计算机科学 ›› 2021, Vol. 48 ›› Issue (8): 191-199.doi: 10.11896/jsjkx.200800202

• 计算机图形学& 多媒体 • 上一篇    下一篇

基于模糊颜色特征和模糊相似度的图像检索方法

王春静, 刘丽, 谭艳艳, 张化祥   

  1. 山东师范大学信息科学与工程学院 济南250014; 山东省分布式计算机软件新技术重点实验室 济南250014
  • 收稿日期:2020-08-29 修回日期:2020-10-07 发布日期:2021-08-10
  • 通讯作者: 王春静(wjzj_1978@126.com)
  • 基金资助:
    国家自然科学基金(61702310,61401260)

Image Retrieval Method Based on Fuzzy Color Features and Fuzzy Smiliarity

WANG Chun-jing, LIU Li, TAN Yan-yan, ZHANG Hua-xiang   

  1. School of Information Science and Engineering,Shandong Normal University,Jinan 250014,China;Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology,Jinan 250014,China
  • Received:2020-08-29 Revised:2020-10-07 Published:2021-08-10
  • About author:WANG Chun-jing,born in 1978,master,assisitant professor,is a member of China Computer Federation.Her main research interests include machine learning and pattern recognition.
  • Supported by:
    National Natural Science Foundation of China (61702310,61401260).

摘要: 基于内容的图像检索系统的性能主要依赖于两个关键技术:图像特征提取和图像特征匹配。文中提取了所有图像的颜色特征,并在颜色特征提取过程中采用了适当的模糊算法以得到图像的模糊颜色特征。图像特征匹配主要取决于两个图像特征向量之间的相似度,文中提出了一种新的模糊相似度衡量方法,该方法利用给定的查询图像与其k幅近邻图像之间的相似度构成查询图像的k维模糊特征向量,利用每幅被检索图像与查询图像的k幅近邻图像之间的相似度构成每幅被检索图像的k维模糊特征向量,计算查询图像的k维模糊特征向量与每幅被检索图像的k维模糊特征向量之间的模糊相似度,并将检索到的图像按照模糊相似度按从大到小的顺序反馈给用户。为了验证提出的模糊颜色特征的有效性,文中在WANG数据集上进行了一系列的实验对比;为了衡量基于不同相似度的图像检索系统的性能,文中在WANG,Corel-5k和Corel-10k数据集上分别进行了一系列的实验对比。实验结果表明,基于最大最小值的图像检索系统的性能优于基于其他3种常用相似度的图像检索系统的性能,而基于模糊相似度的图像检索系统的性能优于基于最大最小值的图像检索系统的性能。在WANG,Corel-5k和Corel-10k数据集上,基于模糊相似度的图像检索系统检索到的前20幅图像的平均查准率比基于最大最小值的图像检索系统检索到的前20幅图像的平均查准率分别高4.92%,17.11%和19.48%;基于模糊相似度的图像检索系统检索到的前100幅图像的平均查准率比基于最大最小值的图像检索系统检索到的前100幅图像的平均查准率分别高4.94%,22.61%和33.02%。

关键词: 查准率, 基于内容的图像检索, 近邻图像, 模糊相似度, 模糊颜色特征, 平均查准率

Abstract: The performance of content-based image retrieval(CBIR) system mainly depends on two key technologies:image feature extraction and image feature matching.In this paper,the color features of all the images are extracted,and an appropriate fuzzy algorithm is adopted in the process of color feature extraction to gain the fuzzy color features of image.Image feature ma-tching mainly depends on the similarity between two image feature vectors.In this paper,a novel fuzzy similarity measure method is proposed it adopts the similarity between the query image and its k nearest neighbor images to constitute the k-dimensional fuzzy feature vector of the query imagem,and adopts the similarity between each retrieved image and k nearest neighbor images of the query image to constitute the k-dimensional fuzzy feature vector of each retrieved image.Then it calculates the fuzzy similarity between the k-dimensional fuzzy feature vector of the query image and the k-dimensional fuzzy feature vector of each retrieved image,and the retrieved images are fed back to users in reverse order of the fuzzy similarity.In order to verify the effectiveness of the proposed fuzzy color features,a series of experimental comparison are performed on the WANG dataset.In order to evaluate the performance of the image retrieval system based on different similarities,a series of experimental comparison are performed on WANG,Corel-5k and Corel-10K datasets.Experimental results show that the performance of the image retrieval system based on the maximum and minimum value outperforms that of the image retrieval systems based on the other three commonly used similarities.And the performance of the image retrieval system based on fuzzy similarity outperformsthat of the image retrieval system based on the maximum and minimum value.On the WANG,Corel-5k and Corel-10K datasets,the average precision of top 20 images retrieved by the image retrieval system based on fuzzy similarity is 4.92%,17.11% and 19.48% higher thanthat of top 20 images retrieved by the image retrieval system based on the maximum and minimum value respectively,and the average precision of top 100 images retrieved by the image retrieval system based on fuzzy similarity is 4.94%,22.61% and 33.02% higher that than of top 100 images retrieved by the image retrieval system based on the maximum and minimum value respectively.

Key words: Average precision, Content-based image retrieval, Fuzzy color features, Fuzzy similarity, Near neighbor images, Precision

中图分类号: 

  • TP391.41
[1]SAKR N A,ELDESOUKY A I,ARAFAT H.An efficient fast-response content-based image retrieval framework for big data [J].Computers & Electrical Engineering,2016,54:522-538.
[2]ISLAM S M,BANERJEE M,BHATTACHARYYA S,et al.Content-based image retrieval based on multiple extended fuzzy-rough framework [J].Applied Soft Computing,2017,57:102-117.
[3]ALI N,BAJWA K B,SABLATNIG R,et al.Image retrieval by addition of spatial information based on histograms of triangular regions [J].Computers & Electrical Engineering,2016,54(C):539-550.
[4]MEHRABI M,ZARGARI F,GHANBARI M,et al.Fast content access and retrieval of JPEG compressed images.Signal Processing [J].Image Communication:A Publication of the European Association for Signal Processing,2016,46:54-59.
[5]ELALAMI M E.A new matching strategy for content based ima-ge retrieval system [J].Applied Soft Computing Journal,2014,14:407-418.
[6]ZHOU J,LIU X,LIU W,et al.Image retrieval based on effective feature extraction and diffusion process [J].Multimedia Tools & Applications,2019,78(5):6163-6190.
[7]XU Y Y,JIA Y.A privacy-preserving content-based image retrieval method in cloud environment [J].Journal of Visual Communication & Image Representation,2017,43:164-172.
[8]YU J,RUI Y,CHEN B.Exploiting click constraints and multi-view features for image re-ranking [J].IEEE Transactions on Multimedia,2013,16(1):159-168.
[9]YU J,TAO D,WANG M,et al.Learning to rank using user clicks and visual features for image retrieval [J].IEEE Transactions on Cybernetics,2015,45(4):767-779.
[10]YU J,YANG X,GAO F,et al.Deep multimodal distance metric learning using click constraints for image ranking [J].IEEE Transactions on Cybernet,2017,47(12):4014-4024.
[11]HE Z,YOU X,YUAN Y.Texture image retrieval based on non-tensor product wavelet filter banks [J].Signal Processing,2009,89(8):1501-1510.
[12]RAO M B.CTDCIRS:Content based Image Retrieval System based on Dominant Color and Texture Features [J].International Journal of Computer Applications,2011,18(6):40-46.
[13]CHEN J,WANG Y,LUO L,et al.Image retrieval based onimage-to-class similarity [J].Pattern Recognition Letters,2016,83(nov.1):379-387.
[14]JACOBS D W,WEINSHALL D,GDALYAHU Y.Classification with nonmetric distances:image retrieval and class representation [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2000,22(6):583-600.
[15]BALA A,KAUR T.Local texton XOR patterns:A new feature descriptor for content-based image retrieval [J].Engineering Science & Technology An International Journal,2016,19:101-112.
[16]VES E D,BENAVENT X,COMA I,et al.A novel dynamic multi-model relevance feedback procedure for content-based image retrieval [J].Neurocomputing,2016,208:99-107.
[17]WANG J,BAI X,YOU X,et al.Shape matching and classification using height functions [J].Pattern Recognition Letters,2012,33(2):134-143.
[18]WALIA E,PAL A.Fusion framework for effective color image retrieval [J].Journal of Visual Communication & Image Representation,2014,25(6):1335-1348.
[19]JIANG J,HU R,WANG Z,et al.CDMMA:Coupled discriminant multi-manifold analysis for matching low-resolution face images [J].Signal Processing,2016,124:162-172.
[20]MA J,ZHAO J,MA Y,et al.Non-rigid visible and infrared face registration via regularized Gaussian fields criterion [J].Pattern Recognition:The Journal of the Pattern Recognition Society,2015,48(3):772-784.
[21]JIANG J,HU R,WANG Z,et al.Facial image hallucinationthrough coupled-layer neighbor embedding [J].IEEE Transactions on Circuits & Systems for Video Technology,2016,26(9):1674-1684.
[22]LI Y,TAO C,TAN Y,et al.Unsupervised multilayer feature learning for satellite image scene classification [J].IEEEGeo-science and Remote Sensing Letters,2016,13(2):157-161.
[23]WANG X Y,LIANG L L,LI Y W,et al.Image retrieval based on exponent moments descriptor and localized angular phase histogram [J].Multimedia Tools and Applications,2017,76(6):7633-7659.
[24]VARISH N,PAL A K.A novel image retrieval scheme using gray level co-occurrence matrix descriptors of discrete cosine transform based residual image [J].Applied Intelligence,2018,48(9):2930-2953.
[25]KHOKHER A,TALWAR R.A fast and effective image retrie-val scheme using color-,texture-,and shape-based histograms [J].Multimedia Tools and Applications,2017,76(20):21787-21809.
[26]KUMAR M,CHHABRA P,GARG N K.An efficient contentbased image retrieval system using BayesNet and K-NN [J].Multimedia Tools & Applications,2018,77(16):1-14.
[27]OUNI A,URRUTY T,VISANI M.A robust cbir framework in between bags of visual words and phrases models for specific image datasets [J].Multimedia Tools & Applications,2018,77(20):26173-26189.
[28]RAGHUWANSHI G,TYAGI V.A novel technique for location independent object based image retrieval [J].Multimedia Tools &Applications,2017,76(12):1-19.
[29]KUMAR A,DYER S,KIM J,et al.Adapting content-basedimage retrieval techniques for the semantic annotation of medical images [J].Computerized Medical Imaging & Graphics the Official Journal of the Computerized Medical Imaging Society,2016,49:37-45.
[30]HANNAN M A,AREBEY M,BEGUM R A,et al.Content-based image retrieval system for solid waste bin level detection and performance evaluation [J].Waste Management,2016,50:10-19.
[1] 孙伟, 赵玉普.
增强旋转不变LBP算法及其在图像检索中的应用
Enhanced Rotation Invariant LBP Algorithm and Its Application in Image Retrieval
计算机科学, 2019, 46(7): 263-267. https://doi.org/10.11896/j.issn.1002-137X.2019.07.040
[2] 徐耀丽, 李战怀.
基于概率推断的质量控制智能体
Quality Control Agent Based on Probability Inference
计算机科学, 2019, 46(4): 8-13. https://doi.org/10.11896/j.issn.1002-137X.2019.04.002
[3] 李轶鲲,胡玉玺,杨萍.
基于频率域信息的遥感图像数据库水体检索
Frequency Domain Information Based Water Body Image Retrieval in High Resolution Satellite Image Databases
计算机科学, 2016, 43(Z6): 118-121. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.028
[4] 沈鹍霄,兰义华,卢玉领,尚耐丽,马晓普.
乳腺辅助诊断系统中可疑肿块分割方法研究
Research on Segmentation Methods in Breast Computer-aided Detection
计算机科学, 2015, 42(Z11): 195-198.
[5] 陈立辉,苏伟,蔡川,陈晓云.
基于LaTex的Web数学公式提取方法研究
Research of Extraction Method of Web Mathematical Formula Based on LaTex
计算机科学, 2014, 41(6): 148-154. https://doi.org/10.11896/j.issn.1002-137X.2014.06.029
[6] 陈刚,岳晓冬,陈宇飞.
基于稀疏低秩描述的图像检索方法
Image Retrieval Method Based on Sparse Low-rank Representation
计算机科学, 2014, 41(3): 302-305.
[7] 邹月娴,霍佳森,刘吉,李奕,邓文军.
基于特征融合的WCE图像检索
WCE Image Retrieval by Using Fused Feature
计算机科学, 2013, 40(Z11): 320-324.
[8] 杨族桥,陈跃鹏,张青.
综合视觉注意模型的显著性局部特征提取算法研究
Salient Local Feature Extraction Algorithm Based on Integrated Visual Attention Model
计算机科学, 2013, 40(8): 289-292.
[9] 高友平,童名文,张凯,野菊苹,陈林林.
基于模糊数学的音乐情感检索技术
Research on Music Emotion Retrieval Technology Employing Fuzzy Mathematics
计算机科学, 2013, 40(6): 233-237.
[10] 石跃祥,文华,龚平,莫浩澜,金银国.
基于模糊神经网络的语义映射方法及其在自然图像检索中的应用
Projection of Semantics and Retrieval in Natural Scenery Images Based on Fuzzy Nerve Network
计算机科学, 2013, 40(12): 122-126.
[11] 郭士会,杨 明,王晓芳,赵东方,邓世涛.
基于FSRM的相关反馈图像检索算法
Relevance Feedback Algorithm Based on Fuzzy Semantic Relevance Matrix in Image Retrieval
计算机科学, 2012, 39(Z6): 540-542.
[12] 肖潇,王宪保,庄德文,王守觉’.
基于均匀区域分割的图像检索研究
Image Retrieval Based on Uniform Region Segmentation
计算机科学, 2012, 39(6): 255-257.
[13] 柯逍,陈小芬,李绍滋.
基于多特征融合的花卉图像检索
Flower Image Retrieval Based on Multi-features Fusion
计算机科学, 2010, 37(11): 282-286.
[14] 杨红菊,张艳,曹付元.
一种基于颜色矩和多尺度纹理特征的彩色图像检索方法
Color Image Retrieval Approach Based on Color Moments and Multi-scale Texture Features
计算机科学, 2009, 36(9): 273-277.
[15] .
一种基于内容的图像检索方法

计算机科学, 2008, 35(7): 250-251.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!