Buckinghamshire CC ANPR cameras
pwt at iosis.co.uk
Tue Feb 7 08:37:09 GMT 2012
Doesn't Prof Peter White, Westminster Uni, specialise in the handling of
large dirty datasets? I know someone who did a PhD on that subject there
some 8 to 10 years ago, sponsored by DfT.
But then DfT is not good a spreading the knowledge that it has (or even
at using it internally)...
On 07/02/2012 08:29, Roland Perry wrote:
> In article <20120206214754.426156c7 at peterson.fenrir.org.uk>, Brian
> Morrison <bdm at fenrir.org.uk> writes
>> Since reg plates are not in one fixed position on vehicles it would need
>> a pretty complex algorithm to find the plate
> You have to do that to perform ANPR at all.
>> and then look only at one part of it,
> Wouldn't you "look at" all of it, then discard all but the middle?
>> particularly as some plates have all characters in a line
>> and others are split into two rows.
> See my first comment above. Also, for the purposes of Trafficmaster,
> you could simply disregard the small percentage of plates that have
> two rows.
More information about the ukcrypto