结合深度卷积网络与加速鲁棒特征配准的图像精准定位

罗家祥; 林畅赫; 王加朋; 胡跃明

doi:10.3788/OPE.20172402.0469

您当前的位置：

首页 >

文章列表页 >

结合深度卷积网络与加速鲁棒特征配准的图像精准定位

信息科学 | 更新时间：2020-07-07

- 结合深度卷积网络与加速鲁棒特征配准的图像精准定位
- Accurate image locating combining deep convolution network with SURF registering
- 光学精密工程 2017年25卷第2期页码：469-476
- 作者机构：
  
  华南理工大学自动化科学与工程学院, 广东广州 510640
- 作者简介：
  
  罗家祥 (1979-), 女, 四川自贡人, 博士, 副教授, 2002年、2007年于东北大学分别获得学士、博士学位, 主要从事生产与优化调度、工业集成自动化过程优化、机器视觉等方面的研究。E-mail:luojx@scut.edu.cn LUO Jia-xiang, E-mail:luojx@scut.edu.cn
  [ "林畅赫 (1990-), 男, 广东饶平人, 2014年于华南理工大学获得学士学位, 主要从事模式识别、图像处理、机器学习等方面的研究。E-mail:lin.changhe@mail.scut.edu.cn" ]
- 基金信息：
  
  国家科技重大专项(2014ZX02503-3);中央高校业务经费(2014z0033);中央高校业务经费(2015ZM137)
- DOI：10.3788/OPE.20172402.0469
  中图分类号： TH703
- 收稿日期：2016-09-01，
  
  录用日期：2016-11-1，
  
  纸质出版日期：2017-02-25
- 稿件说明：
移动端阅览
罗家祥, 林畅赫, 王加朋, 等. 结合深度卷积网络与加速鲁棒特征配准的图像精准定位[J]. 光学精密工程, 2017,25(2):469-476.

Jia-xiang LUO, Chang-he LIN, Jia-peng WANG, et al. Accurate image locating combining deep convolution network with SURF registering[J]. Optics and precision engineering, 2017, 25(2): 469-476.
罗家祥, 林畅赫, 王加朋, 等. 结合深度卷积网络与加速鲁棒特征配准的图像精准定位[J]. 光学精密工程, 2017,25(2):469-476. DOI： 10.3788/OPE.20172402.0469.

Jia-xiang LUO, Chang-he LIN, Jia-peng WANG, et al. Accurate image locating combining deep convolution network with SURF registering[J]. Optics and precision engineering, 2017, 25(2): 469-476. DOI： 10.3788/OPE.20172402.0469.

摘要

针对在大图像中定位小块区域图像的需求，本文提出一种结合深度卷积网络与加速鲁棒特征（SURF）配准的精准定位方法。将标准大区域图像分割成若干个小参考图像，利用深度卷积网络和类局部敏感哈希降维法提取参考图像集的特征并形成特征库；基于特征库，提出了先检索多个相似参考图像后再进行SURF精确配准的两阶段方法，实现目标小图像在标准大图像中的定位。针对电子工业过程中高密度柔性电路板（FPC）及精确末制导中的图像定位数据进行实验，实验结果表明，该方法避免了传统SURF算法大量的特征提取与配对过程，SURF特征提取数减少近90%；与直接根据图像特征进行配准的传统定位方法相比，在保证定位准确率的基础上，耗时可缩小一个数量级以上。

Abstract

For small-scale image locating in a large image

an accurate locating method combining deep convolution network with SURF registering was introduced. The large-scale image was divided into several small reference images

and the feature of such reference image set was extracted to form a feature library by combining the deep convolution network and Similar Local Sensitive Hashing (SLSH); on the basis of the feature library

a two-stage method that carrying out accurate SURF registering after retrieval of multiple similar reference images was put forward to achieve the locating of small target in a large image. Experiment was established on high density FPC and location data of accurate final guidance image

and the results indicate that the method avoids approximately 90% in the amount of feature extraction by comparing with traditional SURF locating methods

in which registering is directly carried out in accordance with image features.So the method can ensure the locating precision

meantime can lower the time consumption by more than one order of magnitudes.

关键词

Keywords

references

ITO M, FUJITA I, TAKEUCHI Y, et al.. Pattern defect analysis and evaluation of printed circuit boards using CAD data[C]. Fifteenth IEEE/CHMT International:Electronic Manufacturing for the Year 2000, Santa Clara, CA:IEEE, 1993:7-10.

范保虎, 赵长明, 马国强.战术导弹成像精确制导技术分析与研究[J].飞航导弹, 2007(1):45-50.

FANG B H, ZHAO CH M, MA G Q.Tactical missile imaging precision guidance technology analysis and research[J].Winged Missile Journal, 2007(1):45-50. (in Chinese)

余先川, 吕中华, 胡丹.遥感图像配准技术综述[J].光学精密工程, 2013, 21(11):2960-2972.

YU X CH, LV ZH H, HU D. Review of remote sensing image registration technique[J].Opt. Precision Eng., 2013, 21(11):2960-2972.(in Chinese)

SUN Y, ZHAO L, HUANG S, et al.. L2-SIFT:SIFT feature extraction and matching for large images in large-scale aerial photogrammetry[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 91:1-16.

丘文涛, 赵建, 刘杰.结合区域分割的SIFT图像匹配方法[J].液晶与显示, 2012, 27(6):827-831.

QIU W T, ZHAO J, LIU J.Image matching algorithm combining SIFT with region segmentation[J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(6):827-831.(in Chinese)

KALIA R, LEE K D, SAMIR B V R, et al.. An analysis of the effect of different image preprocessing techniques on the performance of SURF:Speeded Up Robust Features[C]. The Workshop on Frontiers of Computer Vision, Korea-Japan:IEEE, 2011:1-6.

何林阳, 刘晶红, 李刚, 等.改进BRISK特征的快速图像配准算法[J].红外与激光工程, 2014, 43(8):2722-2727.

HE L Y, LIU J H, LI G, et al.. Fast image registration approach based on improved BRISK[J]. Infrared and Laser Engineering, 2014, 43(8):2722-2727. (in Chinese)

赵辽英, 吕步云, 厉小润, 等.基于尺度不变特征变换和区域互信息优化的多源遥感图像配准[J].物理学报, 2015(12):186-196.

ZHAO L Y, LV B Y, LI X R, et al..Multi-source remote sensing image registration based on scale-invariant feature transform and optimization of regional mutual information[J]. Acta Phys.Sin., 2015(12):186-196.(in Chinese)

CHRISTENSEN G E, RABBITT R D, MILLER M I. Deformable templates using large deformation kinematics[J]. IEEE Transactions on Image Processing, 1996, 5(10):1435-1447.

李玉峰, 李广泽, 谷绍湖, 等.基于区域分块与尺度不变特征变换的图像拼接算法[J].光学精密工程, 2016, 24(5):1197-1205.

LI Y F, LI G Z, GU SH H, et al.. Image mosaic algorithm based on area blocking and SIFT[J]. Opt. Precision Eng., 2016, 24(5):1197-1205. (in Chinese)

王志强, 程红, 杨桄, 等.全局图像配准的目标快速定位方法[J].红外与激光工程, 2015, 44(S):225-229.

WANG ZH Q, CHENG H, YANG G, et al.. Fast target location method of global image registration[J]. Infrared and Laser Engineering, 2015, 44(S):225-229.(in Chinese)

WAN J, WANG D, HOI S C H, et al.. Deep learning for content-based image retrieval:A comprehensive study[C]. Proceedings of the 22nd ACM International Conference on Multimedia, New York:ACM, 2014:157-166.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[C]. Advances in Neural Information Processing Systems, Red Hook, NY:Curran Associates, 2012:1097-1105.

WOLD S, ESBENSEN K, GELADI P. Principal component analysis[J]. Chemometrics and Intelligent Laboratory Systems, 1987, 2(1-3):37-52.

BAY H, ESS A, TUYTELAARS T, et al.. Speeded-up robust features (SURF)[J]. Computer Vision and Image Understanding, 2008, 110(3):346-359.

KRIZHEVSKY A. One weird trick for parallelizing convolutional neural networks[J]. Computing Research Repository, 2014, 3:4-11.

BOUVRIE J. Notes on Convolution Neural networks[R]. MIT CBCL, 2006.

PEREIRA J P, STOJANCIC M M, MERCHANT S. Method and apparatus for multi-dimensional content search and video identification:US, US 8171030 B2[P]. 2012.

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

利用空间分布熵的改进VLAD图像检索

基于聚类和用户兴趣模型的个性化图像搜索

结合主体检测的图像检索方法

基于改进形状上下文特征的二值图像检索

基于局部和全局特征融合的图像检索