Bookmark and Share

Software Topics

Illustration Signature
4 replies [Last post]
ndcolling
ndcolling's picture
Offline
Last seen: 6 years 47 weeks ago
Level 1: Prestidigitator
Joined: 2012-07-20
Points: 4

I'm thinking about working on a project that creates a sort of signature for illustrators based on their drawings. Has anyone heard of research around this problem and could you recommend some algorithms/papers that might help me get started (or scare me away)?

Chung Cha
Offline
Last seen: 6 years 40 weeks ago
Level 1: Prestidigitator
Joined: 2012-09-07
Points: 1

That's a good idea. Continue your research and find ways to solve your problem. Maybe this will help you electronic signature. I hope this will help you in a little way.

Jeff Bier
Jeff Bier's picture
Offline
Last seen: 5 weeks 4 days ago
EditorLevel 4: Thaumaturgist
Joined: 2011-05-29
Points: 93

Here's a paper that describes some related work:  http://web.math.princeton.edu/ipai/spm.pdf.

-jeff-

squreshi
Offline
Last seen: 1 year 41 weeks ago
Level 4: Thaumaturgist
Joined: 2011-05-31
Points: 95

I think what you might be after is a watermark, which are typically used for DRM (Digital Rights Management). There is a wealth of literature available online concerning watermarking technology, which must be impervious to compression artifacts.

Eric Gregori
Eric Gregori's picture
Offline
Last seen: 3 years 50 weeks ago
Level 6: Enchanter
Joined: 2011-08-16
Points: 202

It sounds like you are looking for CBIR (Content Based Image Retrievel).  These are algorithms that create unique image ID's for the purpose of storage, retrievel, and comparision.  

"In literature the term content based image retrieval (CBIR) has been used for the first time by

Kato et.al.[4], to describe his experiments into automatic retrieval of images from a database
by colour and shape feature. The typical CBIR system performs two major tasks [16,17]. The
first one is feature extraction (FE), where a set of features, called feature vector, is generated
to accurately represent the content of each image in the database. The second task is
similarity measurement (SM), where a distance between the query image and each image in
the database using their feature vectors is used to retrieve the “closest” images [16,17,26]."
 
 
 
The general concept is to compress the image down to a unique ID.  The compression is done by breaking the image down into unique features.  The unique ID, essentially "describes" the image.
 
The unique ID can then be used to find the image in a database or compare it to other images.