Fighting malware and spam

OCR

Process of translating an image into plain text

OCR, or Optical Character Recognition, is a technique that converts an image containing text into plain text. Most spam filters use OCR technology to attempt to catch image spam (spam in which the message is contained within an image rather than in plain text). In attempts to circumvent OCR, some spammers use animated images, or images where the text is displayed on a colourful background.

Spammers themselves use OCR techniques in their attempts to solve CAPTCHAs.

Related web links

• Bye bye OCR?
• The rise and rise of image-based spam (Virus Bulletin, November 2006)

Poll

VB100 certification