Spam is most often considered to be electronic junk mail. Spam is defined as unsolicited bulk mail. Image spam is a kind of email spam where the spam text is embedded with an image. Spam email has become difficult in the survival of internet users, causing personal injury and economic losses. In this paper, we propose a feature extraction scheme which focuses on low-level features, like metadata and visual features of images. This technique makes classification better and it is an effective method because it does not depend on extracting text and examining the content of email. A SVM classifier with kernel function is used to identify an image spam and also the accuracy will be calculated.

1. N. Nhung and T. Phuong. "An Efficient Method for Filtering Image Based Spam mail". Proc. IEEE International Conference on Research, Innovation and Vision for the Future (RIVF 07), IEEE Press, Mar. 2007, pp. 96-102. doi: 1O. 1109/RIVF. 2007. 369141.
2. B. Mehta, S. Nangia, M. Gupta. "Detecting image spam using visual features and near duplicate detection". WWW, 2008.
3. HQ. Zuo, x. Li, O. Wu, W. M. Hu , G. Luo. "Image spam filtering using Fourier-Mellin invariant features". ICASSP, 2009.
4. Z. Qu and Y Zhang, "Filtering Image Spam using Image Semantics and Near-Duplicate Detection," Proc. the 2nd International Conference on Intelligent Computation Technology and Automation (ICICTA 2009), IEEE Press, Oct. 2009, in press.
5. Z. Wang, W. Josephson, Q. Lv, M. Charikar, K. Li. "Filtering Image Spam with Near Duplicate Detection". In Fourth Conference on Email and Anti-Spam, August 2-3, 2007, Mountain View, California USA.
6. C. Wu, K. Cheng, Q. Zhu, and Y Wu. "Using Visual Features for Anti-spam Filtering". Proc. IEEE International Conference. Image Processing (ICIP 05). IEEE Press, Sept. 2005 pp. 509-12. doi:10. 1109/ICIP. 2005. 1530440.
7. M. Dredze, R. Gevaryahu, A. E. Bachrach. "Learning Fast Classifiers for Image Spam". In Fourth Conference on Email and Anti-Spam, August 2-3, 2007, Mountain View, California USA.
8. H Aradhye, G. Myers, and J. Herson. "Image Analysis for Efficient Categorization of Image-based spam E-mail". Proc. IEEE Conf. Document Analysis and Recognition (ICDAR 05), IEEE Press, Aug 2005 pp. 914-918, doi: 1O. 1109/lCDAR2005. 135.
9. G. Fumera, I. PilIai, F. Roli. "Image Spam Filtering using textual and visual Information". MIT Spam Conference 2007, 30 March 2007, Cambridge, MA, USA.
10. W. Ma, D. Tran, and D. Sharma, "Detecting Image based Spam Email," Proc. First International Conference on Hybrid Information Technology (ICHIT 06), Springer Press, Nov. 2006, pp. 168-177, doi: 10. 1007/978-3-540-77368-9.
11. J. Shih and L. Chen, "Color Image Retrieval based on Primitives of Color Moments," Lecture Notes in Computer Science, vol 2314, 2002, pp. 19-27, doi: 10. 1007/3-540 45925-1_8.
12. D. Gavilan, H. Takahashi, and M. Nakajima, "Image Categorization Using Color Blobs in a Mobile Environment," Computer Graphics Forum (EG 2003), 22(3), 2003, pp. 427-432.
13. A. K. Jain and A. Vailaya, "Shape-based retrieval: a case study with trademark image database", Pattern Recognition 31 (9) (1998) 1369-1390
14. K. Tsuda, "Support vector classification with asymmetric kernel function". Proc. of 7th European symposium on Artificial Neural Networks, 1999, pp. 183-188.
15. A. Androutsopoulos, J. Koutsias, K. V. Cbandrinos, and C. D. Spyropoulos. "An experimental comparison of naïve bayesian and keyword-based anti-spam filtering with personal e-mail messages". In Proc. ACM Int. Conf. on Research and Developments in Information Retrieval, pages 160–167,2000.
16. H. Drucker, D. Wu, and V. N. Vapnik. "Support vector machines for spam categorization". IEEE Transaction on Neural Networks, 10(5):1048–1054, 1999.

Email Ham Image Spam Image Svm Classifier