计算机科学 ›› 2018, Vol. 45 ›› Issue (12): 52-60.doi: 10.11896／j.issn.1002-137X.2018.12.007
刘颖, 张帅, 葛瑜祥, 王富平, 李大湘
LIU Ying, ZHANG Shuai, GE Yu-xiang, WANG Fu-ping, LI Da-xiang
摘要： 轮胎花纹图像检索在交通事故处理及刑事案件侦破中是获取破案信息的重要手段,虽然基于内容的图像检索技术已发展数十年,但由于轮胎花纹图像数据的来源及应用场景特殊等因素,目前这方面的研究文献并不多。在研究近年来轮胎花纹图像检索领域相关文献的基础上,对该领域的技术现状进行总结分析。首先,围绕轮胎花纹纹理特征提取和高层语义特征提取两项关键技术描述了该领域的主要研究成果,并总结了轮胎花纹数据库以及检索性能评价指标。然后,分别针对轮胎花纹低层特征和高层特征提取进行实验对比并分析结果。最后,结合现有技术及实际应用需求,分析了该领域的技术发展趋势并指出了未来的研究方向。
中图分类号:
| [1]LIU Y,FAN J L,LI Z,et al.Case study on content-based image retrieval for crime scene investigation image database [J].Journal of Xi’an University of Posts and Telecommunications,2015,20(3):11-20.(in Chinese) 刘颖,范九伦,李宗,等.现勘图像数据库检索技术实例探讨[J].西安邮电大学学报,2015,20(3):11-20. [2]ZHANG Q.The development of image retrieval in public security image investigation [J].China Security & Protection,2015(19):59-62.(in Chinese) 张琪.图像检索在公安图像侦查领域的发展[J].中国安防,2015(19):59-62. [3]QIAN B Z.China’s first tire pattern patent database began to operate [J].Rubber Science and Technology,2015,13(1):47.(in Chinese) 钱伯章.国内首个轮胎花纹专利数据库开始运营[J].橡胶科技,2015,13(1):47. [4]LIU Y,YAN H Y.A rotation-invariant texture feature extraction method for tire pattern image [J].Journal of Xi’an University of Posts and Telecommunications,2015,20(6):10-13.(in Chinese) 刘颖,燕皓阳.具有旋转不变性的轮胎纹理特征提取[J].西安邮电大学学报,2015,20(6):10-13. [5]ZHANG R T,DONG Y D,SONG Z H,et al.Study on the extraction of boundary features of tread patterns [J].Tire Industry,2017,37(1):18-23.(in Chinese) 张荣团,董玉德,宋忠辉,等.轮胎胎面花纹边界特征提取方法研究[J].轮胎工业,2017,37(1):18-23. [6]DONG Y D,SONG Z H,CHEN J F,et al.Extraction of boundary features of tread patterns from tire point cloud [J].Journal of Computer-Aided Design and Computer Graphics,2017,29(5):939-949.(in Chinese) 董玉德,宋忠辉,陈进富,等.面向轮胎点云的胎面花纹边界特征提取[J].计算机辅助设计与图形学学报,2017,29(5):939-949. [7]LIU Y,ZHANG D S,LU G J,et al.A survey of content-based image retrieval with high-level semantics [J].Pattern Recognition,2007,40(1):262-282. [8]LIU Y,HUANG Y,GAO Z M.Research on 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) 刘颖,黄源,高梓铭.刑侦图像检索中的特征提取及相似性度量研究[J].西安邮电大学学报,2014,19(6):11-16. [9]LIU Y,FAN J L.A survey on state-of-the-art techniques in content-based image retrieval [J].Journal of Xi’an University of Posts and Telecommunications,2012,17(2):1-8.(in Chinese) 刘颖,范九伦.基于内容的图像检索技术综述[J].西安邮电大学学报,2012,17(2):1-8. [10]LIU Y,LI Z,GAO Z M.An improved texture feature extraction method for type tread patterns[C]∥Intelligence Science and Big Data Engineering.Berlin Heidelberg:Springer Press,2013:705-713. [11]LIU Y,LI Z.Study on texture feature extraction from forensic images with watermark[C]∥Industrial Electronics and Applications.Hangzhou:IEEE Press,2014:1471-1475. [12]YAN H Y,LIU Y.An improved texture feature extractionmethod based on Radon transform[C]∥Seventh International Symposium on Computational Intelligence and Design.Hangzhou:IEEE Press,2014:481-485. [13]WANG S,LIU Y,LI D X,et al.An improved SIFT feature extraction method for type tread patterns retrieval[C]∥Seventh International Symposium on Computational Intelligence and Design.Hangzhou:IEEE Press,2014:539-543. [14]LI Z,LIU Y,LI D X.A new texture feature extraction method for image retrieval[C]∥International Conference on Intelligent Control & Information Processing.Beijing:IEEE Press,2013:482-486. [15]WANG S.Study on type trend patterns similarity retrieval based on SIFT feature [D].Xi’an:Xi’an University of Posts and Te-lecommunications,2015.(in Chinese) 王帅.基于SIFT特征的轮胎花纹图像相似性检索技术研究[D].西安:西安邮电大学,2015. [16]JIA S Y,MA J T.Tire pattern retrieval based on wavelet transform and gray level co-occurrence matrix [J].Computer Mea-surement & Control,2016,24(6):210-213.(in Chinese) 贾世英,马姣婷.基于小波变换和灰度共生矩阵的轮胎花纹检索[J].计算机测量与控制,2016,24(6):210-213. [17]LIU Y,YAN H Y,LIM K P.Study on rotation-invariant texture feature extraction for tire pattern retrieval [J].Multidimensio-nal Systems & Signal Processing,2017,28(2):757-770. [18]LI Z.Study on texture feature extraction for tire tread pattern Retrieval [D].Xi’an:Xi’an University of Posts and Telecommunications,2014.(in Chinese) 李宗.用于轮胎花纹检索的纹理特征提取算法研究[D].西安:西安邮电大学,2014. [19]YAN H Y.Study on texture feature extraction for watermarked forensic image [D].Xi’an:Xi’an University of Posts and Telecommunications,2016.(in Chinese) 燕皓阳.含有隐藏信息的刑侦图像纹理特征提取算法研究[D].西安:西安邮电大学,2016. [20]AI L M,GUO C.Tire image enhancement based on frequency division and singular value decomposition [J].Application Research of Computers,2012,29(3):1178-1180.(in Chinese) 艾玲梅,郭春.基于分频和奇异值分解的轮胎图像增强方法[J].计算机应用研究,2012,29(3):1178-1180. [21]AI L M,GUO C.Tire tread pattern recognition based on composite feature extraction and hierarchical support vector machine [J].Computer Engineering and Application,2013,49(20):179-182.(in Chinese) 艾玲梅,郭春.基于组合特征提取与多级SVM的轮胎花纹识别[J].计算机工程与应用,2013,49(20):179-182. [22]QIAO L,LIU J H,XUE Y F.X-ray tire image enhancement processing research [J].Journal of Changzhi University,2012,29(5):27-29.(in Chinese) 乔丽,刘继华,薛艳峰.X光轮胎图像的增强处理研究[J].长治学院学报,2012,29(5):27-29. [23]HUANG D Y,HU W C,WANG Y W,et al.Recognition of tire tread patterns based on gabor wavelets and support vector machine[C]∥International Conference on Computational Collective Intelligence.Berlin Heidelberg:Springer Press,2010:92-101. [24]MICHALÍKOVÁ A,VAGAČ M.A tire tread pattern detection based on fuzzy logic[C]∥Flexible Query Answering Systems.Ghent:Springer Press,2015:381-388. [25]COLBRY D.Pattern recognition for classification and matching of car tires [J].Tire Science & Technology,2005,33(1):2-17. [26]JUNG S W,BAE S W,PARK G T.A design scheme for a hie-rarchical fuzzy pattern matching classifier and its application to the tire tread pattern recognition [J].Fuzzy Sets & Systems,1994,65(2-3):311-322. [27]THALI M J,BRAUN M,BRÜSCHWEILER W,et al.Matching tire tracks on the head using forensic photogrammetry[J].Forensic Science International,2000,113(1):281-287. [28]CHEN Q,LI J,WU X,et al.Tyre imprint discernment algorithm and example analysis [J].Journal of Jilin University Engineering and Technology Edition,2005,35(1):39-43.(in Chinese) 陈强,李江,吴想,等.轮胎印痕识别算法及实例分析[J].吉林大学学报(工学版),2005,35(1):39-43. [29]CHEN Q,LI J,WU X,et al.Tire imprints identification based on wavelet network [C]∥2004 International Symposium on Road Safety.Beijing:China Communications Press,2004:431-434.(in Chinese) 陈强,李江,吴想,等.基于小波网络的轮胎印痕识别[C]∥2004国际公路安全研讨会.北京:人民交通出版社,2004:431-434. [30]YU Q.Research on scene tire tread pattern retrieval algorithm [D].Dalian:Dalian Maritime University,2015.(in Chinese) 于清.现场轮胎痕迹花纹检索算法研究[D].大连:大连海事大学,2015. [31]ZHOU Q Z.Identification research for scene tire marks of traffic accident [D].Xi’an:Chang’an University,2011.(in Chinese) 周奇智.交通事故现场轮胎痕迹的鉴别研究[D].西安:长安大学,2011. [32]WANG Z,WANG Y P,LI S W.Image matching algorithm for tire impression based on SIFT-Gabor transform[J].Optics and Precision Engineering,2011,19(2):291-297. [33]LIN L,SUN J,WANG Z,et al.Recognition method and application to classify a tire image combined curve evolution and cha-racteristic matching [J].Chinese Journal of Scientific Instrument,2011,32(12):56-60. [34]WEI D,PHLYPO R,ADALI T.Adaptive feature split selection for co-training:Application to tire irregular wear classification[C]∥IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver:IEEE Press,2013:3497-3501. [35]ZHANG C,CHENG Y H.Modified threshold algorithm for feature extraction of tyre surface wear [J].Journal of Beijing Jiaotong University,2007,31(2):57-61.(in Chinese) 张超,程荫杭.改进阈值法的轮胎表面磨损的特征提取[J].北京交通大学学报,2007,31(2):57-61. [36]ZHANG C,CHENG Y H.A hybrid template match approachbased on wavelet analysis and threshold segmentation for detecting tire surface wear [C]∥IEEE International Conference on Control and Automation.Guangzhou:IEEE Press,2007:1079 -1084. [37]ZHANG C.Research on graphical analysis method for tyre wear [D].Beijing:Beijing Jiaotong University,2008.(in Chinese) 张超.轮胎磨损图形化分析的研究[D].北京:北京交通大学,2008. [38]BULAN O,BERNAL E A,LOCE R P,et al.Tire classification from still imagesand video[C]∥International IEEE Conference on Intelligent Transportation Systems.Anchorage:IEEE Press,2012:485-490. [39]Tire Rack in USA.Tire Image Database[EB/OL].(2016-11-15).http://www.Tirerack.com. [40]LIU Y,HU D,FAN J L,et al.Multi-feature fusion for crime scene investigation image database retrieval [C]∥The International Conference on Digital Image Computing:Techniques and Applications.Sydney:Institute of Electrical and Electronics Engineers Inc,2017. [41]WEI N,GENG G H,ZHOU M Q.An overview of performance evaluation on content-based image retrieval [J].Journal of Ima-ge Graphics,2004,9(11):1271-1276.(in Chinese) 韦娜,耿国华,周明全.基于内容的图像检索系统性能评价[J].中国图象图形学报,2004,9(11):1271-1276. [42]LIU Y,HU D,FAN J L.A survey of crime scene investigation image retrieval [J].Acta Electronica Sinica,2017,45(3):761-768.(in Chinese) 刘颖,胡丹,范九伦.现勘图像检索综述[J].电子学报,2017,45(3):761-768. [43]MULLER H,MULLER W,SQUIRE D.A web-based evaluation system for CBIR[C]∥ACM Workshops on Multimedia:Multimedia Information Retrieval.New York:ACM,2001:50-54. [44]LIU X H.Research on the key problems of image retrieval [D].Changsha:Central south University,2011.(in Chinese) 刘小红.图像检索的关键问题研究[D].长沙:中南大学,2011. [45]DONG W J,ZHOU M Q,GENG G H,et al.Image retrieval technique based on content [J].Computer Engineering,2005,31(10):162-163.(in Chinese) 董卫军,周明全,耿国华,等.基于内容的图像检索技术研究[J].计算机工程,2005,31(10):162-163. [46]HAO Y B,WANG R L,MA J,et al.Image retrieval based on improved Tamura texture features [J].Science of Surveying and Mapping,2010,35(4):136-138.(in Chinese) 郝玉保,王仁礼,马军,等.改进Tamura纹理特征的图像检索方法[J].测绘科学,2010,35(4):136-138. [47]DANG N,HU F M,CAO Y.Image retrieval based on wavelet transform [J].Electronic Science & Technology,2012,25(12):137-140.(in Chinese) 党妮,胡方明,曹越.基于小波变换的图像检索技术[J].电子科技,2012,25(12):137-140. [48]HUANG X.Application of wavelet transform on multimedia ima-ge retrieval [D].Chengdu:Southwest Jiaotong University,2006.(in Chinese) 黄铉.小波变换在多媒体图像检索中的应用研究[D].成都:西南交通大学,2006. [49]SELESNICK I W,BARANIUK R G,KINGSBURY N C.The dual-tree complex wavelet transform[J].IEEE Signal Processing Magazine,2005,22(6):123-151. [50]SHEN X M,ZHOU J X,XU T W.Minority costume image retrieval by fusion of color histogram and edge orientation histogram[C]∥International Conference on Computer and Information Science.Shanghai:IEEE Press,2016:1-7. [51]DESAI R,SONAWANE B.Gist,HOG,and DWT-Based Content-Based Image Retrieval for Facial Images[C]∥International Conference on Data Engineering and Communication Technology.Berlin:Springer Press,2017:297-307. [52]OJALA T,PIETIKAINEN M,HARWOOD D.Performanceevaluation of texture measures with classification based on Kullback discrimination of distributions[C]∥International Confe-rence on Pattern Recognition,Quebec.Canada:IEEE Press,2002:582-585. [53]DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]∥IEEE Computer Society Conference on Computer Vision & Pattern Recognition.San Diego:IEEE Press,2005:886-893. [54]LOWE D G.Distinctive image features from scale-invariant key-points [J].International Journal of Computer Vision,2004,60(2):91-110. [55]DONG C,CHEN C L,HE K,et al.Image super-resolution using deep convolutional networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307. [56]SZEGEDY C,TOSHEV A,ERHAN D.Deep neural networks for object detection [J].Advances in Neural Information Processing Systems,2013,26:2553-2561. [57]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNetclassification with deep convolutional neural networks[C]∥International Conference on Neural Information Processing Systems.Nevada:Neural Information Processing System Foundation.2012:1097-1105. [58]LIMA E,SUN X,DONG J,et al.Learning and transferring convolutional neural network knowledge to ocean front recognition [J].IEEE Geoscience and Remote Sensing Letters,2017,14(3):354-358. [59]BABENKO A,SLESAREV A,CHIGORIN A,et al.Neuralcodes for image retrieval[C]∥European Conference on Compu-ter Vision.2014:584-599. [60]PAN S J,YANG Q.A survey on transfer learning [J].IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359. [61]XIE M,JEAN N,BURKE M,et al.Transfer learning from deep features for remote sensing and poverty mapping[C]∥The AAAI Conference on Artificial Intelligence.Arizona:AAAI press,2016:3929-3935. [62]WANG Z,LI D.A review of inspection and identification techniques for vehicle tire traces [J].Highways & Automotive Applications,2009(2):50-53.(in Chinese) 王震,李迪.车辆轮胎痕迹检验鉴定技术研究综述[J].公路与汽运,2009(2):50-53. |
| [1] | 沈超, 何希平. 基于纹理特征增强和轻量级网络的人脸防伪算法 Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network 计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217 |
| [2] | 辛元雪, 史朋飞, 薛瑞阳. 基于区域提取与改进 LBP 特征的运动目标检测 Moving Object Detection Based on Region Extraction and Improved LBP Features 计算机科学, 2021, 48(7): 233-237. https://doi.org/10.11896/jsjkx.200600131 |
| [3] | 彭金喜, 苏远歧, 薛笑荣. 基于深度学习和同生矩阵的SAR图像纹理特征检索方法 SAR Image Feature Retrieval Method Based on Deep Learning and Synchronic Matrix 计算机科学, 2019, 46(6A): 196-199. |
| [4] | 朱威, 易瑶, 王图强, 郑雅羽. 一种深度图像帧内编码单元快速划分算法 Fast Coding Unit Partition Algorithm for Depth Maps 计算机科学, 2019, 46(10): 286-294. https://doi.org/10.11896/jsjkx.180701337 |
| [5] | 包晓安, 林晓东, 张娜, 徐璐, 吴彪. 应用色彩纹理特征的人脸防欺骗算法 Face Anti-spoofing Detection Using Color Texture Feature 计算机科学, 2019, 46(10): 180-185. https://doi.org/10.11896/jsjkx.180901688 |
| [6] | 曲佳, 时增林, 叶阳东. 基于卷积特征的非平衡人群密度估计方法 Unbalanced Crowd Density Estimation Based on Convolutional Features 计算机科学, 2018, 45(8): 236-241. https://doi.org/10.11896/j.issn.1002-137X.2018.08.042 |
| [7] | 王雪峤,齐华山,袁家政,梁爱华,孙力红. 二维Gabor特征与三维NP-3DHOG特征融合的人脸识别算法 Face Recognition Using 2D Gabor Feature and 3D NP-3DHOG Feature 计算机科学, 2018, 45(6A): 247-251. |
| [8] | 张晨斌,张云春,郑杨,张鹏程,林森. 基于灰度图纹理指纹的恶意软件分类 Malware Classification Based on Texture Fingerprint of Gray-scale Images 计算机科学, 2018, 45(6A): 383-386. |
| [9] | 郭宇, 郝晓燕, 张兴忠. 基于预测的多特征融合Mean-Shift跟踪算法 Multi-feature Fusion Mean-Shift Tracking Algorithm Based on Prediction 计算机科学, 2018, 45(6A): 171-173. |
| [10] | 黄志杰,王伊侬,王青. 基于血管内超声图像的心血管动脉粥样硬化斑块组织自动定征的研究 Automatic Characterization Study of Atherothrombotic Plaques Based on Intravascular Ultrasound Images 计算机科学, 2018, 45(5): 260-265. https://doi.org/10.11896/j.issn.1002-137X.2018.05.045 |
| [11] | 郭鑫鹏,黄元元,胡作进. 融合颜色与纹理的复杂场景下的服装图像分割算法 Unsupervised Complex-scene Clothing Image Segmentation Algorithm Based on Color and Texture Features 计算机科学, 2017, 44(Z11): 228-232. https://doi.org/10.11896/j.issn.1002-137X.2017.11A.048 |
| [12] | 李文莉,高宏伟,冀大雄,李岩. 基于遗传算法的海底沉积物纹理特征优化方法 Optimization Method of Seabed Sediment Texture Feature Based on Genetic Algorithm 计算机科学, 2016, 43(Z6): 130-133. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.031 |
| [13] | 李飞,张小洪,赵晨丘,鄢萌. 自适应的SILTP算法在运动车辆检测中的研究 Vehicle Detection Research Based on Adaptive SILTP Algorithm 计算机科学, 2016, 43(6): 294-297. https://doi.org/10.11896/j.issn.1002-137X.2016.06.058 |
| [14] | 邹承明,薛栋,郭双双,赵广辉. 一种改进的图像相似度算法 Improved Image Similarity Algorithm 计算机科学, 2016, 43(6): 72-76. https://doi.org/10.11896/j.issn.1002-137X.2016.06.015 |
| [15] | 唐继勇,仲元昌,张校臣,赵国龙. 基于自适应阈值Kirsch-LBP纹理特征的均值漂移目标跟踪算法 Mean Shift Object Tracking Algorithm of Adaptive Threshold Kirsch-LBP Texture Features 计算机科学, 2015, 42(8): 314-318. |
|
||
首页