Actas de congresos
Pr: More Than Meets The Eye
Registro en:
Proceedings Of The Ieee International Conference On Computer Vision. , v. , n. , p. - , 2007.
10.1109/ICCV.2007.4408921
2-s2.0-50649107656
Autor
Rocha A.
Goldenstein S.
Institución
Resumen
In this paper, we introduce a new image descriptor for broad Image Categorization, the Progressive Randomization (PR), that uses perturbations on the values of the Least Significant Bits (LSB) of images. We show that different classes of images have a distinct behavior under our methodology, and that using statistical descriptors of LSB occurrences and enough training examples, the method already performs as well or better than comparable existing techniques in the literature. With few training examples, PR still has good separability, and its accuracy increases with the size of the training set. We validate our method using four image databases with different categories. ©2007 IEEE.
Allwein, E.L., Schapire, R.E., Singer, Y., Reducing multiclass to binary: A unifying approach for margin classifiers (2001) JMLR, 1, pp. 113-141 Bosch, A., Zisserman, A., Munoz, X., Scene classification via pLSA (2006) ECCV Cutzu, F., Hammoud, R., Leykin, A., Distinguishing paintings from photographs (2005) CVIU, 100, pp. 249-273 Fei, L.F., Fergus, R., Perona, P., One-shot learning of object categories (2006) TPAMI, 28 (4), pp. 594-611 Freedman, D., Pisani, R., Purves, R., Statistics (1978) George J, , McLeod Limited Fridrich, J., Goljan, M., Du, R., Reliable detection of LSB steganography in color and grayscale images (2001) ACM Multimedia and Security, pp. 27-30 Friedman, J., Hastie, T., Tibshirani, R., (2001) The elements of statistical learning, , Springer Verlag Grauman, K., Darrell, T., Efficient Image Matching with Distributions of Local Invariant Features (2005) CVPR, pp. 627-634 Heidemann, G., Unsupervised image categorization (2005) Image and Vision Computing, 23, pp. 861-876 J. Sivic and B. Russell and A. Efros and A. Zisserman and and W. Freeman. Discovering objects and their location in images. In ICCV, pages 370-377, 2005Luo, J., Savakis, A., Indoor vs. outdoor classification of consumer photographs using low-level and semantic features (2001) ICIP, pp. 745-748 Lyu, S., Farid, H., How realistic is photorealistic? (2005) IEEE Trans. on Signal Proc, 53, pp. 845-850 Marszałek, M., Schmid, C., Spatial Weighting for Bag-of-Features (2006) CVPR, pp. 2118-2125 Maurer, U., A universal statistical test for random bit generators (1992) Journal of Cryptology, 5, pp. 89-105 Oliva, A., Torralba, A.B., Modeling the shape of the scene: A holistic representation of the spatial envelope (2001) IJCV, 42 (3), pp. 145-175 Payne, A., Singh, S., Indoor vs. outdoor scene classification in digital photographs (2005) Pattern Recognition, 38 (10), pp. 1533-1545 A. Rocha and S. Goldenstein. Progressive Randomization for Steganalysis. In 8th IEEE Intl. MMSP, 2006Serrano, N., Savakis, A., Luo, J., A computationally efficient approach to indoor/outdoor scene classification (2002) 16th ICPR, pp. 146-149 Vailaya, A., Jain, A., Zhang, H.J., On image classification: City images vs. landscapes (1998) Pattern Recognition, 31, pp. 1921-1935 Vogel, J., Schiele, B., A semantic typicality measure for natural scene categorization (2004) DAGM Annual Pattern Recognition Symposium Wayner, P., (2002) Disappearing cryptography, , Morgan Kaufmann Publishers Westfeld, A., Pfitzmann, A., Attacks on steganographic systems (1999) 3rd Intl. Workshop on Information Hiding, pp. 61-76