A picture is worth a thousand words. Spam images give us many hints; one of them is that they are duplicates. Spam images are often generated from the same templates (which are designed by spammers) as they are sent to various recipients at the same time in batches. Various spam images are generated by randomization of the contents of these templates; as a result a similarity or uniqueness is present among the spam images. This similarity property in visually similar spam images can be exploited by the spam detectors for discriminating them from ham. The spam detectors can further trained on new data, if the spam images are generated from different templates, which is not a frequent phenomenon as it is resources intensive. The detection schemes that exploit the near duplicate characteristics of image spam, uses different types of image characteristics to calculate the similarity among spam images. This chapter provides the details of near duplicate detection based image spam filters, a literature review on these spam filters and their limitations.
Top5.1. Examples Of Similar Images
Some of the examples of similar images which may be generated by spammers using different randomizing techniques are as follows.
5.1.1. Illustration Substitution
It means some of the illustrations are changed with some other illustrations and rest all the other things remains the same. It can be easily understood by the Figure 1 in which text matter in both the images are same, but the bunch of leaves at the top right corner is replaced by the ball of red ribbon. These two images are almost same only differs at the top right corner. The feature of these images differs very little due to the changes made by the spammer. So the technique based on near duplicate detection will easily detect these images made from the same base or template image.
Figure 1. Spam images with illustration substitution