TY - JFULL AU - T. Kumaresan and S. Sanjushree and C. Palanisamy PY - 2014/11/ TI - Image Spam Detection Using Color Features and K-Nearest Neighbor Classification T2 - International Journal of Computer and Information Engineering SP - 1903 EP - 1907 VL - 8 SN - 1307-6892 UR - https://publications.waset.org/pdf/10000193 PU - World Academy of Science, Engineering and Technology NX - Open Science Index 94, 2014 N2 - Image spam is a kind of email spam where the spam text is embedded with an image. It is a new spamming technique being used by spammers to send their messages to bulk of internet users. Spam email has become a big problem in the lives of internet users, causing time consumption and economic losses. The main objective of this paper is to detect the image spam by using histogram properties of an image. Though there are many techniques to automatically detect and avoid this problem, spammers employing new tricks to bypass those techniques, as a result those techniques are inefficient to detect the spam mails. In this paper we have proposed a new method to detect the image spam. Here the image features are extracted by using RGB histogram, HSV histogram and combination of both RGB and HSV histogram. Based on the optimized image feature set classification is done by using k- Nearest Neighbor(k-NN) algorithm. Experimental result shows that our method has achieved better accuracy. From the result it is known that combination of RGB and HSV histogram with k-NN algorithm gives the best accuracy in spam detection. ER -