|
The UKHA-ARCHIVE IS CEASING OPERATIONS 31 DEC 2024
|
|
[Date Prev][Date
Next][Thread Prev][Thread Next][Date
Index][Thread Index]
Re: Re: NOW : Face recognition WAS Car number plate
capture/recognition
- To: <ukha_d@xxxxxxx>
- Subject: Re: Re: NOW : Face recognition WAS Car number
plate capture/recognition
- From: "Dave McLaughlin" <dave@xxxxxxx>
- Date: Fri, 5 Jul 2002 10:47:22 +0100
- Mailing-list: list ukha_d@xxxxxxx; contact
ukha_d-owner@xxxxxxx
- References: <ag3pea+6a7b@xxxxxxx>
- Reply-to: ukha_d@xxxxxxx
Have a look at this 78 neuron neural net chip. Pure hardware based
neural
net for applications such as this.
The video demos give you an idea on what it can do. I have also seen a
demo
that detected room occupancy even if you changed the room around as it
looked for moving objects and there size etc.
http://www.siliconrecognition.com/
Dave...
----- Original Message -----
From: "graham_howe" <graham@xxxxxxx>
To: <ukha_d@xxxxxxx>
Sent: Friday, July 05, 2002 10:38 AM
Subject: [ukha_d] Re: NOW : Face recognition WAS Car number plate
capture/recognition
> > One way to do it just now could be by measuring differences from
a
> > baseline "unoccupied" image. Based on the size of
the object you
> could
> > probably distinguish people from cats (or milk monsters?)
> >
> The big problem with this approach is things like furniture being
> moved, large bags or boxes being left in a room, or even a big
shadow
> or patch of sunlight.
>
> Don't get me wrong, I too believe that this will be the eventual
> method for occupany detection, but it is a little more complicated
> than just detecting that the 'scene' has changed from 'baseline'.
>
> Graham
For more information: http://www.automatedhome.co.uk
Post message: ukha_d@xxxxxxx
Subscribe: ukha_d-subscribe@xxxxxxx
Unsubscribe: ukha_d-unsubscribe@xxxxxxx
List owner: ukha_d-owner@xxxxxxx
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
Home |
Main Index |
Thread Index
|
|