基于融合特征的现勘图像检索结果优化算法
Multi-feature Fusion Based Retrieval Results Optimization for Crime Scene Investigation Image Retrieval
查看参考文献17篇
|
文摘
|
刑侦现勘图像数据库是具有保密性高、图像内容罕见等极具行业特色的图像数据库.针对现勘图像内容复杂、目标物体不明确的特点,提出了DCT-DCT波纹理特征,并与HSV颜色直方图特征、GIST特征相融合构成融合特征.与常用的图像特征相比,DCT-DCT波纹理特征能够得到较高的检索效率,而融合特征的平均检索查准率高于构成其本身的三种特征的平均检索查准率.最后,将语义分析技术引入到检索过程中,提出基于检索结果优化的现勘图像检索算法,利用支持向量机(Support Vector Machine,SVM)分类器对查询图像进行语义提取,并对初次检索的结果进行语义分析,根据初检结果中语义类别的占比选择二次检索方案,该算法能在按例查询的基础上进一步提高平均检索查准率. |
|
其他语种文摘
|
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. |
|
来源
|
电子学报
,2019,47(2):296-301 【核心库】
|
|
DOI
|
10.3969/j.issn.0372-2112.2019.02.006
|
|
关键词
|
刑侦现勘图像
;
现勘图像检索
;
多特征融合
;
检索方法
;
支持向量机
|
|
地址
|
1.
西安邮电大学图像与信息处理研究所, 陕西, 西安, 710121
2.
电子信息现场勘验应用技术公安部重点实验室, 电子信息现场勘验应用技术公安部重点实验室, 陕西, 西安, 710121
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
公安部科技强警
;
国家自然科学基金
|
|
文献收藏号
|
CSCD:6437304
|
参考文献 共
17
共1页
|
|
1.
韩宁. 基于聚类分析的串并案研究.
中国人民公安大学学报(自然科学版),2012,18(1):53-58
|
CSCD被引
3
次
|
|
|
|
|
2.
刘颖. 刑侦图像检索中的特征提取及相似度度量研究.
西安邮电大学学报,2014,19(6):11-16
|
CSCD被引
3
次
|
|
|
|
|
3.
Kong A. A survey of palm print recognition.
Pattern Recognition,2009,42(7):1408-1418
|
CSCD被引
34
次
|
|
|
|
|
4.
Lee J E. Image retrieval in forensics: Tattoo image database application.
IEEE Multimedia,2012,19(1):40-49
|
CSCD被引
1
次
|
|
|
|
|
5.
黎向阳. 基于Gabor变换域的积分直方图鞋印图像检索.
计算机应用与软件,2015,32(3):215-219
|
CSCD被引
4
次
|
|
|
|
|
6.
Liu Y. Study on texture feature extraction from forensic images with watermark.
IEEE 9th Conference on Industrial Electronics and Applications,2014:1471-1475
|
CSCD被引
2
次
|
|
|
|
|
7.
Liu Y. Study on rotation-invariant texture feature extraction for tire pattern retrieval.
Multidimensional Systems & Signal Processing,2017,28(2):757-770
|
CSCD被引
6
次
|
|
|
|
|
8.
Shen X M. Minority costume image retrieval by fusion of color histogram and edge orientation histogram.
International Conference on Computer and Information Science,2016:1-7
|
CSCD被引
3
次
|
|
|
|
|
9.
Vibha B. CBIR using DCT for feature vector generation.
International Journal of Application or Innovation in Engineering & Management (IJAIEM),2012,1(2):196-200
|
CSCD被引
1
次
|
|
|
|
|
10.
秦军. 一种基于DCT域的图像快速检索技术.
计算机系统应用,2005,14(5):29-31
|
CSCD被引
1
次
|
|
|
|
|
11.
Reeves A R. Texture characterization of compressed aerial images using DCT coefficients.
Proceedings of SPIE-The International Society for Optical Engineering,1997:398-407
|
CSCD被引
1
次
|
|
|
|
|
12.
Lay J A. Image retrieval based on energy histograms of the low frequency DCT coefficients.
IEEE International Conference on Acoustics,Speech, and Signal Processing,1999:3009-3012
|
CSCD被引
1
次
|
|
|
|
|
13.
Kekre D H B. Algorithm to generate Kekre's wavelet transform from Kekre's transform.
International Journal of Engineering Science & Technology,2010,2(5):756-767
|
CSCD被引
1
次
|
|
|
|
|
14.
Desai R. Gist,hog, and dwt-based content-based image retrieval for facial images.
Proceedings of the International Conference on Data Engineering and Communication Technology,2017:297-307
|
CSCD被引
1
次
|
|
|
|
|
15.
肖保良. 基于Gist特征与PHOG特征融合的多类场景分类.
中北大学学报自然科学版,2014(6):690-694
|
CSCD被引
3
次
|
|
|
|
|
16.
Oliva B A. Modeling the shape of the scene: A holistic representation of the spatial envelope.
International Journal of Computer Vision,2001,42(3):145-175
|
CSCD被引
219
次
|
|
|
|
|
17.
Oliva A. Scene-centered description from spatial envelope properties.
Biologically Motivated Computer Vision Second International Workshop,2002:263-272
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问