Re: [Rtftr-devel] Promising detection results

[Anjan <roc...@gm...>]

Yeah, we'll start extraction from the frame tomorrow and integrate with the
recognition module. The result should be ok. Also, the detection time is 0.5
secs, processing the video at 1 FPS won't be a problem.

On Tue, Mar 17, 2009 at 4:37 PM, Bibek Shrestha <bib...@gm...>wrote:

> The result is really nice.
> One thing i notice on the detected images are they are uniform. In case of
> frontal faces, you can see that the face detected starts from a little above
> the eyes to 2-3pixels below chin.
>
> I think the results are promising enough, may be we could now train the
> recognition module with extraction module?
>
> Regards
>
> 2009/3/17 Anjan <roc...@gm...>
>
>> The attached image shows the detection performance of adaboost detector on
>> webcam images. The result is of 11 stages of the cascade and the average
>> detection time is around 0.5 seconds on a 256x192 image.
>>
>>
>> --
>> Anjan Nepal
>>
>> GPO Box 11458
>> Registered Linux User #395963
>>
>>
>>
>> ------------------------------------------------------------------------------
>> Apps built with the Adobe(R) Flex(R) framework and Flex Builder(TM) are
>> powering Web 2.0 with engaging, cross-platform capabilities. Quickly and
>> easily build your RIAs with Flex Builder, the Eclipse(TM)based development
>> software that enables intelligent coding and step-through debugging.
>> Download the free 60 day trial. http://p.sf.net/sfu/www-adobe-com
>> _______________________________________________
>> Rtftr-devel mailing list
>> Rtf...@li...
>> https://lists.sourceforge.net/lists/listinfo/rtftr-devel
>>
>>
>
>
> --
> Bibek Shrestha
> bibekshrestha at gmail dot com
>



-- 
Anjan Nepal

GPO Box 11458
Registered Linux User #395963