No subject

are indeed the best indicator of what is and what is not a commercial.
Actually it would be more correct to say the distance between the blank
frames is the best indicator. Logo detection and such just helps to bump up
the accuracy a little bit.

--00c09f8de6b226ec2e0472887f5e
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div class=3D"gmail_quote">On Tue, Sep 1, 2009 at 2:27 AM, Yeechang Lee <sp=
an dir=3D"ltr">&lt;<a href=3D"mailto:ylee at pobox.com">ylee at pobox.com</a>&gt;=
</span> wrote:<br><blockquote class=3D"gmail_quote" style=3D"border-left: 1=
px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"=
>

MythTV&#39;s commflagging has worked quite well for me for almost four<br>
years, with very few false positives or false negatives. (I use All<br>
Methods and Strict on -fixes.) But it managed to impress me again<br>
today.<br>
<br>
I began recording from CNBC HD a few days ago. For those who haven&#39;t<br=
>
seen it, various scrolling banners, charts, and other data occupy one<br>
third of the screen at all times. Nonetheless, mythcommflag accurately<br>
picks up the commercial breaks. How in the world does it do this? I<br>
know it can&#39;t be the logo detection; is it the blank frames?<br>
<font color=3D"#888888"></font></blockquote><div><br>From some work i did o=
n the subject, here in the US at least, Blank frames are indeed the best in=
dicator of what is and what is not a commercial. Actually it would be more =
correct to say the distance between the blank frames is the best indicator.=
 Logo detection and such just helps to bump up the accuracy a little bit.=
=A0 <br>

</div></div><br><br clear=3D"all"><br>

--00c09f8de6b226ec2e0472887f5e--