Bot releases are hidden (Show)
Published by matiasdelellis almost 4 years ago
Person View | Photos of person | Person Integration | Assign Name |
---|---|---|---|
Published by matiasdelellis almost 4 years ago
Person View | Photos of person | Person Integration | Assign Name |
---|---|---|---|
Published by matiasdelellis about 4 years ago
Fixed some minor bugs introduced in the new model. Nothing special if you haven't changed the model yet. 😅 However, they are necessary corrections that deserve a new release. 😉
Also reduce the minimum system memory to 1GB. Keep in mind that this would be the absolute minimum, but it is clear that for large installations it may be insufficient.
Published by matiasdelellis about 4 years ago
Well... In the last month, there were only few changes that came in this release, but before there was a lot of research and testing, to come up with this little release. You can see the PR https://github.com/matiasdelellis/facerecognition/pull/294 to see part of the main discussion.
But the main conclusion is that we discovered that model 2 has many grouping problems, and therefore we should advise against its use. 😞
If you are using it, sorry, but we suggest you migrate your faces to model 1, 3, if you dare, to model 4. However, I must recommend the analysis from scratch when switching to any model.
Perhaps the most important thing about this release is the introduction of model 4, which in summary is an extension of model 1, where we do a validation of the faces using the detector of model 3, to avoid clustering faces which potentially cause problems.
As you can see in this image, these are faces that the CNN detector finds, but the landmark detector fails to align the faces. We are fortunate that HOG does not detect these faces. and we take advantage of that, to validate the faces, and not group these faces. So, you can still see these faces, you can name them, but they will not clustered with others causing errors.
In our tests with 433 Images of The Big Bang Theory we got that:
433 Images | Model 1 | Model 2 | Model 3 | Model 4 |
---|---|---|---|---|
Faces | 1405 | 1405 | 1024 | 1405 |
Total clusters | 757 | 730 | 423 | 820 |
Faces in Bad Clusters | 13 | 63 | 0 | 0 |
Faces Error % | 0,93 % | 4,48 % | 0,00 % | 0,00 % |
As you can see, the quality of groupings improved dramatically. 😃
(and here we reaffirm avoiding model 2. Sorry again..)
...but this is also expensive:
433 Images | Model 1 | Model 2 | Model 3 | Model 4 |
---|---|---|---|---|
AVG Time | 16,70 | 16,59 | 41,56 | 50,21 |
Procesing Time | 02:00:29 | 01:59:43 | 04:59:56 | 06:02:19 |
Percentage | 100,00 % | 99,37 % | 248,93 % | 300,71 % |
It is two times slower. 😞
Well, It's still in testing stages, but it looks promising and everyone will know if it is worth it. 😉
All notable changes to this project will be documented in this file.
Published by matiasdelellis over 4 years ago
I don't know how reliable is this, but it seems that the application was downloaded 3079 times in two months. 🎉
facerecognition_v0.6.0.tar.gz (0.25 MiB) - downloaded 3,079 times. Last updated on 2020-05-05
Well, Far from believing that they are all using the app, I was pleasantly surprised by the number. 😄
In two months there were few reports of errors. Just 2 reports that we never test certain options without having the model installed, and a couple of documentation reports. Also help a couple of users install the dependencies, but overall it seems that all the effort to document was worth it. 😃
And finally there is still confusion about how to interpret the quality of the recognition. Our users still expect to see a single perfect group, and they want to ignore unknown people. Our current focus is to show all the information we have and it seems to be overwhelming. I'm still not clear how to improve this (Although removing the faces view, and leaving the work to photos/viewer would solve everything. 😅) but if users can have perfect groups, even if they are several, I would be really satisfied.
So, I would like to do a small survey to the users to know how they use it, their expectations and the results. 🤔
All notable changes to this project will be documented in this file.
Published by matiasdelellis over 4 years ago
After almost 3 years of development (Wow .. a long time. 😄) we are pleased to publish this face recognition application for Nextcloud. 🎉
Special thanks to Branko Kokanovic (@stalker314314 in Github). He wrote me a simple email a year ago since he intended to do something similar and we joined forces in making this application. Thank you very much. 😃
Of course also appreciate the @goodspb work for the PDlib extension that does most of the magic. Many thanks. 😃
... and I can't stop thanking all the users who test this application, reported errors, suggested changes, or translated the application. Thank you very much to all!. 🥰
It probably has flaws, and surely there are things to improve... but we understand that it is fully functional for everyone can try it.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis over 4 years ago
After almost 3 years of development (Wow .. a long time. 😄) we are pleased to publish this face recognition application for Nextcloud. 🎉
Special thanks to Branko Kokanovic (@stalker314314 in Github). He wrote me a simple email a year ago since he intended to do something similar and we joined forces in making this application. Thank you very much. 😃
Of course also appreciate the @goodspb work for the PDlib extension that does most of the magic. Many thanks. 😃
... and I can't stop thanking all the users who test this application, reported errors, suggested changes, or translated the application. Thank you very much to all!. 🥰
It probably has flaws, and surely there are things to improve... but we understand that it is fully functional for everyone can try it.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis over 4 years ago
All notable changes to this project will be documented in this file.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis over 4 years ago
All notable changes to this project will be documented in this file.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis over 4 years ago
All notable changes to this project will be documented in this file.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis almost 5 years ago
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis almost 5 years ago
After two years of development, we are pleased to publish this face recognition application for Nextcloud.
Special thanks to Branko Kokanovic (@stalker314314 in Github). He wrote me a simple email a year ago since he intended to do something similar and we joined forces in making this application. Thank you very much!.
It probably has flaws, and surely there are things to improve.. . but we understand that it is fully functional for everyone can try it.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.
Published by matiasdelellis almost 5 years ago
After two years of development, we are pleased to publish this face recognition application for Nextcloud.
Special thanks to Branko Kokanovic (@stalker314314 in Github). He wrote me a simple email a year ago since he intended to do something similar and we joined forces in making this application. Thank you very much!.
It probably has flaws, and surely there are things to improve.. . but we understand that it is fully functional for everyone can try it.
If you want to help us to improve it, we invite you to test it. Please, leave us your comments, open new Issues, translate it and any pull request is welcome. 😄
We suggest you read our documentation and mainly the installation notes and the FAQ.