Face Recognition Tips?

Hey Aperture Geniuses (Geni?),
I've been playing around with Aperture 3.0 (only 8000 photos so far ), and I was just curious about the face recognition tech. I know it's supposed to get more accurate as you tag each person with more photos, but what if some of the earlier photos look a bit different from recent ones? Not massively different (not like a child->adult gap, but more teen->adult); would it be best to perhaps keep four year old photos in a separate library to keep the face finder more accurate? Or anything else that I can do to keep it accurate?
What if I ID like a side-view of my face; will that screw up the preview?
I'm just curious about how the tech works, it's very interesting to me. Thanks so much!
Message was edited by: Laurel Grant

Hi Laurel
I'd keep them in the same Library (even though I only have a bit over 5000 images ).
For example: I have quite a lot of shots of my parents, who are now senior citizens. In one shot I was processing recently, Aperture identified a photo of my mother which was pinned to the wall in the background of the photo (my father sitting at their iMac). This was a modern mono laser print (about 8x10" from what I can remember) of a scan of black and white photo taken by my father from around about when they were just married, so that's about a 50 year gap.
I believe I recall also having some success with correct identifications of my nieces. My digital photos range back to late 2001, so their ages have ranged from 9 to 19.
It certainly doesn't get everything right, but I remain more rather than less impressed with the basic technology.
Someone recently posted a link to an Apple knowledge base article describing the face-detection technology in iPhoto (from which Aperture's tech is presumably derived). It said that only faces which are identified by Aperture count as far as identification if individuals is concerned. ie images to which you have added a face square don't count. They're part of the database for that individual, but they don't influence the subsequent identification of people. Which is quite a good thing, since I have more than a few side-on images and even a bunch which are shots of an individual from the back.
Based on observed behaviour, I believe it's sometimes worth telling Aperture to re-detect for faces after doing the first few of a batch. It seems that when it's failed to identify the presence of a face in the initial pass during importing (especially if it's someone new), after teaching it some of the faces it has detected first time around it helps it to detect a face (though perhaps not identify it) when you make a second detection pass.
Regards,
Gary

Similar Messages

  • Face Recognition problem...

    I always get a failed logon when using the face recognition for my u405d-s2902 i set the security low already but still get failed.. can you give me some tips how this face recognition works? pls help thanks...

    You will need webcam on computer and a software pkg: Not too secure, all I have read so far, can be fooled.
    Extracted data: Freeware application BananaScreen adds face recognition login to your webcam-enabled Windows computer. To use, just install BananaScreen and create a face model. Then set up BananaScreen to lock after a predefined amount of inactivity (or hit Alt-L to lock at any time). Once locked, BananaScreen will keep an eye on faces coming and going in front of the camera. When it matches yours, it immediately unlocks your computer. NOT SECURE!
    Check out www.bananasecurity.com   www.alibaba.com   www.luxand.com
    CONTRIBUTOR DISCLAIMER...We are only identifying sources relative to Ezekiel post, and in no way recommend altering OS registry H Key code settings.  May cause unit lockup at owners risk too install. 

  • LRCC Face recognition - best practices?

    Ok so we are all new to the wonderful world of face recognition in LR.  I'm trying to work out what would be the best practices for using this.
    A little bit of background - I have a catalog of over 200,000 images.  In addition to portrait and wedding clients, a significant part of my work is with models and another significant part of my work is theatre photography.  I have be wanting some sort of face recognition to help with both for some time.
    What are your namining conventions for people? - here's mine:
    Ideally I would label people as "surname, firstname" so that I can keep members of a family together in "named people" display, but commas are not allowed in names.  Also the professional name of many models doesn't fit that pattern eg "Strawberry Venom" or "Cute as Sin" are to models I have worked with.
    I am trying to come up with a sensible naming convention at the moment it is "Surname/ Firstname" for clients, theatre folk and friends/family.  Models are still a problem, at present I am thinking of "Surname/ Firstname (model name(s))"  While I may not be able to remember the real names of models, I do usually know the names from model releases.  This naming will still permit me to filter/find them in the keyword List panel by just entering the model name.
    On final addition I am making to this this naming convention is the use of a hashtag suffix to the name:  #F for friends and family, #C for clients, #T for theatre/actors and #M for models.  This enables me to filter on just models, or just actors, or just friends and familiy.  Where people fall into multiple categories I add multiple hashtags.  So photos of me would be keyworded with "Butterfield/ Ian #F #T"
    Unknown / unidentified people.
    What I am not yet certain about is how to handle unknown / unidentified people.  Unidentified people fall into a number of different categories.
    People I don't know and I am never likely to know (Eg random strangers on the street, local tour guides on holiday, random people in the background etc)
    This group is relatively easy to deal with - that is to simply delete the face recognition, End of story.
    People I don't know the names of yet but I am likely to find out (Eg actors in a production for which I don't have a programme)
    For these people I am making up a unique name using the format "date/ Context-Gendernn" Eg an unknown male actor at Stockport Garrick Theatre would be named as "20150313/ SGT-M01"  Although this may appear a complex solution it has a number of advantages.  If/when I do learn the name of the individual (Eg I photograph them in a different production) it is simply a case of renaming the people keyword.  Creating a unique name and not simple assigning all unknowns to a bucket name will help the face recognition algorithms find this person without it being confused by have different faces assigned to the same name. I am also using the hashtage #U to make it easier to filter the unknown faces when I need to.
    People I don't know the names of and there is only a slim possibility of meeting/photographing again (Eg guests as a client weeding)
    It feels as though I out to just delete the face recognition and have done with it, and this is what I would do except for thing. Other than manually drawing face regions I have not yet found a way to get lightroom to rescan a folder for faces if you have previously deleted the face recognition.  This means that deleting face regions from a large number of people is something that cannot be easily reversed.  I might just leave these people in the "Unnamed People" category... at lease until such time as there is a way to rescan a folder or colectoin.
    Summary
    My practices are still evolving. But I hope these thoughts and idea will help others think through the issues and come up with solutions that work for their situation.  I am interested in hearing how other people are using the face recognition system.  Especially if anyone is aware of any 'best practices' that Adobe or anyone else has recommended.

    Glad it helped.
    Yes and no.  You can still put the people keywords into hierarchies within the keyword list - you can arrange them just like any other keywords.so you just create a "smith family" keyword and store "john smith" under it.  What you can't do is apply BOTH smith family and john smith the the same face.
    My use of the hash tags came about because I initially had a top level keyword for models, one for clients, one for theatre peple and one for family and firends.  Then discovered that some of the theatre folk were also clients (headshots) and what to do when a friend is also a client.  So the hash tag system means a person can be both a friend, a model, an actor as well as being a client!  (#T #C #M #F).

  • How do I turn off faces recognition in iphoto

    how do I turn off faces recognition in iphoto?  I mean forever!!

    So by deleting the "Face Profile" or whatever it's called for the individual Faces keeps searching for, you think that's not a solution?
    The actual pictures identified by faces are not deleted. Only the avatar and name you list to be looked for within faces is what you're removing.
    Do you have a better solution? I'm all ears.

  • How do I permanently REMOVE the Face Recognition program in Windows 8.1?

    I want to Uninstall, permanently REMOVE, the Face Recognition program from Windows 8.1.  When I select this program from the list of all programs displayed, I am not given an "uninstall" option, only the option to "change", which
    then begins to install.  I was able to uninstall once before, but somehow the program was placed back onto my computer and now the "uninstall" option is no longer available.  Thanks!

    Hello DePaix,
    What is your current situation?
    Have you tried the solution as MVP Cyber_Defend_Team mentioned?
    Do this program preinstalled? If yes, we need to contact the manufacturer to receive better support.
    If my understanding is right, you uninstalled it once, but the program was back and only the option to ‘change’.
    Could you please provide us a screenshot to avoid misunderstanding if you willing to?
    Can you run the program? If the program runs in the startup, we could use the tool System Configuration (msconfig) to disable apps or services that normally run at startup.
    For more information, please take a look at the following article about using system configuration.
    http://windows.microsoft.com/en-hk/windows/using-system-configuration#1TC=windows-8
    Best regards,
    Fangzhou CHEN
    Fangzhou CHEN
    TechNet Community Support

  • Advanced Sort, Filter (color, image size), DUPLICATES, face recognition, GUI customizeability

    Hi,
    here are some of my Lightroom Feature Requests (maybe later more):
    - Filter based on image size. Example: show me all photos with a resolution of 1600x1200 or less.
    - More complex filtering. Example: show me all photos from the Collection A that are tagged with keyword 'k1' and 'k2' but not with keyword 'k3' and that are in the date range d1-d2 and were made with camera model X.
    - Automatic portrait/human face recognition
    - Sort and filter by color! Example: show me all photos that are mostly green (blue, yellow, red, ...)
    - Intelligent recognition and optional deletion of duplicates. Calculate some kind of fingerprint for each photo (file size won't do I guess) so that it will be possible to recognize duplicates EVEN if they are of different image resolution or orientation (landscape, portrait), i.e. really based on CONTENT of the image!
    - Make the components in the side panels movable so that the user can arrange his/her own panel with the components he uses most and on that side of the screen where he wants it.
    Besides that: I LOVE Lightroom. A GREAT product!! Use it A LOT!
    Nice greetings from Germany,
    Stefan.

    I second that.
    "More complex filtering. Example: show me all photos from the Collection A that are tagged with keyword 'k1' and 'k2' but not with keyword 'k3' and that are in the date range d1-d2 and were made with camera model X."
    This should be relatively easy to do. Most other DAMs in the market, e.g. ACDSee, do have this feature. It doesn't really becomes a real database until you have this feature.
    "Intelligent recognition and optional deletion of duplicates."
    Another great feature in ACDSee. Somehow it finds duplicates, even if filenames and dates are different, shows the different photos and gives you an option on what to do.

  • HT3442 How do you correct the spelling of a name in Face recognition

    How do I change a name in iPhoto face recognition where it is spelt incorrectly?

    You're welcome. Then you're not doing it right. Double click on the name until it's selected - the background will turn dark grey. Then you can edit it.

  • No face recognition in iPhoto on my iPad 2

    Hello, thank you for opening this thread.
    Today I uploaded the photo for the first time on to my iPad 2. When I open the photos, there are Photos, Albums, Events, Places, but there is no "Faces."
    I searched the discussion board but I could not find an answer how to let iPhoto do the face recognition.
    Could someone please help me?
    Thank you!!

    Faces will only show as an option in the Photos app on the iPad if you've synced photos from your Mac which have 'faces' associated with them (http://support.apple.com/kb/HT4236 : 'iPhoto ’09, you can also add your Faces, Places, and Events to your device.', and the manual 'Events and Faces must first be configured in iPhoto or Aperture on a Mac, then synced to iPad') - i.e. it must be associated with photos prior to syncing them to the iPad.
    If you've synced photos with Faces to the iPad and they aren't showing, then try closing the Photos app completely : from the home screen (i.e. not with Photos 'open' on-screen) double-click the home button to bring up the taskbar, then press and hold any of the apps on the taskbar for a couple of seconds or so until they start shaking, then press the '-' in the top left of the Photos app to close it, and touch any part of the screen above the taskbar so as to stop the shaking and close the taskbar.
    If that doesn't work then you could try a reset : press and hold both the sleep and home buttons for about 10 to 15 seconds (ignore the red slider), after which the Apple logo should appear - you won't lose any content, it's the iPad equivalent of a reboot.

  • How to reset the Face Recognition on folder to start the search/detection over again.

    I was going along fine (though very slowly) and had 5000 photos identified as my son. Hours later I was down to a few handful of photo and did a select all and dragged then to my son's named photo. After that I can still see all the photos of him, but Lightroom does not look to detect face on any of the pictures. I tried Photos--> People and all is greyed out. The first run through it detected them (until I did the Select all) and all the photos are still there. It is like Lightroom does not think there are people in the picture and there are , or it thinks that it already analyzed them and will keep doing so.
    Is there a way to tell Lightroom to re-analyse this folder (5k of photos) to look for people again. Lightroom seems to have forgotten the Face Regions?
    All the other proper in the 5K photos are designed correctly.

    I agree with Zim. When you start Toshiba Face recognition tool click on option register Face.
    On the right side click on Next and start to practice the face recognition option. For the first time using the face recognition, practicing is very useful. If you choose skip the recognition will start without practicing.
    Toshiba Face recognition tool takes a digital snapshot of the users face to create a unique password by digital mapping of key features of the users face. Please set also password. Password (inputting through keyboard) is the backup solution when user cannot log-on by face recognition through Web Camera.
    It is not complicated. Just follow menu on the screen.

  • BUG: Face recognition data not saved to images.

    i have the option to automatically save XMP data into the images activated.
    so all keywords and metadata changes are not only saved to the catalog but also into my DNG and TIFF images.
    now this works fine for everything except the new face recognition data.
    i mean the areas (rectangles) where the faces are.
    i guess the problem is that the images already contain the keywords (names) of the persons in the images.
    what i did was using the rectangles to identify the persons in the images. drawing rectangles around their faces and name them.
    this info about the rectangle positions is NOT automatically stored in the image files. not after hours of letting LR run idle.
    this info is only stored when i manually save (CTRL+S) the images or do something other to the metadata (like adding NEW keywords to it).
    so in short:  just adding the face region data (the rectangles) will not trigger the automatic XMP save function when the name keyword was already asigned as keyword to the image.
    that´s very bad and must considered a bug in my opinion..
    i don´t like to rely on the LR catalog only. it´s unsave even with backups.
    i want that the metadata info is stored in the images.
    also when i give away my images i want that the metadata is in the images.
    that´s why "automatically save XMP" is always active and very important for me.

    I don't have any info but repost your original info at this site.  Supposedly Adobe reads this and it should not get lost in the clutter  I have posted a few bugs there and they were acknowledged but not fixed but Adobe seems to be pretty good at fixing potential data loss bugs/problems which I consider this to be if it is working as you describe.
    Photoshop Family Customer Community

  • IPhoto 09 face recognition

    I would like to know if the iPhoto 09 face recognition feature is ON by default and can't be switched off even if we feel we don't need it.
    The reason I ask is that, after a year of Leopard, I am really exasperated at this Spotlight regularly monopolizing 95% of processor time, uncontrollably trying to index the whole Universe, just in case I might want to search the contents of files, a feature that is ON by default and can't be switched off even if we feel we don't need such an overkill process.
    Same with Time Machine, that starts archiving everytime an external drive is plugged in, unless we rush to the Time Machine System Preferences and navigate to the Confidential tab to kill the already running indiscretion.
    I just hope that iPhoto 09 didn't join this recent un-Apple philosophy that uncontrollably overworks processors and noisy fans, temporarily slowing the fastest computer in the World to the speed of my first Mac SE, just because it decides you're an idiot that might not know its own needs.
    Sorry about that !
    I just had to let it out ...
    PP

    iPhoto menu -> Provide iPhoto Feedback
    If you find that Spotlight is “regularly monopolizing 95% of processor time“ then you have a problem with Spotlight. This is not how i works on nay of my machines. Perhaps you need to troubleshoot that.
    I was able to turn off Time machine with no difficulty. Perhaps you need to read the help.
    The faces feature use a one time scan of the iPhoto Library when you first launch 09. Thereafter it does nothing at all unless you use it.
    Regards
    TD

  • Face recognition using labview

    I, am into my final year project. I am  doing face recognition using labview. I want to know how to compare image using labview. it would be  great if someone helped , as it is proving to be a major obstacle in my way

    Hi Sibom,
    There are various face recognizing algorithms available. If your purpose is simple face recognition, then the simplest method would be to segment the image using a line, and to perform the recognition for every tilt of the image.Tthus when the line traces 180 degrees, all possible positions would have been verified. 
    If you like a more holistic approach you can have a look at the trace transform model and the active appearance model, which are used in the industry.
    These models can be studied at : 
     http://www.face-rec.org/algorithms/#Image
    Here are a few other algorithms for face recognition :
    *Automated Face Detection System utilizing USB WebCam 
    *Face Recognition using Vector Quantization Histogram Technique 
    Regards,
    Siva
    A Face Recognition Software using Vector Quantization Histogram Technique 

  • Can't download new face recognition driver for Qosmio G50

    Hi!
    Can't download new face recognition driver for G50 hinted by TEMPRO.
    Possibly bad link: http://81.27.174.53/tedd-files2/0/fareg-20081009112217.zip

    hi TTG
    i got de message on ma TEMPRO and i clicked to dwnload..
    this software can be installed to these models which is having Windows Vista 32 Bit:-
    Tecra A10, Equium L350D, Satellite L300D, Satellite U400, Satellite Pro A300D, Qosmio F50, Satellite Pro L300D, Portege M800, Qosmio X300, Satellite P300D, Equium U400, Satellite Pro P300D, Satellite L350, Satellite Pro P300, Satellite Pro U400, Satellite L300, Satellite L350D, Equium L350, Satellite Pro L350, Equium A300D, Satellite Pro L300, Equium A300, Equium P300D, Satellite Pro S300, Satellite Pro A300, Tecra S10, Equium P300, Satellite A300D, Tecra M10, Satellite A300, Satellite P300, Equium L300, Qosmio G50

  • Strange UI bug when using People view/face recognition

    I've started playing with the face recognition in LR6/CC and have encountered an odd display bug when viewing the groups of 'named people':
    The thumbnail for each named person includes a count of how many images (or perhaps that should be faces) are attributed to their specific name. However, once the number of images for a person exceeds 100, LR only displays the first two digits in the thumbnail and drops off the third one, e.g. 254 is displayed as 25. If you hover over the thumbnail, the full count (e.g. 254) is displayed so long as the mouse cursor is kept on the thumbnail. Interestingly, once the number of images attributed to a named person exceeds 1000, it does the same thing, only it adds an extra digit (so 1400 becomes 140).
    I'm running this on Win7.
    Anyone else seeing this?
    M

    I guess I was primarily "testing the water" to see if the problem was specific to my configuration in some way, but you make a fair point John.
    Here's my (possible) bug report: LIGHTROOM Facial recognition: thumbnails not displaying full number
    M

  • How does Aperture Face recognition work

    Just upgraded to Aperture 3 --- I'm a little baffled by the functionality of the face recognition. Aperture certainly found most (if not all) of the faces in my collection but I thought it was supposed to be able to actually do recognition (to some extent) so that when I associate a certain face with a name, it would automatically find the same face in other photos and mark them.
    I am not seeing any evidence that this actually happens --- I just seem to keep getting fed faces along the bottom that I have to name manually, even if it's a very similar picture that was already seen.
    What am I missing?

    I've noticed that sometimes (seems like all the time, but I've only done a few imports) when I first import new photos it can take a long time before Aperture decides to search for similar faces.
    I can tag a few pics of people in the "Faces View" and then double-click their photo to try to see suggested matches, but watching the "Activity Window" shows no searching for similar faces... I don't know what's stopping it, but it just doesn't seem to even bother searching for quite some time. It's not that it's still detecting faces in the photos (I've checked to see it's finished doing that) — there's nothing in the Activity Window and the CPU usage of Aperture is basically zero. Memory is not full, nothing else is using the CPU, it's just sitting there doing nothing...
    And then randomly, suddenly, it seems to remember that it is meant to search for similar faces and does so...
    Would be interested to see if others are having similar behaviour, where Aperture just doesn't even bother searching until some event, or some time after importing... Open up the Activity window in Aperture (from the Window menu), double-click on a face in the faces view and see if it starts searching for similar faces... if it's not even searching, then that might explain why you're not being given the ability to match faces. If it is searching, then I guess it's just not finding anything. Also note that you won't get any matches until the search finishes (it can take quite a while to search through the photos for similar faces; likely depends on (and is slowed down by) the number of faces for that person, the number of 'unknown faces', the total number of faces and/or people in your library)

Maybe you are looking for