基于多尺度HOG的草图检索

J4 ›› 2016, Vol. 38 ›› Issue (03): 520-527.

基于多尺度HOG的草图检索

李思思,陈曦,肖建

(长沙理工大学计算机与通信工程学院，湖南长沙 410114)

收稿日期:2015-05-11 修回日期:2015-07-06 出版日期:2016-03-25 发布日期:2016-03-25
基金资助:
湖南省自然科学基金（11JJ3069）

Sketch-based image retrieval based on multi-scale HOG

LI Sisi,CHEN Xi,XIAO Jian

(School of Computer & Communication Engineering,Changsha University of Science & Technology,Changsha 410114,China)

Received:2015-05-11 Revised:2015-07-06 Online:2016-03-25 Published:2016-03-25

摘要/Abstract

摘要：

草图检索是图像处理领域中的重要研究内容。提出了一种将高斯金字塔和局部HOG特征融合的特征提取改进方法，并将其用于草图检索。采用高斯金字塔将图像分解到多尺度空间，在所有尺度上进行兴趣点提取，获得基于兴趣点的多尺度HOG特征。利用图像的多尺度HOG特征集生成视觉词典，最终形成与视觉词典相关的特征描述向量，通过相似度匹配实现草图检索。将该算法与单一尺度下的HOG算法及其他几种算法比较，实验结果表明了其可行性和有效性。

关键词: 草图检索, 高斯金字塔, 多尺度HOG, 形状特征

Abstract:

Sketch-based image retrieval is an important research topic in the field of image processing. We present an improved feature extraction method for sketchbased image retrieval, which combines the Gaussian pyramid and local histogram of gradient (HOG) features. By using Gaussian pyramid, the image is decomposed into multiple resolution images on which the points of interest are extracted, and the points based multiscale HOG features are obtained. The visual word dictionary is generated from the multiscale HOG features, and finally feature vectors relative to visual words are formed. The images are ranked according to decreasing similarity which is calculated by the distance between the feature vectors of sketches and the images. Compared with the HOG algorithm at single scale and several other algorithms, experimental results demonstrate the feasibility and effectiveness of the proposed method.

Key words: sketch-based image retrieval;Gaussian pyramid;multiscale HOG;shape feature

李思思,陈曦,肖建. 基于多尺度HOG的草图检索[J]. J4, 2016, 38(03): 520-527.

LI Sisi,CHEN Xi,XIAO Jian. Sketch-based image retrieval based on multi-scale HOG [J]. J4, 2016, 38(03): 520-527.

参考文献［13］

［1］	Shete D S,Chavan D M S.Content based image retrieval:Review ［J］.International Journal of Emerging Technology and Advanced Engineering,2012,2(9):8590.
［2］	Gong Ming,Cao Weiguo,Li Hua.Application of combined shape and color invariants to image retrieval ［J］.Journal of Image and Graphics,2013,18(8):9901003.(in Chinese)
［3］	Xin Yuxuan, Yan Zifei. Research progress of handdrawn sketchbased image retrieval ［J］.CAAI Transactions on Intelligent Systems,2015,10(2):167177.(in Chinese)
［4］	Chatbri H, Kameyama K. Sketchbased image retrieval by shape points description in support regions［C］∥Proc of IEEE 2013 20th International Conference on Systems,Signals and Image Processing (IWSSIP),2013:1922.
［5］	Yang Hongju, Jian Xiaoyan, Cao Fuyuan, et al.Image retrieval method based on combined Euler vector and edges direction histogram［J］.PR&AI,2012,25(3):450455.(in Chinese)
［6］	Abdulbaqi H A,Sulong G,Hashem S H.A sketch based image retrieval:A review of literature［J］.Journal of Theoretical and Applied Information Technology,2014,63(1):158167.
［7］	Kumagai Y,Ohashi G.Querybysketch image retrieval using edge relation histogram［J］.IEICE Transactions on Information and Systems,2013,96(2):340348.
［8］	Saavedra J M,Bustos B.An improved histogram of edge local orientations for sketchbased image retrieval ［M］∥Pattern Recognition.Berlin:Springer Heidelberg,2010:432441.
［9］	Dalal N,Triggs B.Histograms of oriented gradients for human detection［C］∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005(CVPR 2005),2005:886893.
［10］	Chee Won Sun,Park Dong Kwon,Park SooJun.Efficient use of MEPG7 edge histogram descriptor［J］.ETRI Journal, 2002,24(1):3542.
［11］	Eitz M,Hildebrand K,Boubekeur T,et al.Sketchbased image retrieval:Benchmark and bagoffeatures descriptors［J］.IEEE Transactions on Visualization and Computer Graphics,2011,17(11):16241636.
［12］	Pei L,Xie Z,Dai J.Joint edge detector based on Laplacian pyramid［C］∥Proc of 2010 3rd International Congress on Image and Signal Processing,2010:978982.
［13］	Yue Sicong, Zhao Rongchun, Zheng Jiangbin. MERF based edge detection with adaptive threshold［J］.Journal of Electronics & Information Technology,2008,30(4):957960.(in Chinese)
［14］	Sivic J, Zisserman A. Video Google:A text retrieval approach to object matching in videos［C］∥Proc of the 7th IEEE International Conference on Computer Vision,2003:14701477.
［15］	Hu R,Collomosse J.A performance evaluation of gradient field hog descriptor for sketch based image retrieval［J］.Computer Vision and Image Understanding,2013,117(7):790806.
［16］	Kawaguchi E, Taniguchi R. Complexity of binary pictures and image thresholdingAn application of DFExpression to the thresholding problem［C］∥Proc of the 8th ICPR,1986:12211225.
	附中文参考文献：
［2］	公明,曹伟国,李华.形状和颜色混合不变量在图像检索中的应用［J］.中国图象图形学报,2013,18(8):9901003.
［3］	辛雨璇,闫子飞.基于手绘草图的图像检索技术研究进展［J］.智能系统学报,2015,10(2):167177.
［5］	杨红菊,菅小艳,曹付元,等.基于组合欧拉向量与边缘方向直方图的图像检索方法［J］.模式识别与人工智能,2012,25(3):450455.
［13］	岳思聪,赵荣椿,郑江滨.基于多尺度边缘响应函数的自适应阈值边缘检测算法［J］.电子与信息学报,2008,30(4):957960.

[1]	姬子恒, 王斌. 基于深度学习的草图检索方法研究进展[J]. 计算机工程与科学, 2021, 43(12): 2190-2205.
[2]	魏伟一, 王立召, 王婉茹, 赵毅凡. 基于超像素形状特征的图像复制粘贴篡改检测算法[J]. 计算机工程与科学, 2021, 43(02): 312-321.
[3]	刘辉，代照坤，王龙. 基于Hu-GLCM的手势识别方法研究[J]. 计算机工程与科学, 2018, 40(03): 525-532.