基于感知哈希和视觉词袋模型的图像检索方法
|
摘要
针对移动增强现实中图像检索技术耗时长导致的实时性不高的问题,提出了一种基于感知哈希和视觉词袋模型结合的图像检索方法。图像检索过程中,在保证一定正确率的基础上加快了检索速度。首先,对数据集图像使用改进的感知哈希技术处理,选取与查询相似的图像集合,达到筛选图像数据集的作用;然后,对相似图像集使用视觉词袋模型进行图像检索,选取和查询图像中目标一致的目标图像。实验结果表明,该方法相比较视觉词袋模型算法检索的平均正确率提高了3.2%,检索时间缩短了102.9 ms,能够满足移动增强现实中图像检索的实时性要求,为移动增强现实系统提供了有利的条件。
As the existing image retrieval technologies in mobile augmented reality have a low real-time performance caused by long time-consuming, this paper proposes a novel image retrieval method which combines the perceptual hashing and bag of visual word model(BoVW). The method is able to accelerate the search speed with certain accuracy. First, the improved perceptual hashing is used to retrieve a image set in which each image is similar to the current image, which limits the scope of the target. Then a BoVW model is built based on this image set, the BoVW model is used to create a visual vector for each image in the image set and the current image. Finally, hamming distance of the visual vector between the current image and each image in the image set is calculated to finish the image retrieval. The results show that the improvement of our method in accuracy is 3.2% and the retrieval time is reduced by 102.9 ms to the traditional BoVW model algorithm. Our method is able to meet the real-time requirements of image retrieval in mobile augmented reality.
As the existing image retrieval technologies in mobile augmented reality have a low real-time performance caused by long time-consuming, this paper proposes a novel image retrieval method which combines the perceptual hashing and bag of visual word model(BoVW). The method is able to accelerate the search speed with certain accuracy. First, the improved perceptual hashing is used to retrieve a image set in which each image is similar to the current image, which limits the scope of the target. Then a BoVW model is built based on this image set, the BoVW model is used to create a visual vector for each image in the image set and the current image. Finally, hamming distance of the visual vector between the current image and each image in the image set is calculated to finish the image retrieval. The results show that the improvement of our method in accuracy is 3.2% and the retrieval time is reduced by 102.9 ms to the traditional BoVW model algorithm. Our method is able to meet the real-time requirements of image retrieval in mobile augmented reality.
引文
[1]吕强,黄成,刘明.移动云计算:移动增强现实技术和服务[J].中兴通讯技术,2015,21(2):25-29.
[2]孟繁杰,郭宝龙.CBIR关键技术研究[J].计算机应用研究,2004,21(7):21-24,27.
[3]SHEKHAR R,JAWAHAR C V.Word image retrieval using bag of visual words[C]//2012 10th IAPRInternational Workshop on Document Analysis Systems.New York:IEEE Press,2012:297-301.
[4]JEGOU H,DOUZE M,SCHMID C,et al.Aggregating local descriptors into a compact image representation[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2010:3304-3311.
[5]PERRONNIN F,SáNCHEZ J,MENSINK T.Improving the fisher kernel for large-scale image classification[C]//ECCV′10 Proceedings of the 11th European Conference on Computer Vision.Heidelberg:Springer,2010:143-156.
[6]PENG X J,WANG L M,WANG X X,et al.Bag of visual words and fusion methods for action recognition:Comprehensive study and good practice[J].Computer Vision and Image Understanding,2016,150:109-125.
[7]陆平.移动增强现实中的图像处理关键技术研究及应用[D].南京:东南大学,2015.
[8]严雷,杨晓刚,郭鸿飞,等.结合图像识别的移动增强现实系统设计与应用[J].中国图象图形学报,2016,21(2):184-191.
[9]季秀云.基于内容的图像哈希检索算法研究[D].西安:西安电子科技大学,2014.
[10]CHEN L,LI Z,YANG J F.Compressive perceptual hashing tracking[J].Neurocomputing,2017,239:69-80.
[11]刘霞.基于尺度不变与视觉显著特征的图像感知哈希技术研究[D].重庆:西南大学,2015.
[12]LIU X L,HE J F,LANG B,et al.Hash bit selection:Aunified solution for selection problems in hashing[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2013:1570-1577.
[13]曾勇.图像感知哈希算法及应用[D].杭州:浙江理工大学,2012.
[14]金铭,汪友生,边航,等.一种基于视觉词袋模型的图像检索方法[J].计算机应用与软件,2017,34(4):249-254,321.
[15]JéGOU H,DOUZE M,SCHMID C.Improving bag-of-features for large scale image search[J].International Journal of Computer Vision,2010,87(3):316-336.
[16]GALVEZ-LóPEZ D,TARDOS J D.Bags of binary words for fast place recognition in image sequences[J].IEEE Transactions on Robotics,2012,28(5):1188-1197.
[17]KULIS B,DARRELL T.Learning to hash with binary reconstructive embeddings[C]//Proceedings of the 22nd International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc,2009:1042-1050.
[18]LIN W C,TSAI C F,CHEN Z Y,et al.Keypoint selection for efficient bag-of-words feature generation and effective image classification[J].Information Sciences,2016,329:33-51.
[19]PHILBIN J,CHUM O,ISARD M,et al.Object retrieval with large vocabularies and fast spatial matching[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2007:1-8.
[20]LOWE D G.Object recognition from local scale-invariant features[C]//Proceedings of the 7th IEEE International Conference on Computer Vision.New York:IEEE Press,1999:1150.
[21]BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features(SURF)[J].Computer Vision and Image Understanding,2008,110(3):346-359.
[22]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//2011International Conference on Computer Vision.New York:IEEE Press,2011:2564-2571.
[23]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[24]公维思,周绍磊,吴修振,等.基于改进FAST特征检测的ORB-SLAM方法[J].现代电子技术,2018,41(6):53-56.
[25]杜媛媛.基于增强现实的虚拟旅游平台设计与开发[D].北京:北京交通大学,2015.
[26]CHANDRASEKHAR V,CHEN D M,TSAI S S,et al.The Stanford mobile visual search dataset[EB/OL].[2018-11-02].http://purl.stanford.edu/rb470rw0983.
[2]孟繁杰,郭宝龙.CBIR关键技术研究[J].计算机应用研究,2004,21(7):21-24,27.
[3]SHEKHAR R,JAWAHAR C V.Word image retrieval using bag of visual words[C]//2012 10th IAPRInternational Workshop on Document Analysis Systems.New York:IEEE Press,2012:297-301.
[4]JEGOU H,DOUZE M,SCHMID C,et al.Aggregating local descriptors into a compact image representation[C]//2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2010:3304-3311.
[5]PERRONNIN F,SáNCHEZ J,MENSINK T.Improving the fisher kernel for large-scale image classification[C]//ECCV′10 Proceedings of the 11th European Conference on Computer Vision.Heidelberg:Springer,2010:143-156.
[6]PENG X J,WANG L M,WANG X X,et al.Bag of visual words and fusion methods for action recognition:Comprehensive study and good practice[J].Computer Vision and Image Understanding,2016,150:109-125.
[7]陆平.移动增强现实中的图像处理关键技术研究及应用[D].南京:东南大学,2015.
[8]严雷,杨晓刚,郭鸿飞,等.结合图像识别的移动增强现实系统设计与应用[J].中国图象图形学报,2016,21(2):184-191.
[9]季秀云.基于内容的图像哈希检索算法研究[D].西安:西安电子科技大学,2014.
[10]CHEN L,LI Z,YANG J F.Compressive perceptual hashing tracking[J].Neurocomputing,2017,239:69-80.
[11]刘霞.基于尺度不变与视觉显著特征的图像感知哈希技术研究[D].重庆:西南大学,2015.
[12]LIU X L,HE J F,LANG B,et al.Hash bit selection:Aunified solution for selection problems in hashing[C]//2013 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2013:1570-1577.
[13]曾勇.图像感知哈希算法及应用[D].杭州:浙江理工大学,2012.
[14]金铭,汪友生,边航,等.一种基于视觉词袋模型的图像检索方法[J].计算机应用与软件,2017,34(4):249-254,321.
[15]JéGOU H,DOUZE M,SCHMID C.Improving bag-of-features for large scale image search[J].International Journal of Computer Vision,2010,87(3):316-336.
[16]GALVEZ-LóPEZ D,TARDOS J D.Bags of binary words for fast place recognition in image sequences[J].IEEE Transactions on Robotics,2012,28(5):1188-1197.
[17]KULIS B,DARRELL T.Learning to hash with binary reconstructive embeddings[C]//Proceedings of the 22nd International Conference on Neural Information Processing Systems.Red Hook:Curran Associates Inc,2009:1042-1050.
[18]LIN W C,TSAI C F,CHEN Z Y,et al.Keypoint selection for efficient bag-of-words feature generation and effective image classification[J].Information Sciences,2016,329:33-51.
[19]PHILBIN J,CHUM O,ISARD M,et al.Object retrieval with large vocabularies and fast spatial matching[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition.New York:IEEE Press,2007:1-8.
[20]LOWE D G.Object recognition from local scale-invariant features[C]//Proceedings of the 7th IEEE International Conference on Computer Vision.New York:IEEE Press,1999:1150.
[21]BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features(SURF)[J].Computer Vision and Image Understanding,2008,110(3):346-359.
[22]RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//2011International Conference on Computer Vision.New York:IEEE Press,2011:2564-2571.
[23]戴雪梅,郎朗,陈孟元.基于改进ORB的图像特征点匹配研究[J].电子测量与仪器学报,2016,30(2):233-240.
[24]公维思,周绍磊,吴修振,等.基于改进FAST特征检测的ORB-SLAM方法[J].现代电子技术,2018,41(6):53-56.
[25]杜媛媛.基于增强现实的虚拟旅游平台设计与开发[D].北京:北京交通大学,2015.
[26]CHANDRASEKHAR V,CHEN D M,TSAI S S,et al.The Stanford mobile visual search dataset[EB/OL].[2018-11-02].http://purl.stanford.edu/rb470rw0983.