面向仿射目标识别的几何与仿生融合特征提取方法

余伶俐; 易倩; 金鸣岳; 周开军

doi:10.12263/DZXB.20210450

您当前的位置：

首页 >

文章列表页 >

面向仿射目标识别的几何与仿生融合特征提取方法

学术论文 | 更新时间：2025-12-08

- 面向仿射目标识别的几何与仿生融合特征提取方法
- Geometry and Bionic Fusion Feature Extraction Method for Affine Target Recognition
- 电子学报 2023年51卷第6期页码：1607-1618
- 作者机构：
  
  1.中南大学自动化学院，湖南长沙 410083
  2.湖南工商大学智能工程与智能制造学院，湖南长沙 410205
- 作者简介：
  
  [ "余伶俐女，1983年生，江西景德镇人. 中南大学自动化学院教授.主要研究方向为移动机器人导航规划、视觉感知处理.E-mail: llyu@csu.edu.cn" ]
  [ "易倩女，1999年生，湖南长沙人. 中南大学自动化学院硕士研究生.主要研究方向为图像处理、仿生视觉.E-mail: 204612175@csu.edu.cn" ]
  [ "金鸣岳（通讯作者）女，1996年生，河北邯郸人. 中南大学自动化学院硕士研究生. 主要研究方向为仿生视觉感知启发下的不变特征提取方法. E-mail: jinmingyue258@163.com" ]
  [ "周开军男，1979年生，湖南常德人.湖南工商大学智能工程与智能制造学院教授.主要研究方向为机器视觉、图像处理.E-mail: zkj@hutb.edu.cn" ]
- 基金信息：
  
  国家自然科学基金(61976224;61976088)
- DOI：10.12263/DZXB.20210450
  中图分类号： TP391.4;TN911.73
- 收稿：2021-04-09，
  
  修回：2022-04-27，
  
  纸质出版：2023-06-25
- 稿件说明：
移动端阅览
余伶俐,易倩,金鸣岳等.面向仿射目标识别的几何与仿生融合特征提取方法[J].电子学报,2023,51(06):1607-1618.

YU Ling-li,YI Qian,JIN Ming-yue,et al.Geometry and Bionic Fusion Feature Extraction Method for Affine Target Recognition[J].ACTA ELECTRONICA SINICA,2023,51(06):1607-1618.
余伶俐,易倩,金鸣岳等.面向仿射目标识别的几何与仿生融合特征提取方法[J].电子学报,2023,51(06):1607-1618. DOI： 10.12263/DZXB.20210450.

YU Ling-li,YI Qian,JIN Ming-yue,et al.Geometry and Bionic Fusion Feature Extraction Method for Affine Target Recognition[J].ACTA ELECTRONICA SINICA,2023,51(06):1607-1618. DOI： 10.12263/DZXB.20210450.

摘要

针对由于拍摄视角不同，目标图像在水平或垂直方向发生拉长或压缩等仿射变换，进而无法正确识别的问题，本文设计了一种几何与仿生融合的特征提取方法.首先，对传统的角点和直线检测进行改进，提出自适应Harris角点检测方法和去冗余的直线检测方法，并将角点数、直线数和面积比向量作为几何特征.然后，采用生物启发变换算法提取图像的仿生启发特征，该算法包括两个阶段，每个阶段均需执行方向边缘检测和局部空间频率检测.接着，将输入图像的两种特征向量分别与标准数据库中的特征向量进行Pearson相关距离计算，获得匹配得分.最后，在考虑不同数据库两种特征区分性强弱的基础上自适应确定权值，最高融合分数所对应的标签即为该图像的识别结果.实验结果表明，该方法能较好地提取图像的仿射不变特征，并且该方法在Alphanumeric，MPEG-7，GTSRB和MNIST数据库的识别准确率分别为92.2%，96%，90%和87.3%.

Abstract

In view of the problems that the target image is elongated or compressed in the horizontal or vertical direction due to different shooting angles

and the target image cannot be correctly recognized

this paper designs a feature extraction method that combines geometry and bionic vision. Aiming at geometric feature extraction

this paper improves the traditional corner and line detection algorithms

and proposes an adaptive Harris corner detection algorithm based on iterative threshold that draws on the similarity of regional pixels and a de-redundant line detection algorithm based on Hough transform. The number of corner points

the number of straight lines

and the area ratio feature vectors are taken as geometric features. Then

the bio-inspired transformation algorithm is used to extract the bionic visual features of the target image. The algorithm includes two stages. Each stage needs to perform directional edge detection and local spatial frequency detection. Calculate the Pearson correlation distance between the geometric and bionic inspired features of the target image and the features in the standard database to obtain the matching scores. The weights are adaptively determined on the basis of considering the distinguishing strength of the two characteristics of different databases. And the label corresponding to the highest fusion score is the recognition result of the image. Experimental results show that the fusion method can well extract the affine invariance features of affine images. The recognition accuracy of this method in Alphanumeric

MPEG-7

GTSRB and MNIST databases are 92.2%

96%

90% and 87.3% respectively.

关键词

Keywords

references

WANG S J , JIANG F , ZHANG B , et al . Development of UAV-based target tracking and recognition systems [J]. IEEE Transactions on Intelligent Transportation Systems , 2020 , 21 ( 8 ): 3409 - 3422 .

翟颖 , 陈渤 . 基于稳健变分自编码模型的雷达高分辨距离像目标识别算法 [J]. 电子学报 , 2020 , 48 ( 6 ): 1149 - 1155 .

ZHAI Y , CHEN B . Robust variational auto-encoder for radar hrrp target recognition [J]. Chinese Journal of Electronics , 2020 , 48 ( 6 ): 1149 - 1155 . (in Chinese)

HOSNY K M . New set of gegenbauer moment invariants for pattern recognition applications [J]. Arabian Journal for Science and Engineering , 2014 , 39 ( 10 ): 7097 - 7107 .

WANG H , WEI S B , FANG B F . Facial expression recognition using iterative fusion of MO-HOG and deep features [J]. The Journal of Supercomputing , 2020 , 76 ( 5 ): 3211 - 3221 .

YANG X F , WANG W S , LIU L M , et al . Robust 2DPCA by T1 criterion maximization for image recognition [J]. IEEE Access , 2021 , 9 : 7690 - 7700 .

MOREL J M , YU G S . ASIFT: A new framework for fully affine invariant image comparison [J]. SIAM Journal on Imaging Sciences , 2009 , 2 ( 2 ): 438 - 469 .

MAIER J , HUMENBERGER M , MURSCHITZ M , et al . Guided matching based on statistical optical flow for fast and robust correspondence analysis [C]// European Conference on Computer Vision . Virtual Conference : Springer , 2016 , 9911 : 101 - 117 .

HUANG T , ZHANG Q X , LIU J B , et al . Adversarial attacks on deep-learning-based SAR image target recognition [J]. Journal of Network and Computer Applications , 2020 , 162 ( 12 ): 102632 .

郝彤 , 赵杰 . 面向双曲线形态的探地雷达图像识别技术综述 [J]. 电子学报 , 2019 , 47 ( 6 ): 1366 - 1372 .

HAO T , ZHAO J . A brief review of the hyperbola signature recognition techniques for ground penetrating radar [J]. Chinese Journal of Electronics , 2019 , 47 ( 6 ): 1366 - 1372 . (in Chinese)

胡欣 , 许新芳 , 陈娇 . 仿射不变性特征提取在目标识别中的应用 [J]. 兵工自动化 , 2013 ( 8 ): 84 - 87 .

HU X , XU X F , CHEN J . Affine invariability feature extraction in application of target recognition [J]. Ordnance Industry Automation , 2013 ( 8 ): 84 - 87 . (in Chinese)

KAZMI W , ANDERSEN H J . A comparison of interest point and region detectors on structured, range and texture images [J]. Journal of Visual Communication and Image Representation , 2015 , 32 : 156 - 169 .

叶正麟 , 安晓虹 . 线性代数变换与仿射几何变换 [J]. 高等数学研究 , 2021 , 24 ( 1 ): 1 - 4 .

YE Z L , AN X H . Algebra transformation and affine transformation [J]. Studies in College Mathematics , 2021 , 24 ( 1 ): 1 - 4 . (in Chinese)

PATOOMMAKESORN K , VIGNAT F , VILLENEUVE F . A new straight line matching technique by integration of vision-based image processing [J]. Procedia CIRP , 2016 , 41 : 777 - 782

高峰 , 文贡坚 . 利用仿射几何的仿射不变特征提取方法 [J]. 中国图象图形学报 , 2011 , 16 ( 3 ): 389 - 397 .

GAO F , WEN G J . Affine invariant feature extraction based on affine geometry [J]. Chinese Journal of Image and Graphics , 2011 , 16 ( 3 ): 389 - 397 . (in Chinese)

LU Y F , QIAO H , LI Y , et al . Image recommendation based on a novel biologically inspired hierarchical model [J]. Multimedia Tools and Applications , 2017 , 77 ( 4 ): 4323 - 4337 .

KARIMI H S , MOHAMMADI K . Rotational invariant biologically inspired object recognition [J]. IET Image Processing , 2020 , 14 ( 15 ): 3762 - 3773 .

ZHOU X , ZHOU K J , SHEN L . Rotation and translation invariant palmprint recognition with biologically inspired transform [J]. IEEE Access , 2020 , 8 : 80097 - 80119 .

MOYOU M , ANAND R , JOHN C , et al . A grassmannian graph approach to affine invariant feature matching [J]. IEEE Transactions on Image Processing , 2020 , 29 : 3374 - 3387 .

DEVI D R , KATTAMURI N R . Sub-band-based feature fusion and hybrid fusion approaches for multimodal biometric identification [J]. International Journal of Biometrics , 2020 , 12 ( 4 ): 357 - 376 .

PITITHEERAPHAB Y , THONGPANCE N , AOYAMA H , et al . Vein pattern verification and identification based on local geometric invariants constructed from minutia points and augmented with barcoded local feature [J]. Applied Sciences , 2020 , 10 ( 9 ): 3192 .

余伶俐 , 夏旭梅 , 周开军 , 等 . 基于仿生视觉的图像RST不变属性特征提取方法 [J]. 仪器仪表学报 , 2017 , 38 ( 4 ): 985 - 995 .

YU L L , XIA X M , ZHOU K J , et al . RST-invariant feature extraction method inspired by bionic visual perception [J]. Chinese Journal of Scientific Instrument , 2017 , 38 ( 4 ): 985 - 995 . (in Chinese)

WANG Z C , LI R , SHAO Z H , et al . Adaptive Harris corner detection algorithm based on iterative threshold [J]. Modern Physics Letters B , 2017 , 31 ( 15 ): 1750181 .

AGGARWAL N , KARL W C . Line detection in images through regularized Hough transform [J]. IEEE Transactions on Image Processing , 2006 , 15 ( 3 ): 582 - 591 .

宋晓宇 , 袁帅 , 郭寒冰 , 等 . 基于自适应阈值区间的广义Hough变换图形识别算法 [J]. 仪器仪表学报 , 2014 , 35 ( 5 ): 1109 - 1117 .

SONG X Y , YUAN S , GUO H B , et al . Pattern identification algorithm with adaptive threshold interval based extended Hough transform [J]. Chinese Journal of Scientific Instrument , 2014 , 35 ( 5 ): 1109 - 1117 . (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据