结合主体检测的图像检索方法

熊昌镇; 单艳梅; 郭芬红

doi:10.3788/OPE.20172503.0792

您当前的位置：

首页 >

文章列表页 >

结合主体检测的图像检索方法

信息科学 | 更新时间：2020-07-07

- 结合主体检测的图像检索方法
- Image retrieval method based on image principal part detection
- 光学精密工程 2017年25卷第3期页码：792-798
- 作者机构：
  
  1.城市道路交通智能控制技术北京市重点实验室, 北京 100144
  2.北方工业大学理学院, 北京 100144
- 作者简介：
  
  [ "熊昌镇 (1979-), 男, 福建建宁人, 博士, 副教授, 硕士生导师, 2004年于北方工业大学获得硕士学位, 2007年于中山大学获得博士学位, 主要从事交通图像处理和机器学习方面的研究。E-mail:xczkiong@163.com" ]
  [ "单艳梅 (1992-), 女, 河北唐山人, 硕士研究生, 2015年进入北方工业大学学习, 主要研究方向为深度学习和图像检索。E-mail:minions0315@163.com" ]
  郭芬红 (1980-), 女, 山东肥城人, 博士, 讲师, 2004年于北京邮电大学获得硕士学位, 2011年于中山大学获得博士学位, 主要从事图形图象处理方面的研究。E-mail:gfh@ncut.edu.cn GUO Fen-hong, E-mail:gfh@ncut.edu.cn
- 基金信息：
  
  北京市属高等学校青年拔尖人才培育计划资助项目(CIT & TCD201404009);科技创新服务能力建设—科技成果转化—提升计划项目(PXM2016_014212_000036)
- DOI：10.3788/OPE.20172503.0792
  中图分类号： TP391.41
- 收稿日期：2016-12-05，
  
  录用日期：2017-1-14，
  
  纸质出版日期：2017-03-25
- 稿件说明：
移动端阅览
熊昌镇, 单艳梅, 郭芬红. 结合主体检测的图像检索方法[J]. 光学精密工程, 2017,25(3):792-798.

Chang-zhen XIONG, Yan-mei SHAN, Fen-hong GUO. Image retrieval method based on image principal part detection[J]. Optics and precision engineering, 2017, 25(3): 792-798.
熊昌镇, 单艳梅, 郭芬红. 结合主体检测的图像检索方法[J]. 光学精密工程, 2017,25(3):792-798. DOI： 10.3788/OPE.20172503.0792.

Chang-zhen XIONG, Yan-mei SHAN, Fen-hong GUO. Image retrieval method based on image principal part detection[J]. Optics and precision engineering, 2017, 25(3): 792-798. DOI： 10.3788/OPE.20172503.0792.

摘要

为解决图像背景复杂造成图像检索效果差的问题，提出了一种结合主体检测的图像检索方法。该方法首先训练用于目标检测的深度卷积神经网络模型，利用训练好的模型检测查询图像中的物体类别、类别概率和其所在区域坐标及特征。根据物体的类别概率和其所在区域的坐标判断图像主体后，在数据库中查找和主体类别相同的图像。计算查询图像与检索的同类别图像之间区域特征的余弦距离，结合类别概率对所有检索图像进行打分排序，返回分值最高的前10幅图像作为检索结果。最后在VCO2007数据集和自己收集的书页数据集上进行算法验证。实验结果表明，在随机选取的1 000幅测试图片检索结果的全正确率为96.5%，比现有方法提升了6.6个百分点。本文方法可有效排除图像背景的干扰，得到更加准确的检索结果和定位精度。

Abstract

Aimed at the problem-poor result of image retrieval arising from the complexity of image background

a kind of image retrieval method combined with subject detection was put forward. This method has initially trained the deep Convolutional Neural Network (CNN) model used in object detection and used the model detection well trained to inquiry the object class

class probability and the coordinate and feature of region where it was placed in the image. After the image subject estimated in accordance with the object's class probability and coordinate of region where it was placed

the image similar to the subject in the database was found. The cosine distance of region feature between the image inquired and similar image retrieved was caculated

combined with the class probability to carry out grading and sorting for all images retrieved and returned the top 10 images with the highest scores to be as the retrieved result. Finally verification of algorithm was conducted on VCO2007 dataset and paper dataset collected by myself. The experiment result shows that the total accuracy for retrieved result of 1 000 test images is 96.5%

which has raised 6.6 percent points than the existing method. The proposed method can effectively exclude the disturbance of image background and get more accurate retrieved result and location accuracy.

关键词

Keywords

references

吴晓雨, 何彦, 杨磊, 等.基于改进形状上下文特征的二值图像检索[J].光学精密工程, 2015, 23(1): 302-309.

WU X Y, HE Y, YANG L, et al .. Binary image retrieval based on improved shape context algorithm[J]. Opt. Precision Eng., 2015, 23(1): 302-309. (in Chinese)

刘丽, 匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报, 2009, 14(4): 622-635.

LIU L, KUANG G Y. Overview of image textural feature extraction methods [J]. Journal of Image and Graphics , 2009, 14(4): 622-635. (in Chinese)

赵爱罡, 王宏力, 杨小冈, 等.纹理粗糙度在红外图像显著性检测中的应用[J].光学精密工程, 2016, 24(1): 220-228.

ZHAO AI G, WANG H L, YANG X G, et al .. Application of texture coarseness in saliency detection of infrared image [J]. Opt. Precision Eng., 2016, 24(1): 220-228. (in Chinese)

CHEN C C, HSIEH S L. Using binarization and hashing for efficient SIFT matching [J]. Journal of Visual Communication and Image Representation , 2015, 30: 86-93.

DALAL N, TRIGGS B. Histograms of oriented gradients for human detection [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , NJ: IEEE, 2005, 1: 886-893.

SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [J]. CoRR, abs/1409.1556 , 2014.

KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks [C]. In Advances in Neural Information Processing Systems (NIPS) , US: MIT Press, 2012: 1097-1105.

GIRSHICK R, DONAHUE J, DARRELL T, et al .. Rich feature hierarchies for accurate object detection and semantic segmentation [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), NJ: IEEE, 2014:580-587.

GIRSHICK R. Fast R-CNN [C]. Proceedings of the IEEE International Conference on Computer Vision (ICCV), NJ: IEEE, 2015: 1440-1448.

REN SH Q, HE K M, GIRSHICK R, et al .. Faster R-CNN: Towards real-time object detection with region proposal networks [C]. In Advances in Neural Information Processing Systems (NIPS), US: MIT Press, 2015:91-99.

UIJLINGS J RR, SANDE K E A, GEVERS T, et al .. Selective search for object recognition[J]. International Journal of Computer Vision , 2013, 104(2): 154-171.

HE K M, ZHANG X Y, REN SH Q, et al .. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015, 37(9): 1904-1916.

BABENKO A, SLESAREV A, CHIGORIN A, et al .. Neural codes for image retrieval [C]. Proceedings of the European Conference on Computer Vision (ECCV), Berlin:Springer, 2014:584-599.

SALVADOR, AMAIA, GIRO-I-NIETO, et al .. Faster R-CNN features for instance search [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops , NJ: IEEE, 2016.

LIN K, YANG H F, HSIAO J H, et al .. Deep learning of binary hash codes for fast image retrieval [C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop, NJ: IEEE, 2015:27-35.

Han X F, LEUNG T, JIA Y Q, et al .. Matchnet: unifying feature and metric learning for patchbased matching[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), NJ: IEEE, 2015: 3279-3286.

浏览量

621

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于多分支残差注意力网络的水下图像增强

基于策略梯度和伪孪生网络的异源图像匹配

面向点云分类和分割的形状自适应特征聚合网络

基于机载的红外动态目标视频实时超分辨率重建

数据驱动的多模复合制导信息融合及其试验验证