An Image Classification Method Using Graphically Regularized Coding Algorithm

YANG Sai; ZHAO Chun-xia; HU Bin; CHEN Feng

doi:10.3969/j.issn.0372-2112.2017.08.011

您当前的位置：

首页 >

文章列表页 >

An Image Classification Method Using Graphically Regularized Coding Algorithm

更新时间：2025-07-16

- An Image Classification Method Using Graphically Regularized Coding Algorithm
- Acta Electronica Sinica Vol. 45, Issue 8, Pages: 1882-1887(2017)
- 作者机构：
  
  1. 南通大学电气工程学院,南通,226019
  2. 南京理工大学计算机科学与工程学院,江苏,南京,210094
  3. 南通大学计算机科学与技术学院,江苏,南通,226019
  4. 南通大学电气工程学院,南通,226019
  5. 南京理工大学计算机科学与工程学院,江苏,南京,210094
  6. 南通大学计算机科学与技术学院,江苏,南通,226019
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2017.08.011
  CLC： TP391.4
- Published Online：25 August 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
YANG Sai, ZHAO Chun-xia, HU Bin, et al. An Image Classification Method Using Graphically Regularized Coding Algorithm[J]. Acta Electronica Sinica, 2017, 45(8): 1882-1887.
DOI：

YANG Sai, ZHAO Chun-xia, HU Bin, et al. An Image Classification Method Using Graphically Regularized Coding Algorithm[J]. Acta Electronica Sinica, 2017, 45(8): 1882-1887. DOI： 10.3969/j.issn.0372-2112.2017.08.011.

摘要

为了解决经典局部特征编码方法会产生相似局部特征之间编码系数不一致的问题，本文提出一种图正则化局部特征编码算法.该算法在对初始编码矢量所定义的能量化函数中引入正则化项，保证空间上相邻外观上相似的局部特征之间的编码矢量尽可能一致.MSRcv2、Caltech101、Scene 15以及Indoor 67四个公开数据集上的实验结果表明本文方法能够提高硬分配、软分配、稀疏编码、局部约束线性编码以及局部软分配五种经典编码方法的性能，并且基于本文编码算法的图像分类方法在上述四个公开数据集上的平均分类正确率分别达到了91.13%、76.02%、83.76%、44.78%.

Abstract

In order to solve the problem that current coding schemes lost consistence between similar local features

this paper proposes a new graphically regularized coding algorithm.This algorithm used any current coding scheme to get the initial coding coefficients

and utilized a regularized term to preserve locality constrains both in the feature space and the spatial domain of the image.Experimental results on popular benchmark datasets show that our method improves the performances of the current coding algorithms

and the average classification accuracies of our proposed method in MSRcv2

Caltech101

Scene15

Indoor 67 and UIUC-sport has reached 91.13%

76.02%

83.76%

44.78% and 89.05% respectively.

关键词

Keywords

references

Views

495

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image Classification Network of Background Perception Mechanism

Image Classification Algorithm Based on Coordinate Importance Pooling and Decoupled Class Alignment Distillation

Feature Anomaly Detection and Pseudo-Label Regression for Adversarial Domain Adaptation

Graph-Based Representation Knowledge Distillation for Image Classification

Related Author

YUAN Heng

RAN Chao

ZHANG Sheng-chong

LIU Ying

XUE Jia-hao

ZHANG Wei-dong

XU Zhi-jie

PAN Jie

Related Institution

Key Laboratory of Optoelectronic Information Control and Security Technology

School of Software, Liaoning Technical University

Center for Image and Information Processing, Xi’an University of Posts and Telecommunications

International Joint-Research Center for Wireless Communication and Information Processing

University of Huddersfield, West Yorkshire HD13DH, United Kingdom of Great Britain and Northern Ireland

⁰