[R] compare two fingerprint images

[Charles C. Berry]

On Sun, 4 Apr 2010, Tal Galili wrote:

> Hi Jim,
> Another thing I am wondering is - even if you have a metric for comparing
> two images (which I admit I didn't come across and I don't know how to
> approach), would that be enough to decide if two images are "close" or not?
> My guess is that no - one would also need a database of other fingerprints,
> to compare how much a particular image is closer to another image, compared
> to how other images are close to that image.

Well, I am not Jim, but there is a literature on fingerprint ID starting 
before 1892 when Galton's "Finger Prints" was published (see below).


And yes, you need a database.

 	 "The main challenge in studies of fingerprint individuality is
           to adequately capture the variability of fingerprint features
           in a population. "

from:

Sarat C. Dass and Mingfei Li, Hierarchical mixture models for assessing 
fingerprint individuality. Ann. Appl. Stat. Volume 3, Number 4 (2009), 
1448-1466.

===

See

 	http://galton.org/fingerprinter.html

for a summary of Francis Galton's work and a links to classic works like 
his 1892 opus:

"Let no one despise the ridges on account of their smallness, for they are 
in some respects the most important of all anthropological data. " Galton 
1892.

It is amusing to me to ponder how Galton might have revised that 
statement in view of modern DNA sequencing technology. 'Let no one despise 
the nucleotide bases on account of their smallness, ...'


HTH,

Chuck


>
>
>
> Tal
>
>
> ----------------Contact
> Details:-------------------------------------------------------
> Contact me: Tal.Galili at gmail.com |  972-52-7275845
> Read me: www.talgalili.com (Hebrew) | www.biostatistics.co.il (Hebrew) |
> www.r-statistics.com (English)
> ----------------------------------------------------------------------------------------------
>
>
>
>
> On Sun, Apr 4, 2010 at 1:55 AM, Jim Lemon <jim at bitwrit.com.au> wrote:
>
>> On 04/04/2010 05:18 AM, Juan Antonio Gil Pascual wrote:
>>
>>> Hi Bernado
>>>
>>> I need to compare two fingerprint images and let me know if you can do
>>> with R. I have used the technique of minutiae but it seems to work
>>> better with the cross-correlation and wanted to know if you can do with R.
>>>
>>>  Hi Juan,
>> If you're using minutiae, you will want something like character
>> recognition to identify the (admittedly arbitrary) elements of fingerprints
>> like loops and whorls and their relative extents and positions. I don't know
>> whether there is much character recognition stuff done in R, but it would
>> certainly be related.
>>
>> Jim
>>
>>
>> ______________________________________________
>> R-help at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

Charles C. Berry                            (858) 534-2098
                                             Dept of Family/Preventive Medicine
E mailto:cberry at tajo.ucsd.edu	            UC San Diego
http://famprevmed.ucsd.edu/faculty/cberry/  La Jolla, San Diego 92093-0901