Improved Generic Object Retrieval In Large Scale Databases By SURF Descriptor
محورهای موضوعی : Data Miningحسن فرسی 1 , Reza Nasiripour 2 , Sajad Mohammadzadeh 3
1 -
2 - University of Birjand
3 - University of Birjand
کلید واژه: Object retrieval , Speeded Up Robust Features (SURF) , Large-scale dataset , Supervised training , Training-Free,
چکیده مقاله :
Normally, the-state-of-the-art methods in field of object retrieval for large databases are achieved by training process. We propose a novel large-scale generic object retrieval which only uses a single query image and training-free. Current object retrieval methods require a part of image database for training to construct the classifier. This training can be supervised or unsupervised and semi-supervised. In the proposed method, the query image can be a typical real image of the object. The object is constructed based on Speeded Up Robust Features (SURF) points acquired from the image. Information of relative positions, scale and orientation between SURF points are calculated and constructed into the object model. Dynamic programming is used to try all possible combinations of SURF points for query and datasets images. The ability to match partial affine transformed object images comes from the robustness of SURF points and the flexibility of the model. Occlusion is handled by specifying the probability of a missing SURF point in the model. Experimental results show that this matching technique is robust under partial occlusion and rotation. The properties and performance of the proposed method are demonstrated on the large databases. The obtained results illustrate that the proposed method improves the efficiency, speeds up recovery and reduces the storage space.
Normally, the-state-of-the-art methods in field of object retrieval for large databases are achieved by training process. We propose a novel large-scale generic object retrieval which only uses a single query image and training-free. Current object retrieval methods require a part of image database for training to construct the classifier. This training can be supervised or unsupervised and semi-supervised. In the proposed method, the query image can be a typical real image of the object. The object is constructed based on Speeded Up Robust Features (SURF) points acquired from the image. Information of relative positions, scale and orientation between SURF points are calculated and constructed into the object model. Dynamic programming is used to try all possible combinations of SURF points for query and datasets images. The ability to match partial affine transformed object images comes from the robustness of SURF points and the flexibility of the model. Occlusion is handled by specifying the probability of a missing SURF point in the model. Experimental results show that this matching technique is robust under partial occlusion and rotation. The properties and performance of the proposed method are demonstrated on the large databases. The obtained results illustrate that the proposed method improves the efficiency, speeds up recovery and reduces the storage space.
P. Kontschieder, H. Riemenschneider, M. Donser, H. Bischof, “Discriminative learning of contour fragments for object detection”, In Proc. Brit. Mach. Vis. Conference. pp. 1-12, 2011.
X. Meng, Z. Wang, L. Wu, “Building global image feature for scene recognition”, Pattern Recognition. pp. 373-380, 2012.
B. Leibe, K. Schindler, N. Cornelis, L. Van Gool, “Coupled object detection and tracking from static cameras and moving vehicles", IEEE Transaction. Pattern. Anal Mach Intelligence, pp. 1683-1698, 2008.
H. Riemenschneider, M. Donoser, H. Bischof, “Using partial edge contour matches for efficient object category localization”, in Proc. Europa Conference Computer, pp. 29-42, 2010.
X. Yang, H. Liu, Latecki, “Contour-based object detection as dominant set computation”, Pattern Recognition, pp. 1927-1936, 2012.# V. Ferrari, T. Tuytelaars, and L. Van Gool, “Object detection by contour segment networks”, In (ECCV), 2006.
V. Ferrari, F. Jurie, and C. Schmid, “Accurate object detections with deformable shape models learnt from images”, In (CVPR), 2007.
V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid, “Groups of adjacent contour segments for object detection”, (PAMI), 2008.
X. Meng, Z.Wang, and L.Wu, “Building global image features for scene recognition”, Pattern Recognition, Vol.45, No.1, pp. 373–380, 2012.
B. Leibe, K. Schindler, N. Cornelis, and L. Van Gool, “Coupled object detection and tracking from static cameras and moving vehicles”, IEEE Trans. Pattern Anal. Mach. Intell, Vol.30, No.10, pp. 1683–169, 2008.
S. Agarwal, A. Awan, and D. Roth, “Learning to detect objects in images via a sparse, part-based representation” , IEEE PAMI, 2004.
Pages. Available: http://www.flickr.com.
Pages. Available http://wang.ist.psu.edu/docs/related.
J. Tangelder, R. Veltkamp, “Polyhedral model retrieval using weighted point sets”, Int. J. Image Graph, 2003.
R. Osada, T. Funkhouser, B. Chazelle, D. Dobkin, “Shape distributions”, ACM Transaction, 2002.# # A.Makadia, K.Daniilidis, “Spherical correlation of visual representations for 3D model retrieval”, Int.J.Computer, Vol.89, No.2, 2010.
L. Zhu, Y. Chen, A. Yuille, “Unsupervised learning of a probabilistic grammar-Markov models for object categories”, Pattern Analysis and Machine Intelligence, IEEE Transactions, pp. 114-128, 2009.
D. G. Lowe, “Object recognition from local scale-invariant feature”, In Proceedings of the International Conference on Computer Vision, pp. 1150-, 1999.
S. Malik, J. Puzicha, “Shape matching and object recognition using shape context”, IEEE Transaction. pp. 509-522, 2002.
E. Shechtman, M. Irani, “Matching local self-similarities across images and videos”, IEEE Conference on Computer Vision and Pattern Recognition, 2007.
H. Seo, P. Milanfar, “Training-free, generic object detection using locally adaptive regression kernels”, IEEE Transaction, pp. 1688-1704, 2010.
O. Chum, J. Philbin, J. Sivic, M. Isard, A.A. Zisserman, “Total recall: automatic query expansion with a generative feature model for object retrieval”, IEEE 11th International Conference, 2007.
R.Arandjelović, A.Zisserman, “Three things everyone should know to improve object retrieval”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
D.Qin, S.Gammeter, L.Bossard, T.Quack, L.V.Gool, “accurate object retrieval with k-reciprocal nearest neighbors”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
S. E. Grigoresco, N. Petkov, P. Kruizinga, “Comparision of texture features based on Gabor filters”, IEEE Transaction, pp. 1160-1167, 2002.
C. Grigorescu, N. Petcov, M. A. Westenberg, “Contour detection based on nonclassical receptive field inhibition”, IEEE Transaction, pp. 729-739, 2003.
Chun, Kim, Jang, “Content-based image retrieval using multi-resolution color and texture features”, IEEE Transaction, pp. 1073-1084, 2008.
Veganzones M. A, Grana, M, “A spectral/spatial CBIR system for hyper spectral images”, IEEE J. Sel. Top. Earth Obs. Remote Sens, pp. 488-500, 2012.
Montagna R, Finlayson, G.G, “Padua point interpolation and L^P-norm minimization in color-based image indexing and retrieval”, IET Image Process. pp. 139-147, 2012.
R. Troncy, B. Huet, S. Schenk, “Multimedia semantics, desktop edition (XML): metadata, analysis and interaction”, John Wiley & Sons Inc., New York, (1st edition), pp. 36-54, 2011.
A. Ibrahim, A. Zou'bi, R. Sahawneh, M. Makhadmeh, “Fixed representative colors feature extraction algorithm for moving picture experts group-7 dominant color descriptor”, Journal of Computer Science, pp. 773-777, 2009.# J. Philibin, O. Chum, M. Isard, J. Sivic, A. Zisserman, “Object retrieval with large vocabularies and fast spatial matching”, Computer Vision and Pattern Recognition (CVPR), pp. 1-8, 2007.
B. Geng, L. Yang, C. Xu, “A study of language model for image retrieval”, IEEE Int. Conf. Data Mining Workshops, IEEE Computer Society, pp. 158-163, 2009.
Linjun Yang, Bo Geng, Yang Cai, Alan Hanjalic, Xian-Sheng Hua, “Object retrieval using visual query context”, IEEE Transactions on multimedia, 2011.# # B. Herbert, E. Andreas, T. Tinne, V.G. Luc, “Speeded-up robust features (SURF)”, Computer vision and image understanding (CVIU), pp. 346-359, 2008.
J. YU, Z. C, T. W AND X. ZHANG, “Feature integration analysis of bag-of-features model for image retrieval”, Nero computing, [On-line], 2013.
J. Ng, F. Yang, and L. Davis. “Exploiting local features from deep networks for image retrieval”, In Computer Vision and Pattern Recognition Workshops (CVPRW), 2015.
A. Babenko and V. Lempitsky, “Aggregating local deep features for image retrieval”, In International Conference on Computer Vision (ICCV), 2015.
G. Tolias, R. Sicre, and H. J_egou, “Particular object retrieval with integral max-pooling of CNN activations”, arXiv preprint arXiv:1511.05879, 2015.
Y. Kalantidis, C. Mellina, and S. Osindero, “Cross-dimensional weighting for aggregated deep convolutional features”, arXiv:1512.04065, 2015.