轮胎花纹图像检索技术综述  

Survey of Tire Pattern Image Retrieval Techniques

作　　者：刘颖[1,2] 张帅 葛瑜祥[1,2] 王富平 李大湘 LIU Ying;ZHANG Shuai;GE Yu-xiang;WANG Fu-ping;LI Da-xiang(Center for Image and Information Processing,Xi’an University of Posts and Telecommunications,Xi’an 710121,China;Key Laboratory of Electronic Information Application Technology for Scene Investigation,Ministry of Public Security,Xi’an 710121,China)

机构地区：[1]西安邮电大学图像与信息处理研究所,西安710121 [2]电子信息现场勘验应用技术公安部重点实验室,西安710121

出　　处：《计算机科学》2018年第12期52-60,共9页Computer Science

基　　金：本文受国家自然科学基金项目(61671377),公安部科技强警项目(2016GABJC51),陕西省国际合作研究项目(2017KW-013)资助。

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。Tire pattern image retrieval(TPIR)plays an important role in traffic accident management and criminal case solving.Although content-based image retrieval(CBIR)has been studied for decades,and few literatures has been done in TPIR due to the lack of tire pattern data source and its special application scenario.Based on the review of the research papers in the field of TPIR in recent years,this paper provided a comprehensive survey of the state-of-the-art techniques in this area.First,this paper described the research status of TPIR by summarizing the existing techniques in low-level texture feature extraction and high-level semantic learning for tire pattern images.Then,this paper introduced tire pattern image databases appeared in literature and the performance evaluation parameters used by researchers.In addition,this paper presented experimental results testing on low-level and high-level features of tire pattern images,with results analysis provided.Lastly,considering existing techniques and practical applications,this paper discussed the research challenges in this filed and pointed out a few potential future research directions.

关 键 词：轮胎花纹图像检索 纹理特征 高层语义特征 轮胎花纹数据库 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]