文献详情
Interest Point Detection by Limiting Form of Median Log Filter
文献类型期刊
作者Chen, Junzhang[1];Lyu, Mengyao[2];Wang, Xing[3];Bai, Xiangzhi[4];Yang, Chao[5];Liu, Miaoming[6];Zhou, Fugen[7]
机构
2019
通讯作者Bai, XZ (reprint author), Beijing Univ Aeronaut & Astronaut, Image Proc Ctr, Beijing 100191, Peoples R China.; Wang, X (reprint author), Syst Control & Intelligent Agent Cooperat Lab, Sci & Technol Complex, Beijing 100074, Peoples R China.; Bai, XZ (reprint author), Beihang Univ, State Key Lab Virtual Real Technol & Syst, Beijing 100191, Peoples R China.; Bai, XZ (reprint author), Beihang Univ, Adv Innovat Ctr Biomed Engn, Beijing 100083, Peoples R China.
期刊名称IEEE ACCESS影响因子和分区
来源信息年:2019  卷:7  页码范围:84182-84196  
7
期刊信息IEEE ACCESS影响因子和分区  ISSN:2169-3536
页码范围84182-84196
关键词Feature extraction; image registration; interest point detection; Laplacian of Gaussian filter
增刊正刊
摘要Interest point detection has been widely used in image analysis applications. However, some interest points, including small structures and large angle corners, could not be effectively extracted. This paper proposes a limiting form of median Laplacian of Gaussian (LMLG) filter, which combines the superiority of the traditional Laplacian of Gaussian (LoG) filter and a limiting form of the weighted median LoG filter. A detector is also proposed based on the LMLG filter. The LMLG filter aims to improve the detection of LoG-based methods for interest points, especially small structures and large angle corners. Also, it could detect blobs, edges, and local structures. We conduct the repeatability and discrimination experiments on the Oxford dataset. Moreover, we conduct the recall rate experiment on the DTU dataset. The experiments show that the proposed method achieves comparable performance with state-of-the-art methods. In order to verify the utility of the LMLG detector, we carry out a series of interest point detector-based applications: face recognition, infrared-visible image registration, and image classification. The results demonstrate that the LMLG detector performs better than the nine detectors in face recognition. The LMLG detector outperforms the nine detectors and Hrkac's, Han's and Liu's methods in infrared-visible image registration. Our method also gives a comparable result on image classification. The source code of the proposed LMLG detector is made publicly available at https://github.com/chenjzBUAA/LMLG-detector.
收录情况SCIE(WOS:000475918200001)  EI(20192907199831)  
所属部门计算机学院;生物与医学工程学院;宇航学院
DOI10.1109/ACCESS.2019.2924238
百度学术Interest Point Detection by Limiting Form of Median Log Filter
语言外文
ISSN2169-3536
人气指数58
浏览次数58
基金National Natural Science Foundation of China [U1736217]; Fundamental Research Funds for the Central Universities [YWF-19-BJJ-43]; Program for New Century Excellent Talents in Universities [NCET-13-0020]
全部评论(0 条评论)
作者其他论文

Feature based fuzzy inference system for segmentation of low-contrast infrared ship images.

Bai, Xiangzhi;Liu, Miaoming;Wang, Tao,等.APPLIED SOFT COMPUTING.2016,46,128-142.

Semi-automated infrared simulation on real urban scenes based on multi-view images.

Xiong, Xixian;Zhou, Fugen;Bai, Xiangzhi,等.OPTICS EXPRESS.2016,24(11),1345-1375.

Infrared ship target segmentation through integration of multiple feature maps.

Liu, Zhaoying;Bai, Xiangzhi;Sun, Changming,等.IMAGE AND VISION COMPUTING.2016,48-49,14-25.

Determination of the Dynamic Characteristics of a Multi-Point Excitation System Using Electrodynamic Shakers and Control of their Exciting Force.

Ma, Chengji;Wu, Zhigang;Yang, Chao.JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES.2016,4(2),161-173.

登录