Similar articles

Abstract: Content-based satellite image registration is a difficult issue in the fields of remote sensing and image processing. The difficulty is more significant in the case of matching multisource remote sensing images which suffer from illumination, rotation, and source differences. The scale-invariant feature transform (SIFT) algorithm has been used successfully in satellite image registration problems. Also, many researchers have applied a local SIFT descriptor to improve the image retrieval process. Despite its robustness, this algorithm has some difficulties with the quality and quantity of the extracted local feature points in multisource remote sensing. Furthermore, high dimensionality of the local features extracted by SIFT results in time-consuming computational processes alongside high storage requirements for saving the relevant information, which are important factors in content-based image retrieval (CBIR) applications. In this paper, a novel method is introduced to transform the local SIFT features to global features for multisource remote sensing. The quality and quantity of SIFT local features have been enhanced by applying contrast equalization on images in a pre-processing stage. Considering the local features of each image in the reference database as a separate class, linear discriminant analysis (LDA) is used to transform the local features to global features while reducing dimensionality of the feature space. This will also significantly reduce the computational time and storage required. Applying the trained kernel on verification data and mapping them showed a successful retrieval rate of 91.67% for test feature points.

The authors present a novel method that benefits from the advantages of both local and global features in the field of satellite image retrieval. They use a methodology inspired by the SIFT algorithm using a pre-processing stage and transforming local features produced by SIFT keypoint detector and descriptor to general type image features using LDA. The results indicate that the proposed method combines the advantages of both local and global features while severely reduces their disadvantages.

一种快速均匀的采用尺度不变特征变换描述符进行基于内容的卫星图像配准方法

[1]Andre, B., Vercauteren, T., Buchner, A.M., et al., 2012. Learning semantic and visual similarity for endomicroscopy video retrieval. IEEE Trans. Med. Imag., 31(6): 1276-1288.

[2]Arica, N., Vural, F.T.Y., 2003. BAS: a perceptual shape descriptor based on the beam angle statistics. Patt. Recogn. Lett., 24(9-10):1627-1639.

[3]Bakar, S.A., Hitam, M.S., Wan, Y., et al., 2013. Content-based image retrieval using SIFT for binary and greyscale images. IEEE Int. Conf. on Signal and Image Applications, p.83-88.

[4]Bhatia, S.K., Samal, A., Vadlamani, P., 2007. RISE-SIMR: a robust image search engine for satellite image matching and retrieval. Int. Symp. on Visual Computting, p.245-254.

[5]Bhattacharya, D., Bhaskar, K., 2013. Efficient aerial image matching algorithm for autonomous navigation of aerial vehicle. Int. J. Sci. Eng. Technol., 2(12):1204-1207.

[6]Blanchart, P., Datcu, M., 2010. A semi-supervised algorithm for auto-annotation and unknown structures discovery in satellite image databases. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., 3(4):698-717.

[7]Chandrakanth, R., Saibaba, J., Varadan, G., et al., 2014. A novel image fusion system for multisensor and multiband remote sensing data. IETE J. Res., 60(2):168-182.

[8]Chu, L., Jiang, S., Wang, S., et al., 1996. Robust spatial consistency graph model for partial duplicate image retrieval. IEEE Trans. Multim., 15(8):1982-1996.

[9]Dagher, I., Sallak, N., Hazim, H., 2014. Face recognition using the most representative SIFT images. Int. J. Signal Process. Imag. Process. Patt. Recogn., 7(1):225-236.

[10]Eugenio, F., Marqués, F., 2003. Automatic satellite image georeferencing using a contour-matching approach. IEEE Trans. Geosci. Remote Sens., 41(12):2869-2879.

[11]Goswami, D., Bhatia, S.K., Samal, A., 2007. RISE: a robust image search engine. IEEE Int. Conf. on Electron/ Information Technology, p.354-359.

[12]Irtazaa, A., Jaffarb, M.A., Aleisab, E., 2013. Correlated networks for content based image retrieval. Int. J. Comput. Intell. Syst., 6(6):1189-1205.

[13]Kupfer, B., Netanyahu, N.S., Shimshoni, I., 2015. An efficient SIFT-based mode-seeking algorithm for sub-pixel registration of remotely sensed images. IEEE Geosci. Remote Sens. Lett., 12(2):379-383.

[14]Li, H., Wang, X., Tang, J., et al., 2013. Combining global and local matching of multiple features for precise item image retrieval. Multim. Syst., 19(1):37-49.

[15]Li, J., Narayanan, R.M., 2004. Integrated spectral and spatial information mining in remote sensing imagery. IEEE Trans. Geosci. Remote Sens., 42(3):673-685.

[16]Li, Z., Park, U., Jain, A.K., 2011. A discriminative model for age invariant face recognition. IEEE Trans. Inform. Forens. Secur., 6(3):1028-1037.

[17]Liu, G., Sun, X., Fu, K., et al., 2013. Aircraft recognition in high-resolution satellite images using coarse-to-fine shape prior. IEEE Geosci. Remote. Sens. Lett., 10(3): 573-577.

[18]Lowe, D.G., 2004. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis., 60(2):91-110.

[19]Maloo, A., Thepade, S.D., Kekre, H., 2010. CBIR feature vector dimension reduction with eigenvectors of covariance matrix using row, column and diagonal mean sequences. Int. J. Comput. Appl., 3(12):39-46.

[20]Manuel, I., Tavares, R.S., Natal, J., 2013. Computational Vision and Medical Image Processing IV. CRC Press, London, UK.

[21]Meena, K., Suruliandi, A., Reena, R.R., 2014. Face recognition based on local derivate ternary pattern. IETE J. Res., 60(1):20-32.

[22]Mikolajczyk, K., Schmid, C., 2005. A performance evaluation of local descriptors. IEEE Trans. Patt. Anal. Mach. Intell., 27(10):1615-1630.

[23]Nileshsingh, V., Koli, N., 2010. An overview of feature extraction methods in CBIR. Int. J. Comput. Sci. Appl., 3(2):71-76.

[24]Okade, M., Biswas, P.K., 2014. Improving video stabilization using multi-resolution MSER features. IETE J. Res., 60(5):373-380.

[25]Sedaghat, A., Mokhtarzade, M., Ebadi, H., 2011. Uniform robust scale-invariant feature matching for optical remote sensing images. IEEE Trans. Geosci. Remote Sens., 49(11):4516-4527.

[26]Sedaghat, A., Mokhtarzade, M., Ebadi, H., 2012. Image matching of satellite data based on quadrilateral control networks. Photogr. Rec., 27(140):423-442.

[27]Singaravelan, S., Murugan, D., 2013. Combined global–local specialized feature descriptor for content based image retrieval under noisy query. Int. Conf. on Advanced Computing and Communication Systems, p.1-6.

[28]Stehling, R.O., Nascimento, M.A., Falcão, A.X., 2002. A compact and efficient image retrieval approach based on border/interior pixel classification. Proc. 11th Int. Conf. on Information and Knowledge Management, p.102-109.

[29]Torres, R.S., Picado, E.M., Falcao, A.X., et al., 2003. Effective image retrieval by shape saliences. 16th Brazilian Symp. on Computer Graphics and Image Processing, p.167-174.

[30]Valenzuela, R.E.G., Schwartz, W.R., Pedrini, H., 2012. Dimensionality reduction through PCA over SIFT and SURF descriptors. IEEE 11th Int. Conf. on Cybernetic Intelligent Systems, p.58-63.

[31]Veganzones, M.A., Maldonado, J.O., Grana, M., 2008. On content-based image retrieval for hyper spectral remote sensing images. In: Graña, M., Duro, R.J. (Eds.), Computational Intelligence for Remote Sensing. Springer-Verlag, Berlin, Germany, p.125-144.

[32]Wen, G.J., Lv, J.J., Yu, W., et al., 2008. A high-performance feature-matching method for image registration by combining spatial and similarity information. IEEE Trans. Geosci. Remote Sens., 46(4):1266-1277.

[33]Wu, Y.Y., Wu, Y.Q., 2009. Shape based image retrieval using combining global and local shape features. 2nd Int. Congress on Image and Signal Processing, p.12-20.

[34]Yu, I., Zhang, D., Holden, E.J., 2008. A fast and fully automatic registration approach based on point features for multi-source remote-sensing images. Comput. Geosci., 34(7):838-848.