A survey and experimental evaluation of image spam filtering techniques
Pattern Recognition Letters
On online high-dimensional spherical data clustering and feature selection
Engineering Applications of Artificial Intelligence
A survey of image spamming and filtering techniques
Artificial Intelligence Review
Hi-index | 0.00 |
Image spam has become a real threat to email communication these days, since most prevalent content based spam filters can not efficiently detect them out, even when the latest OCR techniques are employed, spammers could compromise the system easily through text distortion and other obscuring skills. In this paper, we propose a novel and efficient image modeling approach for spam image classification, this content based statistical model does not rely on the availability of text information embedded in the image files, so that it is robust to obfuscations. Experimental results show that the proposed method can perform with good accuracy in practice.