint, seeking the mapping between LR images and HR ones. In the reconstructed HR image space, faces of one person in the same manifold are close and those in different manifolds are far apart. Experiments on Extended Yale-B database and AR face database demonstrate that the learned discriminant information is essential for improving recognition accuracy. Through the contrastive experiment, the results (recognition rates) indicate that the proposed GDAMM method can greatly surpass classical super-resolution approaches, even outperforming the ideal case of having probe images of HR gallery by a big margin (nearly 9% on Extended Yale-B database and 8% on AR face database).

show abstract

Efficient Single Image Super-Resolution via Graph Embedding

Cited by 15 publications

References 10 publications

Object Detection in Low-Resolution Image via Sparse Representation

Object Detection in Low-Resolution Image via Sparse Representation

Super-resolution: a comprehensive survey

Graph discriminant analysis on multi-manifold (GDAMM): A novel super-resolution method for face recognition

Contact Info

Product

Resources

About