噪声不敏感的柱状图特征描述符及其在图像检索中的应用

doi:10.11896/j.issn.1002-137X.2016.01.065

摘要/Abstract

摘要： 基于内容的图像检索方法往往将图片的内容表示成柱状图,根据图片柱状图之间的相似性进行图片的检索。数码图片中包含的噪声使得柱状图变得平滑,从而使图片之间变得更为相似,这增加了返回结果中包含的图片数量。为了进一步提高图片检索的性能,提出了一种对噪声不敏感的柱状图特征描述符,并应用该特征描述符进行图像之间的相似性匹配。首先将图片中的噪声描述为平稳附加高斯白噪声,并给出了相应的柱状图表示；然后通过随机变量的原点矩定义了柱状图的特征描述符,并分析了如何应用特征描述符恢复原始图片的柱状图。在算法的性能验证过程中,将提出的方法与4种相关算法进行比较,应用两个真实的图片数据库的图像检索实验验证了所提方法的有效性。

关键词: 图像检索,柱状图,噪声,特征描述符

Abstract: Content based image retrieval methods usually represent images as histograms,and retrieve images based on similarity between images.The noise in digital photography makes its histogram even more smoothing,and at the same time,makes two images more similar,which increases the number of result images during retrieving.In order to improve the performance of image retrieval,this paper proposed a feature descriptor,which is insensitive to noise for histogram,and computed similarities between images based on the proposed feature descriptor.We described the noise in an image as stationary additive Gaussian white noise,and gave its corresponding histogram.Then,we defined the feature descriptor of histogram by the general moments of random variable,and analyzed how to recover original histogram of an image using the proposed feature descriptor.During the validation of the proposed method,we compared it with four popular related algorithms,and validated its efficiency according to image retrieval experiments in two real image databases.

Key words: Image retrieval,Histogram,Noise,Feature descriptor

刘淑琴,彭进业. 噪声不敏感的柱状图特征描述符及其在图像检索中的应用[J]. 计算机科学, 2016, 43(1): 302-305. https://doi.org/10.11896/j.issn.1002-137X.2016.01.065

LIU Shu-qin and PENG Jin-ye. Noise Insensitive Feature Descriptors for Histogram and Application in Image Retrieval[J]. Computer Science, 2016, 43(1): 302-305. https://doi.org/10.11896/j.issn.1002-137X.2016.01.065

参考文献

[1] Li Xiang-yang,Lu Dong-ming.Study of Color Based Retrieval for Image Database[J].Journal of Computer Research and Development,1999(3):359-363(in Chinese) 李向阳,鲁东明.基于色彩的图像数据库检索方法的研究[J].计算机研究与发展,1999(3):359-363
[2] Cui Chao-ran,Ma Jun.An Image Tag Recommendation Approach Combining Relevance with Diversity[J].Chinese Journal of Computers,2013,6(3):654-663(in Chinese) 崔超然,马军.一种结合相关性和多样性的图像标签推荐方法[J].计算机学报,2013,36(3):654-663
[3] Dharani T,Aroquiaraj I L.A survey on content based image retrieval[C]∥2013 International Conference on Pattern Recognition,Informatics and Mobile Engineering (PRIME).IEEE,2013:485-490
[4] Wen Yu-feng,Zhou Ji-liu,Zhou Yang.Implementation of CBIR engine on the distributed environment[J].Journal of Sichuan University(Natural Science Edition),2007,4(5):995-999(in Chinese) 文宇峰,周激流,周扬.分布式计算环境下CBIR 检索引擎的实现[J].四川大学学报(自然科学版),2007,44(5):995-999
[5] Wang Tao,Hu Shi-min,Sun Jia-guang.Image Retrieval Based on Color-Spatial Feature[J].Journal of Software,2002,3(10):2031-2036(in Chinese) 王涛,胡事民,孙家广.基于颜色-空间特征的图像检索[J].软件学报,2002,13(10):2031-2036
[6] Liu G H,Yang J Y.Content-based image retrieval using color difference histogram[J].Pattern Recognition,2013,46(1):188-198
[7] Pass G,Zabih R.Histogram refinement for content-based image retrieval[C]∥Proceedings 3rd IEEE Workshop on Applications of Computer Vision,1996(WACV’96).IEEE,1996:96-102
[8] Xiaoling W.A novel circular ring histogram for content-based image retrieval[C]∥First International Workshop on Education Technology and Computer Science,2009(ETCS’09).IEEE,2009:785-788
[9] Rashedi E,Nezamabadi-Pour H,Saryazdi S.A simultaneous feature adaptation and feature selection method for content-based image retrieval systems[J].Knowledge-Based Systems,2013,39(2):85-94
[10] Yu H,Li M,Zhang H J,et al.Color texture moments for content-based image retrieval[C]∥2002 International Conference on Image Processing.2002.IEEE,2002:929-932
[11] Liu G H,Zhang L,Hou Y K,et al.Image retrieval based onmulti-texton histogram[J].Pattern Recognition,2010,43(7):2380-2389
[12] Mandal M K,Aboulnasr T,Panchanathan S.Image indexingusing moments and wavelets[J].IEEE Transactions on Consumer Electronics,1996,42(3):557-565
[13] Yap P T,Paramesran R.Content-based image retrieval usingLegendre chromaticity distribution moments[J].IEE Procee-dings-Vision,Image and Signal Processing,2006,153(1):17-24
[14] Pyatykh S,Hesser J,Zheng L.Image noise level estimation by principal component analysis[J].IEEE Transactions on Image Processing,2013,22(2):687-699
[15] Philbin J,Chum O,Isard M,et al.Object retrieval with large vocabularies and fast spatial matching[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2007(CVPR’07).IEEE,2007:1-8
[16] Jegou H,Douze M,Schmid C.Hamming embedding and weak geometric consistency for large scale image search[M]∥Computer Vision-ECCV 2008.Springer Berlin Heidelberg,2008:304-317
[17] Hua Xing-yan,Wu Zong-jia.Processing Method of Image Captured by Photo-electronic Theodolite Based on Gray System Theory[J].Journal of Sichuan Ordnance,2014,35(6):98-100(in Chinese) 花兴艳,吴宗佳.基于灰色系统理论的经纬仪噪声图像处理方法[J].四川兵工学报,2014,35(6):98-100

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed