[digiKam-users] howto improove face recognition rate?

[Gerhard]

Hi,

now, some mor data....

After several runs and tagging face recogintion does not recognize any more out of already found faces (~25k images, ~6k faces not recognized ~14k already tagged).  But there are very much faces very similar to already recoginzed/tagged ones.

Is there a way for me to icrease recognition rate?

I've done some "case studies" with my data. Current settings yolo_v3, with accuracy rate at

• 100%  does not suggest any recogniton
• 95% finds one downscaled/compressed jpg (rate to 10% size=225kB, no edits)
• 90% one more suggestion but very inaccurate/wronn
• 85% found 3 more suggestions, one a perfect match, one a fairly reasonable, one bad
• 80% aims to recoginze/suggest  some more, but with a very low  recoginition rate (17/6000), and low match rate (10/71)
  

As i mentioned, having lots of very similar faces assinged already, i would assume this a poor recognition rate. (6k  pics, ~20% very similar to already tagged ones, but not found any suggestion.)

From the manual, it is suggested to remove tagged "weird" faces (carneval or other not very clear representations), to prevent false suggestions. But this would lead to a  processing and suggestion next run again, probably false again, wouldn't it?

Cheers, Gerhard

[Maik Qualmann]

Have you rebuilt the training database in the maintenance tool (option in the
face detection section) if you have already tagged faces with an older digiKam
version?

Maik

Am Sonntag, 16. Mai 2021, 21:16:21 CEST schrieb KRODER Gerhard:

> Hi,
>
> now, some mor data....
>
> After several runs and tagging face recogintion does not recognize any
> more out of already found faces (~25k images, ~6k faces not recognized
> ~14k already tagged).  But there are /very much faces very similar/ to
> already recoginzed/tagged ones.
>
> Is there a way for me to icrease recognition rate?
>
> I've done some "case studies" with my data. Current settings yolo_v3,
> with accuracy rate at
>
>   * 100%  does not suggest any recogniton
>   * 95% finds one downscaled/compressed jpg (rate to 10% size=225kB, no
>     edits)
>   * 90% one more suggestion but very inaccurate/wronn
>   * 85% found 3 more suggestions, one a perfect match, one a fairly
>     reasonable, one bad
>   * 80% aims to recoginze/suggest  some more, but with a very low
>     recoginition rate (17/6000), and low match rate (10/71)
>
> As i mentioned, having lots of very similar faces assinged already, i
> would assume this a poor recognition rate. (6k  pics, ~20% very similar
> to already tagged ones, but not found any suggestion.)
>
>  From the manual, it is suggested to remove tagged "weird" faces
> (carneval or other not very clear representations), to prevent false
> suggestions. But this would lead to a  processing and suggestion next
> run again, probably false again, wouldn't it?
>
> Cheers, Gerhard

[Gerhard]

Hi,

this is a new 7.2 version, no previous processing/DB data, so no rebuild
others than starting face detecting/recogintion tool.

Am 16.05.2021 um 22:15 schrieb Maik Qualmann:

> Have you rebuilt the training database in the maintenance tool (option in the
> face detection section) if you have already tagged faces with an older digiKam
> version?
>
> Maik
>
> Am Sonntag, 16. Mai 2021, 21:16:21 CEST schrieb KRODER Gerhard:
>> Hi,
>>
>> now, some mor data....
>>
>> After several runs and tagging face recogintion does not recognize any
>> more out of already found faces (~25k images, ~6k faces not recognized
>> ~14k already tagged).  But there are /very much faces very similar/ to
>> already recoginzed/tagged ones.
>>
>> Is there a way for me to icrease recognition rate?
>>
>> I've done some "case studies" with my data. Current settings yolo_v3,
>> with accuracy rate at
>>
>>    * 100%  does not suggest any recogniton
>>    * 95% finds one downscaled/compressed jpg (rate to 10% size=225kB, no
>>      edits)
>>    * 90% one more suggestion but very inaccurate/wronn
>>    * 85% found 3 more suggestions, one a perfect match, one a fairly
>>      reasonable, one bad
>>    * 80% aims to recoginze/suggest  some more, but with a very low
>>      recoginition rate (17/6000), and low match rate (10/71)
>>
>> As i mentioned, having lots of very similar faces assinged already, i
>> would assume this a poor recognition rate. (6k  pics, ~20% very similar
>> to already tagged ones, but not found any suggestion.)
>>
>>   From the manual, it is suggested to remove tagged "weird" faces
>> (carneval or other not very clear representations), to prevent false
>> suggestions. But this would lead to a  processing and suggestion next
>> run again, probably false again, wouldn't it?
>>
>> Cheers, Gerhard
>
>
>

[Maik Qualmann]

How many faces per person and in total have you assigned so far to train face
recognition?

Maik

Am Montag, 17. Mai 2021, 01:11:58 CEST schrieb KRODER Gerhard:

> Hi,
>
> this is a new 7.2 version, no previous processing/DB data, so no rebuild
> others than starting face detecting/recogintion tool.
>
> Am 16.05.2021 um 22:15 schrieb Maik Qualmann:
> > Have you rebuilt the training database in the maintenance tool (option in
> > the face detection section) if you have already tagged faces with an
> > older digiKam version?
> >
> > Maik
> >
> > Am Sonntag, 16. Mai 2021, 21:16:21 CEST schrieb KRODER Gerhard:
> >> Hi,
> >>
> >> now, some mor data....
> >>
> >> After several runs and tagging face recogintion does not recognize any
> >> more out of already found faces (~25k images, ~6k faces not recognized
> >> ~14k already tagged).  But there are /very much faces very similar/ to
> >> already recoginzed/tagged ones.
> >>
> >> Is there a way for me to icrease recognition rate?
> >>
> >> I've done some "case studies" with my data. Current settings yolo_v3,
> >> with accuracy rate at
> >>
> >>    * 100%  does not suggest any recogniton
> >>    * 95% finds one downscaled/compressed jpg (rate to 10% size=225kB, no
> >>    
> >>      edits)
> >>    
> >>    * 90% one more suggestion but very inaccurate/wronn
> >>    * 85% found 3 more suggestions, one a perfect match, one a fairly
> >>    
> >>      reasonable, one bad
> >>    
> >>    * 80% aims to recoginze/suggest  some more, but with a very low
> >>    
> >>      recoginition rate (17/6000), and low match rate (10/71)
> >>
> >> As i mentioned, having lots of very similar faces assinged already, i
> >> would assume this a poor recognition rate. (6k  pics, ~20% very similar
> >> to already tagged ones, but not found any suggestion.)
> >>
> >>   From the manual, it is suggested to remove tagged "weird" faces
> >>
> >> (carneval or other not very clear representations), to prevent false
> >> suggestions. But this would lead to a  processing and suggestion next
> >> run again, probably false again, wouldn't it?
> >>
> >> Cheers, Gerhard

[Gerhard]

out of about 26000 image items total

• ~13900 images w/o any face detected
• ~13700  faces detectet
• ~6000 facces verified/asigned (rate ~44%)                        
  
• ~5100 unknowns
  
• dupes not yet solved
• some small persona collections  up to 50%
• large collections ~15% (estmiation)
  

out of ~150 persona tags,  top faces already assigned /confirmed

• Sa ~4000
  
• Ph ~750
  
• Si ~330
• Bru ~300
• Mar ~190
  
• Ka ~150
• So ~100
• An ~90
  

Descending numbers for all others

Am 17.05.2021 um 07:50 schrieb Maik Qualmann:

How many faces per person and in total have you assigned so far to train face 
recognition? 

Maik

Am Montag, 17. Mai 2021, 01:11:58 CEST schrieb KRODER Gerhard:

Hi,

this is a new 7.2 version, no previous processing/DB data, so no rebuild
others than starting face detecting/recogintion tool.

Am 16.05.2021 um 22:15 schrieb Maik Qualmann:

Have you rebuilt the training database in the maintenance tool (option in
the face detection section) if you have already tagged faces with an
older digiKam version?

Maik

Am Sonntag, 16. Mai 2021, 21:16:21 CEST schrieb KRODER Gerhard:

Hi,

now, some mor data....

After several runs and tagging face recogintion does not recognize any
more out of already found faces (~25k images, ~6k faces not recognized
~14k already tagged).  But there are /very much faces very similar/ to
already recoginzed/tagged ones.

Is there a way for me to icrease recognition rate?

I've done some "case studies" with my data. Current settings yolo_v3,
with accuracy rate at

   * 100%  does not suggest any recogniton
   * 95% finds one downscaled/compressed jpg (rate to 10% size=225kB, no
   
     edits)
   
   * 90% one more suggestion but very inaccurate/wronn
   * 85% found 3 more suggestions, one a perfect match, one a fairly
   
     reasonable, one bad
   
   * 80% aims to recoginze/suggest  some more, but with a very low
   
     recoginition rate (17/6000), and low match rate (10/71)

As i mentioned, having lots of very similar faces assinged already, i
would assume this a poor recognition rate. (6k  pics, ~20% very similar
to already tagged ones, but not found any suggestion.)

  From the manual, it is suggested to remove tagged "weird" faces

(carneval or other not very clear representations), to prevent false
suggestions. But this would lead to a  processing and suggestion next
run again, probably false again, wouldn't it?

Cheers, Gerhard