Hierarchical Representation Method for Object Recognition

HUANG Wei-guo; GU Chao; SHANG Li; YANG Jian-yu; ZHU Zhong-kui

doi:10.3969/j.issn.0372-2112.2015.05.004

您当前的位置：

首页 >

文章列表页 >

Hierarchical Representation Method for Object Recognition

更新时间：2025-07-16

- Hierarchical Representation Method for Object Recognition
- Acta Electronica Sinica Vol. 43, Issue 5, Pages: 854-861(2015)
- 作者机构：
  
  1. 苏州大学城市轨道交通学院,江苏,苏州,215131
  2. 苏州职业大学电子信息工程系,江苏,苏州,215000
  3. 苏州大学城市轨道交通学院,江苏,苏州,215131
  4. 苏州职业大学电子信息工程系,江苏,苏州,215000
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2015.05.004
  CLC： TP391.4
- Published：2015
- 稿件说明：
移动端阅览
HUANG Wei-guo, GU Chao, SHANG Li, et al. Hierarchical Representation Method for Object Recognition[J]. Acta Electronica Sinica, 2015, 43(5): 854-861.
DOI：

HUANG Wei-guo, GU Chao, SHANG Li, et al. Hierarchical Representation Method for Object Recognition[J]. Acta Electronica Sinica, 2015, 43(5): 854-861. DOI： 10.3969/j.issn.0372-2112.2015.05.004.

摘要

有效的目标轮廓分段是描述目标局部特征的关键环节.针对现有轮廓描述算法存在轮廓分段不合理的问题

本文基于认知心理学

提出了分层描述的轮廓描述算法.算法思想是首先根据角点特征将整个轮廓划分成一些轮廓分段

接着对轮廓分段的分布特点提出价值尺度

然后将多级轮廓分段按照价值尺度原则合并得到有限个能够完整描述目标轮廓的特征分段

最后将特征分段综合考虑长度尺度应用到Shape Context相似度检测模型中进行目标识别.通过对MPEG-7图像数据库中的图像进行实验分析表明该算法能够完整描述目标图像的形状特征

提高了目标识别率和形状检索率

并对部分遮挡的目标也具有良好的鲁棒性.基本满足目标识别识别和形状检索对准确率、稳定性、抗遮挡能力等方面的要求.

Abstract

Efficient object contour segment is a critical problem to describe the local features of objects.In order to solve the improper contour segments obtained by the existing recognition methods

a hierarchical description algorithm of contour description is proposed.Firstly

the whole contour is divided into several contour segments by the corners on the contour.Then the valuation scale is put forward via the distribution of contour segments.Thirdly

combine these contour segments into several contour feature segments according to the valuation scale.Finally

the similarity of different contour feature segments

in combination with their lengths

is jointly used to get the best recognized results.The experimental results of MPEG-7 database indicate that this algorithm has great advantage over recently published algorithms

especially for the objects with partial occlusion.Hence

this novel algorithm satisfies the requirements of accuracy

robust and anti-occlusion in object recognition and shape retrieval.

关键词

Keywords

references

Views

1698

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Learning Large Scale Class Specific Hyper Graphs for Non-Cooperative Object Recognition

Affine Invariant Pattern Recognition Based on Multi-Scale Autoconvolution Normalized Histograms

Weakly Supervised Learning with Denoising Restricted Boltzmann Machines for Extracting Features

A Fast Computational Algorithm of Multi-Scale Autoconvolution

A Representation of the Fractal Property of Images and Its Applications

Related Author

Edwin Hancock

YU Hua

ZHANG Le-feng

LIU Jian-jun

SONG Rui

XIA Sheng-ping

ZHAO Ji-yin

HUANG Bo

Related Institution

Department of Computer ScienceUniversity of YorkYork UK

State Lab of ATRNational University of Defense TechnologyChangshaHunan 410073China

Department of Computer Science,University of York

State Lab of ATR,National University of Defense Technology

大连民族学院机电信息工程学院辽宁大连

⁰