Multi-feature Fusion Based Retrieval Results Optimization for Crime Scene Investigation Image Retrieval
LIU Ying1,2, HU Dan1,2, FAN Jiu-lun1, WANG Fu-ping1,2, LI Da-xiang1,2
1. Center for Image and Information Processing, Xi'an University of Posts & Telecommunications, Xi'an, Shaanxi 710121, China;
2. Key Lab of Electronic Information Processing with Applications in Crime Scene Investigation, Ministry of Public Security, Xi'an, Shaanxi 710121, China
Abstract：The image database of crime scene investigation (CSI)has the characteristics of high confidentiality,rare image content and so on.Aiming at the complexity of the content and the ambiguity of the target object,the DCT-DCT wave texture feature is proposed,which is fused with HSV color histogram feature and GIST feature to form the fusion feature.Compared with the commonly used image features,DCT-DCT wave texture feature can get higher retrieval efficiency,and the average retrieval precision rate of the fused features is higher than that of the three features.Finally,the semantic analysis technology is introduced into the retrieval process,and an image retrieval algorithm based on the optimization of retrieval results is proposed.Support vector machine (SVM)classifier was used to extract the semantic of the query image.The semantic analysis of the results of the first retrieval is carried out,and the second retrieval scheme is selected according to the proportion of semantic categories in the initial retrieval results.The algorithm can further improve the average retrieval accuracy based on case-by-case query.
刘颖, 胡丹, 范九伦, 王富平, 李大湘. 基于融合特征的现勘图像检索结果优化算法[J]. 电子学报, 2019, 47(2): 296-301.
LIU Ying, HU Dan, FAN Jiu-lun, WANG Fu-ping, LI Da-xiang. Multi-feature Fusion Based Retrieval Results Optimization for Crime Scene Investigation Image Retrieval. Acta Electronica Sinica, 2019, 47(2): 296-301.
[1] 韩宁,陈巍.基于聚类分析的串并案研究[J].中国人民公安大学学报(自然科学版),2012,18(1):53-58. HAN N,CHEN W.Research on serial case based on cluster analysis[J].Journal of Chinese People's Public Security University (Science and Technology),2012,18(1):53-58.(in Chinese)
[2] 刘颖,黄源,高梓铭.刑侦图像检索中的特征提取及相似度度量研究[J].西安邮电大学学报,2014,19(6):11-16. LIU Y,HUANG Y,GAO Z.Feature extraction and similarity measure for crime scene investigation image retrieval[J].Journal of Xi'an University of Posts and Telecommunications,2014,19(6):11-16.(in Chinese)
[3] KONG A,ZHANG D,KAMEL M.A survey of palm print recognition[J].Pattern Recognition,2009,42(7):1408-1418.
[4] LEE J E,JIN R,JAIN A K,et al.Image retrieval in forensics:Tattoo image database application[J].IEEE Multimedia,2012,19(1):40-49.
[5] 黎向阳,吴敏华,施智平.基于Gabor变换域的积分直方图鞋印图像检索[J].计算机应用与软件,2015,32(3):215-219. LI X,WU M,SHI Z.Shoeprint images retrieval based on integral histogram in gabor transform domain[J].Computer Application and Software,2015,32(3):215-219.(in Chinese)
[6] LIU Y,LI Z.Study on texture feature extraction from forensic images with watermark[A].IEEE 9th Conference on Industrial Electronics and Applications[C].Piscataway,USA:IEEE,2014.1471-1475.
[7] LIU Y,YAN H,LIM K P.Study on rotation-invariant texture feature extraction for tire pattern retrieval[J].Multidimensional Systems & Signal Processing,2017,28(2):757-770.
[8] SHEN X M,ZHOU J X,XU T W.Minority costume image retrieval by fusion of color histogram and edge orientation histogram[A].International Conference on Computer and Information Science[C].Piscataway,USA:IEEE,2016.1-7.
[9] VIBHA B,SANDEEP B P.CBIR using DCT for feature vector generation[J].International Journal of Application or Innovation in Engineering & Management (IJAIEM),2012,1(2):196:200.
[10] 秦军,罗国明.一种基于DCT域的图像快速检索技术[J].计算机系统应用,2005,14(5):29-31. QIN J,LUO G.Image retrieval technique in the DCT domain[J].Computer Systems & Applications,2005,14(5):29-31.(in Chinese)
[11] REEVES A R,KUBIK K,OSBERGER W M.Texture characterization of compressed aerial images using DCT coefficients[A].Proceedings of SPIE-The International Society for Optical Engineering[C].USA:SPIE Digital Library,1997.398-407.
[12] LAY J A,GUAN L.Image retrieval based on energy histograms of the low frequency DCT coefficients[A].IEEE International Conference on Acoustics,Speech,and Signal Processing[C].Piscataway,USA:IEEE,1999.3009-3012.
[13] KEKRE D H B,ATHAWALE A,SADAVARTI D.Algorithm to generate Kekre's wavelet transform from Kekre's transform[J].International Journal of Engineering Science & Technology,2010,2(5):756-767.
[14] DESAI R,SONAWANE B.Gist,hog,and dwt-based content-based image retrieval for facial images[A].Proceedings of the International Conference on Data Engineering and Communication Technology[C].Singapore:Springer,2017.297-307.
[15] 肖保良.基于Gist特征与PHOG特征融合的多类场景分类[J].中北大学学报自然科学版,2014(6):690-694. XIAO B.Multiclass scene classification based on fusion of gist feature and phog feature[J].Journal of North University of China(Natural Science Edition),2014(6):690-694.(in Chinese)
[16] OLIVA B A,TORRALBA.A (2001)Modeling the shape of the scene:A holistic representation of the spatial envelope[J].International Journal of Computer Vision,2001,42(3):145-175.
[17] OLIVA A,TORRALBA A B.Scene-centered description from spatial envelope properties[A].Biologically Motivated Computer Vision Second International Workshop[C].Germany:Springer International Publishing,2002.263-272.
2019, Vol. 47 
