Visual Saliency Weighting and Cross-Domain Manifold Ranking for Sketch-Based Image Retrieval
作者： Takahiko Furuya , Ryutarou Ohbuchi
DOI: 10.1007/978-3-319-04114-8_4
关键词:
摘要: A Sketch-Based Image Retrieval (SBIR) algorithm compares a line-drawing sketch with images. The comparison is made difficult by image background clutter. query includes an object of interest only, while database images would also contain clutters. In addition, variability hand-drawn sketches, due to "stroke noise" such as disconnected and/or wobbly lines, makes the difficult. Our proposed SBIR edges detected in lines sketch. To emphasize presumed and disregard backgrounds, we employ Visual Saliency Weighting (VSW) image. effectively compare containing stroke noise images, Cross-Domain Manifold Ranking (CDMR), manifold-based distance metric learning algorithm. experimental evaluation using two benchmarks showed that combination VSW CDMR significantly improves retrieval accuracy.
springer.com
acm.org 
sci-hub.st 参考文章(18)
Jose M Saavedra, Benjamin Bustos, None, An improved histogram of edge local orientations for sketch-based image retrieval dagm conference on pattern recognition. pp. 432- 441 ,(2010) , 10.1007/978-3-642-15986-2_44
Radhakrishna Achanta, Francisco Estrada, Patricia Wils, Sabine Süsstrunk, Salient region detection and segmentation international conference on computer vision systems. pp. 66- 75 ,(2008) , 10.1007/978-3-540-79547-6_7
Chuan Yang, Lihe Zhang, Huchuan Lu, Xiang Ruan, Ming-Hsuan Yang, Saliency Detection via Graph-Based Manifold Ranking computer vision and pattern recognition. pp. 3166- 3173 ,(2013) , 10.1109/CVPR.2013.407
Yang Cao, Changhu Wang, Liqing Zhang, Lei Zhang, Edgel index for large-scale sketch-based image search computer vision and pattern recognition. pp. 761- 768 ,(2011) , 10.1109/CVPR.2011.5995460
Takahiko Furuya, Ryutarou Ohbuchi, Ranking on Cross-Domain Manifold for Sketch-Based 3D Model Retrieval 2013 International Conference on Cyberworlds. pp. 274- 281 ,(2013) , 10.1109/CW.2013.60
Rui Hu, Mark Barnard, John Collomosse, Gradient field descriptor for sketch based retrieval and localization international conference on image processing. pp. 1025- 1028 ,(2010) , 10.1109/ICIP.2010.5649331
Kilian Q. Weinberger, Lawrence K. Saul, Distance Metric Learning for Large Margin Nearest Neighbor Classification Journal of Machine Learning Research. ,vol. 10, pp. 207- 244 ,(2009) , 10.5555/1577069.1577078
Mathias Eitz, Ronald Richter, Tamy Boubekeur, Kristian Hildebrand, Marc Alexa, Sketch-based shape retrieval international conference on computer graphics and interactive techniques. ,vol. 31, pp. 31- ,(2012) , 10.1145/2185520.2185527
Rui Hu, John Collomosse, A performance evaluation of gradient field HOG descriptor for sketch based image retrieval Computer Vision and Image Understanding. ,vol. 117, pp. 790- 806 ,(2013) , 10.1016/J.CVIU.2013.02.005
Konstantinos Bozas, Ebroul Izquierdo, Large Scale Sketch Based Image Retrieval Using Patch Hashing international symposium on visual computing. pp. 210- 219 ,(2012) , 10.1007/978-3-642-33179-4_21