Another idea (US-centric): those awful TVPG (etc) ratings logos
in the upper left, which apparently became mandated after -every-
commercial break fairly recently, no doubt because of panic over
the wardrobe malfunction incident. In two sizes---godawful huge
at the start of the program, and merel
On Sat, 10 Dec 2005 05:45 am, Chris Pinkham wrote:
> > - Australia doesn't have blanks between ads so changed MAX_COMM_LENGTH
> > to match MAX_COMM_BREAK_LENGTH (is this the right thing to do?)
> I think that would accomplish what you want yes. In SVN, you could use
> the undocumented 'CommDetect
Date: Fri, 9 Dec 2005 17:16:48 -0500 (EST)
From: [EMAIL PROTECTED]
Another idea that might deserve some thought: Looking for the sudden
disappearance of closed-captioning information.
If anyone's inspired to actually try this, I just dug up a really
excellent tool that will help;
On 12/9/05, [EMAIL PROTECTED] <[EMAIL PROTECTED]> wrote:
Hey, whaddya know! It's someone from the MIT Media Lab (Who is famous
for such things as this) talking about Machine Learning for Commercial
Flagging (Something like a Neural Net, or the like).
Perhaps some changes could be made to the "C
Date: Sat, 10 Dec 2005 01:27:11 +0100
From: "Pascal Favre" <[EMAIL PROTECTED]>
I use commflagging for all my channels, the results depend highly on the
channel.
There are several options which are global. Would it make sense a user can
set the options on each channel, which are p
From: "Chris Pinkham" <[EMAIL PROTECTED]>
Just to give you an idea of what other things I may be looking into
shortly, here are a few things from my TODO:
* Keep track of min/max brightness found during logo detection so we can
use that information later to determine what is rea
Date: Fri, 9 Dec 2005 14:45:09 -0500 (EST)
From: "Chris Pinkham" <[EMAIL PROTECTED]>
Just to give you an idea of what other things I may be looking into
shortly, here are a few things from my TODO:
* Keep track of min/max brightness found during logo detection so we can
> Chris Pinkham and interested persons,
>
> I've been messing with the commercial detector in 18.1 (very similar to svn
> version) to improve detection of Australian ads. Here is what I've found so
> far using the ALL method:
Yeah, I haven't spent much time recently in the flagger although the
On Friday 09 December 2005 09:41, Paul Andreassen wrote:
> Chris Pinkham and interested persons,
>
> I've been messing with the commercial detector in 18.1 (very similar to svn
> version) to improve detection of Australian ads. Here is what I've found
> so far using the ALL method:
>
> - Strict i
Chris Pinkham and interested persons,
I've been messing with the commercial detector in 18.1 (very similar to svn
version) to improve detection of Australian ads. Here is what I've found so
far using the ALL method:
- Strict is better because otherwise all white screens detected as blanks.
10 matches
Mail list logo
