Re: Image forensics

[Martin Tomasek <tomasek () ufe cz>]

Dan Kaminsky napsal(a):
> I also dont doubt the fundamental thesis that  
> some manipulation can be detected (especially in a trivial case like  
> 'was this image downsized' or 'was this saved by Photoshop instead of  
> a Canon camera', which is obvious from quantization tables if not from  
> the raw EXIF).

Well.. the manipulations you mention doesn't seem like something bad to 
me. And it is pretty normal to retouch the photos. No professional 
photographer would sell unretouched photos.

And just one more thing: standard formats for photographs are raw 
formats. Most people use tools from adobe for jpeg conversion. So, you 
if you are insurance company for example, you can detect adobe-specific 
quantisation algorithms, but it does not prove fradulent manipulation. 
If software like adobe lightroom is involved in the process, it even 
does light sharpening before export to jpeg (the reason of this is that 
transfer of jpeg to photographic paper blurs the photo slightly).

I wonder what would image manipulation detectors detect in photos with 
heavy tonality corrections, such as photos from inca's gold exhibition 
in my gallery:
http://www.ufe.cz/~tomasek/gallery/zlato_inku/index.html 
<http://www.ufe.cz/%7Etomasek/gallery/zlato_inku/index.html>

or in photos with split toning:
http://www.ufe.cz/~tomasek/gallery/zvire_v_pasti/content/DSC_2822_large.html 
<http://www.ufe.cz/%7Etomasek/gallery/zvire_v_pasti/content/DSC_2822_large.html>

-- 
Martin Tomasek

_______________________________________________
Fun and Misc security discussion for OT posts.
https://linuxbox.org/cgi-bin/mailman/listinfo/funsec
Note: funsec is a public and open mailing list.