A Method of Image Content Matching with Lattice Closeness and Multi-Feature Fusion

doi:10.7652/xjtuxb201904017

您当前的位置：

首页 >

文章列表页 >

A Method of Image Content Matching with Lattice Closeness and Multi-Feature Fusion

更新时间：2025-07-09

- A Method of Image Content Matching with Lattice Closeness and Multi-Feature Fusion
- Vol. 53, Issue 4, Pages: 115-121(2019)
- 作者机构：
  
  湖南工业大学计算机学院,湖南,株洲,412007
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201904017
  CLC： TP391
- Online First：10 April 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
A Method of Image Content Matching with Lattice Closeness and Multi-Feature Fusion[J]. 2019, 53(4): 115-121.
DOI：

A Method of Image Content Matching with Lattice Closeness and Multi-Feature Fusion[J]. 2019, 53(4): 115-121. DOI： 10.7652/xjtuxb201904017.

摘要

针对目前基于内容的图像检索方法中存在噪声、边界划分模糊及相似匹配算法复杂而检索精度不高的问题

提出了一种多特征融合的格贴近度图像内容匹配方法。为了抑制噪声

对像素间的灰度关系S

与空间关系S

进行合成

提出了邻域窗口像素灰度特征描述子; 为了对组成图像的对象的边界进行分割

设计了一个像素密度分布特征描述子; 在对图像的灰度、纹理及密度特征进行融合的基础上

提出了一种格贴近度图像匹配方法

实现了两图像相似性比较。实验结果表明:在灰度图像的相似性检索中

多特征融合的格贴近度匹配方法与特征压缩匹配及兴趣区域匹配等其他方法相比

平均归一化修正检索秩低10%左右

查准率-查全率综合评价指标高5%左右

该方法不仅设计简单

而且具有较高的检索精度。

Abstract

An image content matching method with lattice closeness and multi-feature fusion is proposed to improve the problem of low retrieval performance in content-based image retrieval. Firstly

an original image is scaled and segmented by clustering to obtain various objects of the image. Then

a gray feature descriptor is defined taking pixel gray and spatial relations into account. The texture and pixel density distribution of the object are integrated

and a set of feature vectors is obtained according to their weights. Lastly

the matching degree of the image is calculated based on lattice closeness. Theoretical analysis and experimental results show that this method has higher retrieval precision in the similarity matching retrieval of gray images.

关键词

Keywords

references

ELALAMI M E. A new matching strategy for content based image retrieval system [J]. Applied Soft Computing, 2014, 14(1): 407-418.

ZHOU Zhengzhong, ZHANG Liqing. Content-based image retrieval using iterative search [J]. Neural Processing Letters, 2018, 47(3): 907-919.

WANG Han, LIANG Wei, WU Xinxiao, et al. Scene image retrieval via re-ranking semantic and packed dense interest points [J]. Neurocomputing, 2013, 119(16): 65-73.

NISHANT S, VIPIN T. Content based image retrieval based on relative locations of multiple regions of interest using selective regions matching [J]. Information Sciences, 2014, 259: 212-224.

KHAN Y D, AHMAD F, KHAN S A, et al. Content-based image retrieval using extroverted semantics: a probabilistic approach [J]. Neural Computing and Applications, 2014, 24(7/8): 1735-1748.

HSIAO M, HUANG Y, TSAI T, et al. An efficient and flexible matching strategy for content-based image retrieval [J]. Life Science Journal, 2010, 7(1): 99-106.

熊钢, 平西建, 张涛, 等. 一种基于图像内容的最低有效位匹配隐写分析方法 [J]. 电子与信息学报, 2012, 34(6): 1380-1387.

XIONG Gang, PING Xijian, ZHANG Tao, et al. An approach of detecting least significant bit matching based on image content [J]. Journal of Electronics Information Technology, 2012, 34(6): 1380-1387.

HARALICK R M, SHANMUGAM K, DINSTEIN I. Textural features for image classification [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1973, 3(6): 610-621.

MEHTA R, YUAN J, EGIAZARIAN K, et al. Face recognition using scale-adaptive directional and textural features [J]. Pattern Recognition, 2014, 47(5): 1846-1858.

MARTINEZ-MURCIA F J, GOÓRRIZ J M, RAMIÍREZ J, et al. Parametrization of textural patterns in I-123-ioflupane imaging for the automatic detection of Parkinsonism [J]. Medical Physics, 2014, 41(1): 012502.

SAMIEE K, KIRANYAZ S, GABBOUJ M, et al. Long-term epileptic EEG classification via 2D mapping and textural features [J]. Expert Systems with Application, 2015, 42(20): 7175-7185.

张翔, 王诗琪, 张新峰, 等. 视频局部特征描述子的紧凑表示方法 [J]. 中国图象图形学报, 2016, 21(3): 390-395.

ZHANG Xiang, WANG Shiqi, ZHANG Xinfeng, et al. Compact representation of video local feature descriptors [J]. Journal of Image Graphics, 2016, 21(3): 390-395.

黄明明. 图像局部特征提取及应用研究 [D]. 北京: 北京科技大学, 2016: 22-25.

ZHU C, BICHOT C E, CHEN L, et al. Image region description using orthogonal combination of local binary patterns enhanced with color information [J]. Pattern Recognition, 2013, 46(7): 1949-1963.

谢博鋆, 朱杰, 于剑. 基于Pivots选择的有效图像块描述子 [J]. 软件学报, 2015, 26(11): 2930-2938.

XIE Bojun, ZHU Jie, YU Jian. Efficient patch-level descriptor for image categorization via patch Pivots selection [J]. Journal of Software, 2015, 26(11): 2930-2938.

TORIU T, HIRONAGA M, HASEBE M. Two methods for color constancy based on the color correlation matrix [J]. Genetic and Evolutionary Computing, 2016, 387: 165-173.

肖满生, 吴卫, 王宏. 基于邻域灰度值聚类的图像色彩量化 [J]. 控制与决策, 2013, 28(6): 935-939.

XIAO Mansheng, WU Wei, WANG Hong. Image color quantization based on clustering of neighborhood gray level [J]. Control and Decision, 2013, 28(6): 935-939.

FALLAHI A, KHOTANLOU H, POOYAN M, et al. Segmentation of uterine using neighborhood information affected possibilistic FCM and Gaussian mixture model in uterine fibroid patients MRI [J]. Biomedical Engineering: Applications, Basis and Communications, 2014, 26(1): 1450010.

王春静, 许圣梅. 基于内容的图像检索的相似度测量方法 [J]. 数据采集与处理, 2017, 32(1): 104-110.

WANG Chunjing, XU Shengmei. Effective similarity measure method for content-based image retrieval [J]. Journal of Data Acquisition Processing, 2017, 32(1): 104-110.

JIN Cong, KE Shanwu. Content-based image retrieval based on shape similarity calculation [J]. 3D Research, 2017, 8(3): 22-40.

杨纶标, 高英仪. 模糊数学原理及应用 [M]. 广州: 华南理工大学出版社, 2006: 33-37.

MANJUNATH B S, OHM J R, VASUDEVAN V V, et al. Color and texture descriptors [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2011, 11(6): 703-715.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Image Super Resolution Algorithm Based on Receptive Field Optimization and Progressive Feature Fusion

Research on Railway Track Foreign Object Intrusion Detection Based on Multi-Scale Feature Fusion

Anomaly Detection Method Based on One-Class Random Forest with Applications

Spatial Attention Mechanism with Global Characteristics

Numerical Simulation of Heat-Moisture Barrier Performance of a Horizontal Air Curtain in Cold Storage

Related Author

WU Hongwu

GAI Shaoyan

DA Feipeng

WANG Nan

HOU Tao

NIU Hongxia

张西宁

张雯雯

Related Institution

School of Automation, Southeast University

Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University

(School of Automation and Electrical Engineering, Lanzhou Jiaotong University,,)

State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University

School of Information and Communications Engineering, Xi’an Jiaotong University

⁰