Image based spam blocking
A fingerprint of an image identified within a received message is generated following analysis of the message. A spam detection engine identifies an image within a message and converts the image into a grey scale image. The spam detection engine analyzes the grey scale image and assigns a score. A fingerprint of the grey scale image is generated based on the score. The fingerprint may also be based on other factors such as the message sender's status (e.g. blacklisted or whitelisted) and other scores and reports generated by the spam detection engine. The fingerprint is then used to filter future incoming messages.
1. A method for filtering an image based message, the method comprising:
receiving an image based message from a sender,
executing instructions stored in memory, wherein execution of the instructions by a processor:
converts an image located within the received image based message into a grey scale image,
analyzes the grey scale image to identify whether one or more text lines appear within the grey scale image,
determines whether the one or more text lines fit a numeric pattern comprising a number of characters and a number of spaces, and
assigns a score to the grey scale image based on the presence or absence of the one or more text lines within the grey scale image and whether the one or more text lines fit the numeric pattern comprising the number of characters and the number of spaces; and
filtering the received image based message based on the assigned score.
2. The method of claim 1 , further comprising delivering the received image based message to the message recipient following the determination that the received message is a good message, the good message having a fewer number of text lines within the image than a spam message.
3. The method of claim 1 , further comprising blocking delivery of the received image based message to the message recipient following the determination that the received message is a spam message, the spam message having a greater number of text lines within the image than a good message.
4. The method of claim 1 , wherein analyzing the grey scale image includes using edge detection techniques.
5. The method of claim 1 , wherein analyzing the grey scale image includes removing background noise associated with the image.
6. The method of claim 1 , wherein analyzing the grey scale image further includes generating a histogram of a number of non-white pixels located within the grey scale image, the histogram serving as a basis for determining the presence or absence of the one or more text lines within the image.
7. A system for filtering an image based message, the system comprising:
a processor to execute instructions;
a spam detection engine executable by the processor to:
convert an image located within the image based message into a grey scale image,
analyze the grey scale image to identify whether one or more text lines appear within the grey scale image,
determine whether the one or more text lines fit a numeric pattern comprising a number of characters and a number of spaces,
assign a score to the grey scale image based on the presence or absence of = the one or more text lines within the grey scale image and whether the one or more text lines fit the numeric pattern comprising the number of characters and the number of spaces; and
filter the received image based message based on the assigned score; and
a memory to store:
the spam detection engine,
the grey scale image; and
the score assigned to the grey scale image.
8. The system of claim 7 , wherein analyzing the grey scale image further includes generating a histogram of a number of non-white pixels located within the grey scale image, the histogram serving as a basis for determining the presence or absence of the one or more text lines within the grey scale image.
9. The system of claim 7 , wherein analyzing the grey scale image includes using edge detection techniques.
10. A non-transitory computer-readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for filtering an image based message, the method comprising:
receiving an image based message from a sender;
converting an image located within the received image based message into a grey scale image;
analyzing the grey scale image to identify whether one or more text lines appear within the grey scale image;
determining whether the one or more text lines fit a numeric pattern comprising a number of characters and a number of spaces;
assigning a score to the grey scale image based on the presence or absence of the one or more text lines within the grey scale image and whether the one or more text lines fit the numeric pattern comprising the number of characters and the number of spaces; and
filtering the received image based message based on the assigned score.