结合显著区域检测和手绘草图的服装图像检索
|
摘要
针对服装图像检索准确率和效率较低的问题,提出一种服装显著区域检测和手绘草图的服装图像检索方法。首先采用正则化随机漫步算法对输入的服装图像库进行视觉显著区域检测,并结合其边缘轮廓信息,得到服装显著边缘图像;其次,对输入的服装草图和服装边缘图像进行特征提取,得到服装草图和服装边缘图像各自的方向梯度直方图(HOG)特征;然后,通过计算服装草图特征和服装边缘特征的相似度,实现特征匹配;最后,按照特征匹配结果在服装图像库中检索与服装草图相似的服装图像,采用基于距离相关系数的重排序算法对其相似度进行排序并输出检索结果。结果表明,该方法提高了服装检索的准确率,具有较好的鲁棒性,检索准确率可达78. 5%。
In order to solve the problems of unsatisfactory accuracy and low efficiency in the clothing image retrieval,a sketch based clothing image retrieval method by visual salient regions and re-ranking was proposed. Firstly, clothing salient edge map was obtained by saliency detection method with regularized random walks walking and the edge map. Then,histogram of oriented gradeient features of user sketches and the salient edge in clothing images were extracted,respectively,and the feature matching was achieved by similarity calculation between the input sketches and clothing images. Finally,the retrieval results were output in descending order according to the similarity. Using the re-ranking optimization based on distance correlation coefficients,final results were obtained. Experimental results show that the method can effectively provide clothing retrieval results and significantly improve accuracy and robustness comparison with other approaches. The accuracy ratio of the algorithm is higher than 78. 5%.
In order to solve the problems of unsatisfactory accuracy and low efficiency in the clothing image retrieval,a sketch based clothing image retrieval method by visual salient regions and re-ranking was proposed. Firstly, clothing salient edge map was obtained by saliency detection method with regularized random walks walking and the edge map. Then,histogram of oriented gradeient features of user sketches and the salient edge in clothing images were extracted,respectively,and the feature matching was achieved by similarity calculation between the input sketches and clothing images. Finally,the retrieval results were output in descending order according to the similarity. Using the re-ranking optimization based on distance correlation coefficients,final results were obtained. Experimental results show that the method can effectively provide clothing retrieval results and significantly improve accuracy and robustness comparison with other approaches. The accuracy ratio of the algorithm is higher than 78. 5%.
引文
[1]KIAPOUR M H,HAN X,LAZEBNIK S,et al.Where to buy it:matching street clothing photos in online shops[C]//IEEE International Conference on Computer Vision.Piscataway:IEEE Xplore,2015:3343-3351.
[2]LIU Z,LUO P,QIU S,et al.Deep Fashion:powering robust clothes recognition and retrieval with rich annotations[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE Xplore,2016:1096-1104.
[3]TSENG C H,HUNG S S,TSAY J J.An efficient garment visual search based on shape context[J].Wseas Transactions on Computers,2009,8(7):223-230.
[4]KONDO S,TOYOURA M,MAO X,et al.Sketch based skirt image retrieval[C]//Non Photorealistic Animation and Rendering.New York:ACM Digital Library,2014:11-16.
[5]李东,万贤福,汪军.采用傅里叶描述子和支持向量机的服装款式识别方法[J].纺织学报,2017,38(5):122-127.LI Dong,WAN Xianfu,WANG Jun.Clothing style recongnition approach using Fourier descriptor and support vector machines[J].Journal of Textile Research,2017,38(5):122-127.
[6]项明,姚雪存,崔振东,等.利用相关反馈技术和形状特征的服装图像检索算法[J].纺织学报,2014,35(2):94-98.XIANG Ming,YAO Xuecun,CUI Zhendong,et al.Research on image retrieval algorithm by relevance feedback technology and shape features[J].Journal of Textile Research,2014,35(2):94-0.
[7]LI K,PANG K,SONG Y Z,et al.Fine-grained sketch-based image retrieval:the role of part-aware attributes[C]//Applications of Computer Vision.Piscataway:IEEE Xplore,2016:1-9.
[8]AZIZPOUR H,LAPTEV I.Object detection using strongly-supervised deformable part models[C]//European Conference on Computer Vision.Berlin:Springer-Verlag,2014:836-849.
[9]ZHANG Y,QIAN X,TAN X,et al.Sketch-based image retrieval by salient contour reinforcement[J].IEEE Transactions on Multimedia,2016,18(8):1604-1615.
[10]PEDRONETTE D C G,TORRES R D S.Exploiting clustering approaches for image re-ranking[J].Journal of Visual Languages&Computing,2011,22(6):453-466.
[11]ARBELEZ P,MAIRE M,FOWLKES C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2011,33(5):898-916.
[12]ACHANTA R,SHAJI A,SMITH K,et al.SLICsuperpixels compared to state-of-the-art superpixel methods.[J].IEEE Trans Pattern Anal Mach Intell,2012,34(11):2274-2282.
[13]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//IEEE Computer Society.Piscataway:IEEE Xplore,2005:886-893.
[14]HU R,COLLOMOSSE J.A performance evaluation of gradient field HOG descriptor for sketch based image retrieval[J].Computer Vision&Image Understanding Cviu,2013,117(7):790-806.
[15]SZKELY G J,RIZZO M L,BAKIROV N K.Measuring and testing dependence by correlation of distances.[C]//ACM Symposium on Virtual Reality Software and Technology.New York:ACM Digital Library,2007:141-144.
[16]YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//IEEEConference on Computer Vision and Pattern Recognition.IEEE Computer Society.Piscataway:IEEE Xplore,2013:3166-3173.
[17]CHENG M M,ZHANG G X,MITRA N J,et al.Global contrast based salient region detection[C]//Computer Vision and Pattern Recognition.Piscataway:IEEEXplore,2011:409-416.
[18]CAO Y,WANG C,ZHANG L,et al.Edgel index for large-scale sketch-based image search[C]//IEEEConference on Computer Vision and Pattern Recognition.Piscataway:IEEE Xplore,2011:761-768.
[19]WANG S,ZHANG J,HAN T X,et al.Sketch-based image retrieval through hypothesis-driven object boundary selection with HLR descriptor[J].IEEETransactions on Multimedia,2015,17(7):1045-1057.
[20]SAAVEDRA J M,RST-SHELO.Sketch-based image retrieval using sketch tokens and square root normalization[J].Multimedia Tools&Applications,2017,76(1):931-951.
[21]SEZGIN T M,STAHOVICH T,DAVIS R.Sketch based interfaces:early processing for sketch understanding[C]//The Workshop on Perceptive User Interfaces.New York:ACM Digital Library,2001:1-8.
[2]LIU Z,LUO P,QIU S,et al.Deep Fashion:powering robust clothes recognition and retrieval with rich annotations[C]//Computer Vision and Pattern Recognition.Piscataway:IEEE Xplore,2016:1096-1104.
[3]TSENG C H,HUNG S S,TSAY J J.An efficient garment visual search based on shape context[J].Wseas Transactions on Computers,2009,8(7):223-230.
[4]KONDO S,TOYOURA M,MAO X,et al.Sketch based skirt image retrieval[C]//Non Photorealistic Animation and Rendering.New York:ACM Digital Library,2014:11-16.
[5]李东,万贤福,汪军.采用傅里叶描述子和支持向量机的服装款式识别方法[J].纺织学报,2017,38(5):122-127.LI Dong,WAN Xianfu,WANG Jun.Clothing style recongnition approach using Fourier descriptor and support vector machines[J].Journal of Textile Research,2017,38(5):122-127.
[6]项明,姚雪存,崔振东,等.利用相关反馈技术和形状特征的服装图像检索算法[J].纺织学报,2014,35(2):94-98.XIANG Ming,YAO Xuecun,CUI Zhendong,et al.Research on image retrieval algorithm by relevance feedback technology and shape features[J].Journal of Textile Research,2014,35(2):94-0.
[7]LI K,PANG K,SONG Y Z,et al.Fine-grained sketch-based image retrieval:the role of part-aware attributes[C]//Applications of Computer Vision.Piscataway:IEEE Xplore,2016:1-9.
[8]AZIZPOUR H,LAPTEV I.Object detection using strongly-supervised deformable part models[C]//European Conference on Computer Vision.Berlin:Springer-Verlag,2014:836-849.
[9]ZHANG Y,QIAN X,TAN X,et al.Sketch-based image retrieval by salient contour reinforcement[J].IEEE Transactions on Multimedia,2016,18(8):1604-1615.
[10]PEDRONETTE D C G,TORRES R D S.Exploiting clustering approaches for image re-ranking[J].Journal of Visual Languages&Computing,2011,22(6):453-466.
[11]ARBELEZ P,MAIRE M,FOWLKES C,et al.Contour detection and hierarchical image segmentation[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2011,33(5):898-916.
[12]ACHANTA R,SHAJI A,SMITH K,et al.SLICsuperpixels compared to state-of-the-art superpixel methods.[J].IEEE Trans Pattern Anal Mach Intell,2012,34(11):2274-2282.
[13]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//IEEE Computer Society.Piscataway:IEEE Xplore,2005:886-893.
[14]HU R,COLLOMOSSE J.A performance evaluation of gradient field HOG descriptor for sketch based image retrieval[J].Computer Vision&Image Understanding Cviu,2013,117(7):790-806.
[15]SZKELY G J,RIZZO M L,BAKIROV N K.Measuring and testing dependence by correlation of distances.[C]//ACM Symposium on Virtual Reality Software and Technology.New York:ACM Digital Library,2007:141-144.
[16]YANG C,ZHANG L,LU H,et al.Saliency detection via graph-based manifold ranking[C]//IEEEConference on Computer Vision and Pattern Recognition.IEEE Computer Society.Piscataway:IEEE Xplore,2013:3166-3173.
[17]CHENG M M,ZHANG G X,MITRA N J,et al.Global contrast based salient region detection[C]//Computer Vision and Pattern Recognition.Piscataway:IEEEXplore,2011:409-416.
[18]CAO Y,WANG C,ZHANG L,et al.Edgel index for large-scale sketch-based image search[C]//IEEEConference on Computer Vision and Pattern Recognition.Piscataway:IEEE Xplore,2011:761-768.
[19]WANG S,ZHANG J,HAN T X,et al.Sketch-based image retrieval through hypothesis-driven object boundary selection with HLR descriptor[J].IEEETransactions on Multimedia,2015,17(7):1045-1057.
[20]SAAVEDRA J M,RST-SHELO.Sketch-based image retrieval using sketch tokens and square root normalization[J].Multimedia Tools&Applications,2017,76(1):931-951.
[21]SEZGIN T M,STAHOVICH T,DAVIS R.Sketch based interfaces:early processing for sketch understanding[C]//The Workshop on Perceptive User Interfaces.New York:ACM Digital Library,2001:1-8.