Spatial-Aware Dictionary Learning for Hyperspectral Image Classification

Soltani-Farani, Ali; Rabiee, Hamid R.; Hosseini, Seyed Abbas

doi:10.1109/tgrs.2014.2325067

Cited by 119 publications

(48 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, sparsity based regularization has achieved great success, offering solutions that outperform classical approaches in various image and signal processing applications. Among the others, we can mention inverse problems such as denoising [35,36], reconstruction [22,37], classification [38], recognition [39,40], and compression [41,42]. The underlying assumption of methods based on sparse representation is that signals such as audio and images are naturally generated by a multivariate linear model, driven by a small number of basis or regressors.…”

Section: Sparse Image Representationmentioning

confidence: 99%

Non-Local Sparse Image Inpainting for Document Bleed-Through Removal

et al. 2018

View full text Add to dashboard Cite

Bleed-through is a frequent, pervasive degradation in ancient manuscripts, which is caused by ink seeped from the opposite side of the sheet. Bleed-through, appearing as an extra interfering text, hinders document readability and makes it difficult to decipher the information contents. Digital image restoration techniques have been successfully employed to remove or significantly reduce this distortion. This paper proposes a two-step restoration method for documents affected by bleed-through, exploiting information from the recto and verso images. First, the bleed-through pixels are identified, based on a non-stationary, linear model of the two texts overlapped in the recto-verso pair. In the second step, a dictionary learning-based sparse image inpainting technique, with non-local patch grouping, is used to reconstruct the bleed-through-contaminated image information. An overcomplete sparse dictionary is learned from the bleed-through-free image patches, which is then used to estimate a befitting fill-in for the identified bleed-through pixels. The non-local patch similarity is employed in the sparse reconstruction of each patch, to enforce the local similarity. Thanks to the intrinsic image sparsity and non-local patch similarity, the natural texture of the background is well reproduced in the bleed-through areas, and even a possible overestimation of the bleed through pixels is effectively corrected, so that the original appearance of the document is preserved. We evaluate the performance of the proposed method on the images of a popular database of ancient documents, and the results validate the performance of the proposed method compared to the state of the art.

show abstract

Section: Sparse Image Representationmentioning

confidence: 99%

Non-Local Sparse Image Inpainting for Document Bleed-Through Removal

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The fixed training set is challenging because it is made up of small patches, and most of the patches in an HSI contain no training samples. The proposed method is compared with SVM with Composite Kernel (SVM-CK) [70], SADL [40], Simultaneous Orthogonal Matching Pursuit (SOMP) [70], Learning Sparse-Representation-based Classification with Kernel-smoothed regularization (LSRC-K) [26], MPM-LBP and SMLP-SpATV. The experimental results are given in Table 6, where some results come from the related references (parameters are given in the forth column of the Table 2).…”

Section: Experiments With the Rosis University Of Pavia Datasetmentioning

confidence: 99%

Spectral-Spatial Response for Hyperspectral Image Classiﬁcation

Wei

Zhou

2017

Remote Sensing

View full text Add to dashboard Cite

This paper presents a hierarchical deep framework called Spectral-Spatial Response (SSR) to jointly learn spectral and spatial features of Hyperspectral Images (HSIs) by iteratively abstracting neighboring regions. SSR forms a deep architecture and is able to learn discriminative spectral-spatial features of the input HSI at different scales. It includes several existing spectral-spatial-based methods as special scenarios within a single unified framework. Based on SSR, we further propose the Subspace Learning-based Networks (SLN) as an example of SSR for HSI classification. In SLN, the joint spectral and spatial features are learned using templates simply learned by Marginal Fisher Analysis (MFA) and Principal Component Analysis (PCA). An important contribution to the success of SLN is the exploitation of label information of training samples and the local spatial structure of HSI. Extensive experimental results on four challenging HSI datasets taken from the Airborne Visible-Infrared Imaging Spectrometer (AVIRIS) and Reflective Optics System Imaging Spectrometer (ROSIS) airborne sensors show the implementational simplicity of SLN and verify the superiority of SSR for HSI classification.

show abstract

“…The parameters of SVM (linear-kernel parameter , d, and regularization parameter C) are obtained by cross-validation. The parameters of SADL are set in the same way as in [10]. The parameters of SLDL are set according to our experience.…”

Section: Experiments and Analysismentioning

confidence: 99%

“…In order to solve this problem, a spatial-aware dictionary learning (SADL) algorithm was proposed in [6]. The algorithm divides hyperspectral images into groups of multiple rectangles, assuming that the same group of pixels consists of the same material.…”

Section: Introductionmentioning

confidence: 99%

Super pixel-level dictionary learning for hyperspectral image classification

Zhao¹,

Zhu²,

Liao³

et al. 2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. This paper presents a superpixel-level dictionary learning model for hyperspectral data. The idea is to divide the hyperspectral image into a number of super-pixels by means of the super-pixel segmentation method. Each super-pixel is a spatial neighborhood called contextual group. That is, each pixel is represented using a linear combination of a few dictionary items learned from the train data, but since pixels inside a super-pixel are often consisting of the same materials, their linear combinations are constrained to use common items from the dictionary. To this end, the sparse coefficients of the context group have a common sparse pattern by using the joint sparse regularizer for dictionary learning. The sparse coefficients are then used for classification using linear support vector machines. The validity of the proposed method is experimentally verified on a real hyperspectral images.

show abstract

Spatial-Aware Dictionary Learning for Hyperspectral Image Classification

Cited by 119 publications

References 53 publications

Non-Local Sparse Image Inpainting for Document Bleed-Through Removal

Non-Local Sparse Image Inpainting for Document Bleed-Through Removal

Spectral-Spatial Response for Hyperspectral Image Classiﬁcation

Super pixel-level dictionary learning for hyperspectral image classification

Contact Info

Product

Resources

About