[digiKam-users] howto improove face recognition rate?

[KRODER 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
      o some small persona collections  up to 50%
      o 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
>
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.kde.org/pipermail/digikam-users/attachments/20210517/7a52c09f/attachment.htm>