An ordered sparse subspace clustering algorithm based on p‐Norm

Liping Chen, Gongde Guo, H. Wang

Research output: Contribution to journalArticle

Abstract

Images in video may include both Gaussian noise and geometric rotation. Thus, it is challenging to represent an image sequence in its intrinsically low‐dimensional space in a noise‐robust and rotation‐robust manner. In this paper, we propose a novel‐ordered sparse subspace clustering algorithm based on a p‐norm to achieve an effective clustering of sequential data under heavy noise conditions. We also use the wavelet‐histogram of oriented gradient (HOG) transform in the kernel view to extract both the global features (with the wavelet process) and the local features (with the HOG process) from the image. In addition, we assign different weights to different features to obtain a sparse coefficient matrix that helps to emphasize the global and local correlations in each sample. Similarly, the clustering algorithm based on the p‐norm for sequential images emphasizes the within‐class correlations amongst samples. Therefore, in this paper, we select additional denoising main components under a Laplacian constraint to achieve a better block‐diagonal structure and highlight the independence of different clusters. Extensive experiments performed on various public datasets (including the ordered face dataset, handwritten recognition dataset, video scene segmentation dataset, and object recognition dataset) demonstrate that the proposed method is more resilient to noise and rotation than other representative sparse subspace clustering methods.
LanguageEnglish
Article numbere12368
Number of pages15
JournalExpert Systems
Volume2019;e12368
DOIs
Publication statusPublished - 9 Jan 2019

Fingerprint

Clustering algorithms
Object recognition
Experiments

Keywords

  • block-diagonal transform
  • image sequence clustering
  • sparse subspace clustering
  • wavelet-HOG

Cite this

Chen, Liping ; Guo, Gongde ; Wang, H. / An ordered sparse subspace clustering algorithm based on p‐Norm. In: Expert Systems. 2019 ; Vol. 2019;e12368.
@article{0f3f244f3bf2478b890671b24a4e58e1,
title = "An ordered sparse subspace clustering algorithm based on p‐Norm",
abstract = "Images in video may include both Gaussian noise and geometric rotation. Thus, it is challenging to represent an image sequence in its intrinsically low‐dimensional space in a noise‐robust and rotation‐robust manner. In this paper, we propose a novel‐ordered sparse subspace clustering algorithm based on a p‐norm to achieve an effective clustering of sequential data under heavy noise conditions. We also use the wavelet‐histogram of oriented gradient (HOG) transform in the kernel view to extract both the global features (with the wavelet process) and the local features (with the HOG process) from the image. In addition, we assign different weights to different features to obtain a sparse coefficient matrix that helps to emphasize the global and local correlations in each sample. Similarly, the clustering algorithm based on the p‐norm for sequential images emphasizes the within‐class correlations amongst samples. Therefore, in this paper, we select additional denoising main components under a Laplacian constraint to achieve a better block‐diagonal structure and highlight the independence of different clusters. Extensive experiments performed on various public datasets (including the ordered face dataset, handwritten recognition dataset, video scene segmentation dataset, and object recognition dataset) demonstrate that the proposed method is more resilient to noise and rotation than other representative sparse subspace clustering methods.",
keywords = "block-diagonal transform, image sequence clustering, sparse subspace clustering, wavelet-HOG",
author = "Liping Chen and Gongde Guo and H. Wang",
year = "2019",
month = "1",
day = "9",
doi = "10.1111/exsy.12368",
language = "English",
volume = "2019;e12368",
journal = "Expert Systems",
issn = "0266-4720",

}

An ordered sparse subspace clustering algorithm based on p‐Norm. / Chen, Liping; Guo, Gongde; Wang, H.

In: Expert Systems, Vol. 2019;e12368, e12368, 09.01.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An ordered sparse subspace clustering algorithm based on p‐Norm

AU - Chen, Liping

AU - Guo, Gongde

AU - Wang, H.

PY - 2019/1/9

Y1 - 2019/1/9

N2 - Images in video may include both Gaussian noise and geometric rotation. Thus, it is challenging to represent an image sequence in its intrinsically low‐dimensional space in a noise‐robust and rotation‐robust manner. In this paper, we propose a novel‐ordered sparse subspace clustering algorithm based on a p‐norm to achieve an effective clustering of sequential data under heavy noise conditions. We also use the wavelet‐histogram of oriented gradient (HOG) transform in the kernel view to extract both the global features (with the wavelet process) and the local features (with the HOG process) from the image. In addition, we assign different weights to different features to obtain a sparse coefficient matrix that helps to emphasize the global and local correlations in each sample. Similarly, the clustering algorithm based on the p‐norm for sequential images emphasizes the within‐class correlations amongst samples. Therefore, in this paper, we select additional denoising main components under a Laplacian constraint to achieve a better block‐diagonal structure and highlight the independence of different clusters. Extensive experiments performed on various public datasets (including the ordered face dataset, handwritten recognition dataset, video scene segmentation dataset, and object recognition dataset) demonstrate that the proposed method is more resilient to noise and rotation than other representative sparse subspace clustering methods.

AB - Images in video may include both Gaussian noise and geometric rotation. Thus, it is challenging to represent an image sequence in its intrinsically low‐dimensional space in a noise‐robust and rotation‐robust manner. In this paper, we propose a novel‐ordered sparse subspace clustering algorithm based on a p‐norm to achieve an effective clustering of sequential data under heavy noise conditions. We also use the wavelet‐histogram of oriented gradient (HOG) transform in the kernel view to extract both the global features (with the wavelet process) and the local features (with the HOG process) from the image. In addition, we assign different weights to different features to obtain a sparse coefficient matrix that helps to emphasize the global and local correlations in each sample. Similarly, the clustering algorithm based on the p‐norm for sequential images emphasizes the within‐class correlations amongst samples. Therefore, in this paper, we select additional denoising main components under a Laplacian constraint to achieve a better block‐diagonal structure and highlight the independence of different clusters. Extensive experiments performed on various public datasets (including the ordered face dataset, handwritten recognition dataset, video scene segmentation dataset, and object recognition dataset) demonstrate that the proposed method is more resilient to noise and rotation than other representative sparse subspace clustering methods.

KW - block-diagonal transform

KW - image sequence clustering

KW - sparse subspace clustering

KW - wavelet-HOG

UR - http://www.scopus.com/inward/record.url?scp=85059664085&partnerID=8YFLogxK

U2 - 10.1111/exsy.12368

DO - 10.1111/exsy.12368

M3 - Article

VL - 2019;e12368

JO - Expert Systems

T2 - Expert Systems

JF - Expert Systems

SN - 0266-4720

M1 - e12368

ER -