Sketch-Based Image Retrieval with Multiple Binary HoG Descriptor

The proliferation of touch screen devices has enabled Sketch-Based Image Retrieval (SBIR) to become an effective method for image retrieval. Although prior research efforts have ex-tensively explored the methods for SBIR, the appropriate descriptor which can accurately and efficiently describe sketch and natural images is still unavailable. To further improve the accuracy and efficiency of SBIR, in this paper, we pro-pose a novel sketch-based image retrieval method leveraging Multiple Binary HoG (MBHoG) descriptor. In this method, two novel binary descriptors named Primary Binary HoG (PBHoG) and Discrete Binary HoG (DBHoG), are proposed and combined, together with the color feature as an extra condition to enhance the accuracy of results. We use Ham-ming distance with two binary masks as constraint to re-trieve images. The method ensures time and space efficiency. The experimental results performed on the public dataset demonstrate that the proposed method has the superiority of accuracy.

[1]  Jing Liu,et al.  Clustering-Guided Sparse Structural Learning for Unsupervised Feature Selection , 2014, IEEE Transactions on Knowledge and Data Engineering.

[2]  Meng Wang,et al.  Neighborhood Discriminant Hashing for Large-Scale Image Retrieval , 2015, IEEE Transactions on Image Processing.

[3]  Rui Hu,et al.  Gradient field descriptor for sketch based retrieval and localization , 2010, 2010 IEEE International Conference on Image Processing.

[4]  Marc Alexa,et al.  PhotoSketch: a sketch based image query and compositing system , 2009, SIGGRAPH '09.

[5]  Rui Hu,et al.  A performance evaluation of gradient field HOG descriptor for sketch based image retrieval , 2013, Comput. Vis. Image Underst..

[6]  Marc Alexa,et al.  Sketch-Based Image Retrieval: Benchmark and Bag-of-Features Descriptors , 2011, IEEE Transactions on Visualization and Computer Graphics.

[7]  Shi-Min Hu,et al.  Sketch2Photo: internet image montage , 2009, ACM Trans. Graph..

[8]  Marc Alexa,et al.  A descriptor for large scale image retrieval based on sketched feature lines , 2009, SBIM '09.

[9]  Xiangwei Kong,et al.  BHoG: binary descriptor for sketch-based image retrieval , 2014, Multimedia Systems.

[10]  C. Lawrence Zitnick,et al.  Fast Edge Detection Using Structured Forests , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[12]  Liqing Zhang,et al.  Sketch-based image retrieval on a large scale database , 2012, ACM Multimedia.

[13]  John P. Collomosse,et al.  Scalable Sketch-Based Image Retrieval Using Color Gradient Features , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[14]  David A. Forsyth,et al.  Generalizing motion edits with Gaussian processes , 2009, ACM Trans. Graph..

[15]  C. Won,et al.  Efficient Use of MPEG‐7 Edge Histogram Descriptor , 2002 .

[16]  Liqing Zhang,et al.  Edgel index for large-scale sketch-based image search , 2011, CVPR 2011.

[17]  Winston H. Hsu,et al.  Sketch-based image retrieval on mobile devices using compact hash bits , 2012, ACM Multimedia.

[18]  R. Aarthi,et al.  Saliency based modified chamfers matching method for sketch based image retrieval , 2015, 2015 International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS).

[19]  Liqing Zhang,et al.  MindFinder: interactive sketch-based image search on millions of images , 2010, ACM Multimedia.