版权说明 帮助中心
首页 > 成果 > 详情

Affine invariant fusion feature extraction based on geometry descriptor and BIT for object recognition

SCI-E
认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Yu, Lingli;Xia, Xumei;Zhou, Kiajun*;Zhao, Lijun
通讯作者:
Zhou, Kiajun
作者机构:
[Yu, Lingli; Zhao, Lijun] Harbin Inst Technol, State Key Lab Robot & Syst, Harbin, Heilongjiang, Peoples R China.
[Yu, Lingli; Xia, Xumei] Cent S Univ, Sch Informat Sci & Engn, Changsha, Hunan, Peoples R China.
[Zhou, Kiajun] Hunan Univ Commerce, Sch Comp & Informat Engn, Changsha, Hunan, Peoples R China.
通讯机构:
[Zhou, Kiajun] Hunan Univ Commerce, Sch Comp & Informat Engn, Changsha, Hunan, Peoples R China.
语种:
英文
关键词:
feature extraction;image recognition;affine transforms;object recognition;face recognition;edge detection;valuable technology;image recognition;bio-visual mechanism;object recognition method;fusion feature framework;geometry descriptor;double biologically inspired transformation;shape feature;interest detector;contour features;area estimation;affine region detector;area ratio feature vectors;orientation edge detector;local space frequency detector;DBIT feature vectors;weighted fusion strategy;Pearson correlation distance;geometry feature;highly stable recognition accuracy;feature invariance;selectivity;affine invariant fusion feature extraction;affine transformation;viewing angle;distance variations;affine invariant feature extraction
期刊:
IET IMAGE PROCESSING
ISSN:
1751-9659
年:
2019
卷:
13
期:
1
页码:
57-72
文献类别:
WOS:Article
所属学科:
WOS学科类别:Computer Science, Artificial Intelligence;Engineering, Electrical & Electronic;Imaging Science & Photographic Technology
入藏号:
基金类别:
State Key Laboratory of Robotics and System (HIT) [SKLRS-2017-KF-13]; State Key Laboratory of Mechanical Transmissions of Chongqing University [SKLMT-KFKT-201602]; National Natural Science Foundation of China [61403426]; Major Projects of Science and Technology in Hunan [2017GK1010]; National Key Research and Development Plan [2018YFB1201602]; Natural Science Foundation of Hunan [2018JJ2531]; Fundamental research funds for the central universities of Central South University [2017zzts490]
机构署名:
本校为通讯机构
院系归属:
计算机与信息工程学院
摘要:
It is difficult to recognise an image with affine transformation due to viewing angle and distance variations. Therefore, affine invariant feature extraction is a valuable technology in the field of image recognition. Inspired by bio-visual mechanism, an affine invariant for object recognition method based on a fusion feature framework is proposed in this study, which employs geometry descriptor and double biologically inspired transformation (DBIT). First, a shape feature of interest detector is adopted to detect contour features. Then, the area estimation of affine region detector is utilised to construct area ratio feature vectors. Second, an orientation edge detector is built to highlight the edges of different directions. On this basis, local space frequency detector is adopted to measure the spatial frequency at each direction and interval, which converts the output map into DBIT feature vectors. A weighted fusion strategy is performed based on Pearson correlation distance to fuse the geometry feature and DBIT feature. Some tests for Alphanumeric, Coil-100 MPEG-7, Mixed National Institute of Standards and Technology (MNIST) and Olivetti Research Laboratory face images database (ORL) database remain highly stable recognition accuracy, even when the shear factor is between -0.5 and +0.5. The experiment results show the authors' proposed approach has a nice performance in feature invariance, selectivity and recognition accuracy.
参考文献:
Adamek T, 2004, IEEE T CIRC SYST VID, V14, P742, DOI 10.1109/TCSVT.2004.826776
Alajlan N, 2007, PATTERN RECOGN, V40, P1911, DOI 10.1016/j.patcog.2006.12.005
Alameer A, 2016, IEEE SIGNAL PROC LET, V23, P1062, DOI 10.1109/LSP.2016.2582541
[Anonymous], 2010, COLUMBIA U COIL 100
Anvaripour M, 2015, PATTERN ANAL APPL, V18, P277, DOI 10.1007/s10044-013-0342-x

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com