deleteIdentity
Locked
12
12
 
|
2014-07-15 20:09 GMT+02:00 Marcel Wiesweg <[hidden email]>:
> > >> Marcel, >> >> A patch attached below remove TLD data table from recognition >> database. I incremented DB revision in XML config file... >> >> It's fine for you ? > > Please also increment the number returned by SchemaUpdater::schemaVersion() to > 2. The currentRequiredVersion can remain at 1. > Then, I think it's fine. Done and committed : http://commits.kde.org/libkface/fc6ecdf932a948ddb84d0c76a988260494f63726 > For some reason, the necessary dummy updater methods > (updateV1ToV2) are already present. I can remove it if necessary, but this method is called by makeUpdates() Gilles _______________________________________________ Digikam-devel mailing list [hidden email] https://mail.kde.org/mailman/listinfo/digikam-devel |
|
|
Marcel,
This string returned by this method is wrong i think as TLD algorithm is fully replaced by LBPH: https://projects.kde.org/projects/extragear/libs/libkface/repository/revisions/master/entry/libkface/recognitiondatabase.cpp#L520 Right ? Gilles 2014-07-15 23:27 GMT+02:00 Gilles Caulier <[hidden email]>: > 2014-07-15 20:09 GMT+02:00 Marcel Wiesweg <[hidden email]>: >> >> >>> Marcel, >>> >>> A patch attached below remove TLD data table from recognition >>> database. I incremented DB revision in XML config file... >>> >>> It's fine for you ? >> >> Please also increment the number returned by SchemaUpdater::schemaVersion() to >> 2. The currentRequiredVersion can remain at 1. >> Then, I think it's fine. > > Done and committed : > > http://commits.kde.org/libkface/fc6ecdf932a948ddb84d0c76a988260494f63726 > >> For some reason, the necessary dummy updater methods >> (updateV1ToV2) are already present. > > I can remove it if necessary, but this method is called by makeUpdates() > > Gilles Digikam-devel mailing list [hidden email] https://mail.kde.org/mailman/listinfo/digikam-devel |
|
|
Marcel,
Do you take a look to OpenBR project in the past ? http://openbiometrics.org/ Gilles 2014-07-16 8:37 GMT+02:00 Gilles Caulier <[hidden email]>: > Marcel, > > This string returned by this method is wrong i think as TLD algorithm > is fully replaced by LBPH: > > https://projects.kde.org/projects/extragear/libs/libkface/repository/revisions/master/entry/libkface/recognitiondatabase.cpp#L520 > > Right ? > > Gilles > > 2014-07-15 23:27 GMT+02:00 Gilles Caulier <[hidden email]>: >> 2014-07-15 20:09 GMT+02:00 Marcel Wiesweg <[hidden email]>: >>> >>> >>>> Marcel, >>>> >>>> A patch attached below remove TLD data table from recognition >>>> database. I incremented DB revision in XML config file... >>>> >>>> It's fine for you ? >>> >>> Please also increment the number returned by SchemaUpdater::schemaVersion() to >>> 2. The currentRequiredVersion can remain at 1. >>> Then, I think it's fine. >> >> Done and committed : >> >> http://commits.kde.org/libkface/fc6ecdf932a948ddb84d0c76a988260494f63726 >> >>> For some reason, the necessary dummy updater methods >>> (updateV1ToV2) are already present. >> >> I can remove it if necessary, but this method is called by makeUpdates() >> >> Gilles Digikam-devel mailing list [hidden email] https://mail.kde.org/mailman/listinfo/digikam-devel |
|
|
In reply to this post by Gilles Caulier-4
> Marcel,
> > This string returned by this method is wrong i think as TLD algorithm > is fully replaced by LBPH: > > https://projects.kde.org/projects/extragear/libs/libkface/repository/revisio > ns/master/entry/libkface/recognitiondatabase.cpp#L520 > > Right ? Yes, it's wrong > >> For some reason, the necessary dummy updater methods > >> (updateV1ToV2) are already present. > > > > I can remove it if necessary, but this method is called by makeUpdates() I meant to say, we need these mehods now, they were there although not needed previously. All is well. > Do you take a look to OpenBR project in the past ? > > http://openbiometrics.org/ No, I have not seen this project yet.. After a quick read through the paper they mention, they use Viola-Jones faces detection (as we do), normalized by the detected eye location (brings difficulties in my experience, as the eye is often not detected) and by Tan- Triggs (simple, implemented in libkface). Recognition is based on LBP (as we do) and, in addition, SIFT descriptors and some improvements in the matching algorithm. _______________________________________________ Digikam-devel mailing list [hidden email] https://mail.kde.org/mailman/listinfo/digikam-devel |
|
|
2014-07-16 20:06 GMT+02:00 Marcel Wiesweg <[hidden email]>:
>> Marcel, >> >> This string returned by this method is wrong i think as TLD algorithm >> is fully replaced by LBPH: >> >> https://projects.kde.org/projects/extragear/libs/libkface/repository/revisio >> ns/master/entry/libkface/recognitiondatabase.cpp#L520 >> >> Right ? > > Yes, it's wrong Fixed : http://commits.kde.org/libkface/bbe822aeca1a2267a67cda283ebe347d78eb6010 Gilles > > >> >> For some reason, the necessary dummy updater methods >> >> (updateV1ToV2) are already present. >> > >> > I can remove it if necessary, but this method is called by makeUpdates() > > I meant to say, we need these mehods now, they were there although not needed > previously. All is well. ok > >> Do you take a look to OpenBR project in the past ? >> >> http://openbiometrics.org/ > > No, I have not seen this project yet.. > After a quick read through the paper they mention, they use Viola-Jones faces > detection (as we do), normalized by the detected eye location (brings > difficulties in my experience, as the eye is often not detected) and by Tan- > Triggs (simple, implemented in libkface). Recognition is based on LBP (as we > do) and, in addition, SIFT descriptors and some improvements in the matching > algorithm. Very interesting. The technic explain on OpenBR site is very instructive (i never look how form recognition and detection work previously). If i well read the code, there is a part, always compiled in libkface but not used due to bad results : funelreal.cpp It's to Align, Normalize, and Flat face elements for better analysis in case of train and later recognize using LBPH. If it's something like that, this part must be improved in the future, through GSoC. I'm sure that we can find a student easily to work on face management algorithm. Or perhaps you have others ideas to improve libkface in the future ? Gilles _______________________________________________ Digikam-devel mailing list [hidden email] https://mail.kde.org/mailman/listinfo/digikam-devel |
«
Return to digikam-devel
|
1 view|%1 views
| Free forum by Nabble | Edit this page |