Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification

Jinjun KUANG; Yi CHAI

doi:10.1587/transinf.E96.D.758

Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification

Jinjun KUANG, Yi CHAI

Full Text Views

0

Share
Cite this

Summary :

This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for ₁ minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.

Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.3 pp.758-761

Publication Date: 2013/03/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E96.D.758

Type of Manuscript: LETTER

Category: Image Recognition, Computer Vision

Cite this

Copy

Jinjun KUANG, Yi CHAI, "Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification" in IEICE TRANSACTIONS on Information, vol. E96-D, no. 3, pp. 758-761, March 2013, doi: 10.1587/transinf.E96.D.758.
Abstract: This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for ₁ minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E96.D.758/_p

Copy

@ARTICLE{e96-d_3_758,
author={Jinjun KUANG, Yi CHAI, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification},
year={2013},
volume={E96-D},
number={3},
pages={758-761},
abstract={This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for ₁ minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.},
keywords={},
doi={10.1587/transinf.E96.D.758},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification
T2 - IEICE TRANSACTIONS on Information
SP - 758
EP - 761
AU - Jinjun KUANG
AU - Yi CHAI
PY - 2013
DO - 10.1587/transinf.E96.D.758
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2013
AB - This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for ₁ minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.
ER -