Facial Recognition per se for Thumbnails

I have about 500 images of people for an online directory and also for MS Outlook 2010 contact images. I need to generate images 95 x 95 pixels of only their faces. Most images vary in size so the standard crop does not work buy using guides and hard coded coordinates for the bounding box.
What I would like to do is.....
1: Open a series of pictures through Bridge, (for loop structure) I ve found some stuff to get that going.
2: On each one opened have the user select a point (typicall the nose since its the center of the face)
3:Adjust a bounding box based on center point to cover the whole face and some surrounding context via a graphical slider.
4: click Ok to Crop the image.
5: Prompting "OK" would then resize the image to 95 x 95 pixels and save a thumbnail verison of the jpeg leaving the original intact.
My biggest problem is getting to read the mouse click that defines the center point in photoshop. I can see in the info box that it is tracking my mouse through the bounding of the picture, however have not found a way through the listener to gain access to these values via javascript
Any help is greatly appreciated. I'm stumped.

Mr. Riggot? Forgive me but i'm incredibly new to all this so i might be broaching a point of etiquette (i fear so but couldn't figure out a way to message you) in attempting to aks a question on another matter in this thread, but some forum research has led me to believe you may be just the person to ask a question i've posted as general Bridge discussion concerning how to override automatic overwriting of a previously established manual sort ordering. i'll just post the link to it as i already fear i might be bothering y'all:
http://forums.adobe.com/message/4748987#4748987
again so sorry to tug on your shirtsleeve in this way, and thank you in advance for your forebearance....

Similar Messages

TS1702 Can anyone explain to me if iPhoto for iPod/iPad is suppose to have facial recognition. I downloaded it for that purpose but cant get it to work. I was about to buy an iPad but without the Facial Recognition I won't bother.

I need to have a Facial Recognition program for the iPad. I use iPhoto on the Mac and need to be able to use the Facial Recognition on the iPad.

I'm not sure where did you get that?
iPhoto for OS X does have facial recognition. The iPad version doesn't.
newer iPhone and iPad do have facial recognition in their camera applications (for auto-focus).

Facial recognition for a new app

I am working on an idea for a new app for the iPhone. I was wondering if Apple or anyone else has used a type of facial recognition within their app. I have this idea about taking a photo of something and having the image try to match a database of other images.

Reditions cannot be implemented on DPS Single Edition Apps. For information on how to design for Single Edition Apps, refer to this earlier forum post which has alot of inputs on how to go ahead and desgin for both Retina and non retina display : http://forums.adobe.com/thread/985690?start=0&tstart=0

Does Kinect for Windows V2 provide facial recognition API? Thanks

Does Kinect for Windows V2 provide facial recognition API? Thanks

For facial recognition with the Kinect, you can use the Developer Toolkit (v1.5.1). The API for the FaceTracking tools can be found
here: http://msdn.microsoft.com/en-us/library/jj130970.aspx.
You can also refer: How
To: Kinect for Windows SDK Face Recognition Series
Facial Recognition with Kinect
Kinect
for Windows: SDK and Runtime version 1.5 Released
As mentioned in the article: Kinect for Windows:
Frequently asked questions
Does Kinect for Windows SDK offer facial recognition capabilities?
Since version 1.5, the Kinect for Windows SDK and toolkit have supported real-time face tracking. Face tracking is not intended for facial recognition or identification. Face tracking detects and tracks the positions and orientations of faces in real time and
provides animated three-dimensional (3D) meshes that are positioned in 3D over the Kinect depth sensor data. Face tracking can animate, in real time, eyebrow positions and mouth shape, as well as provide a high-resolution 3D mesh of the face than can be animated.
With the SDK 2.0, Kinect can also track whether eyes are open or closed, the position of the nose, facial expressions, and the direction the face is pointing. The resolution of the tracked face has been increased by 20 times with a 1,360-point mesh, so that
faces look more realistic. Conventional face-recognition algorithms can be used with the Kinect for Windows sensor’s RGB stream; we continue to investigate how the Kinect for Windows sensor's extra capabilities can be used.
For more details you can Ask a Question @ Kinect
for Windows v2 SDK
Rachit
Please mark as answer or vote as helpful if my reply does

Lightroom 6 / CC2015 - Facial Recognition Terribly Slow, not using all of CPU or GPU, still keeps going when paused.

This is actually a couple of issue but wondering if others are experiencing it and worked through it.
I am using a Dual Xeon CPU 3.2 ghz Mac Pro, Catalog on SSD, Images files on Mirrored Pair, Dedicated GPU (max I can install in my version of Mac Pro) and hardware acceleration enabled in Lightroom.
I watched the Lightroom 6 Facial Recognition tutorial which leaves out a lot of the bulk editing and says basically let it loose on your whole catalog.. NOT recommended.
I started out with a couple small portrait galleries that identified a couple hundred total people to seed facial recognition so it didn't suggest everyone is the first person I confirmed (which it will do otherwise). I have also optimized my catalog multiple times.
I have encountered the following serious performance issues and bugs with Facial Recognition.:
Lightroom Facial Recognition goes to a ridiculous crawl after about 2000 images to be confirmed. (i.e. 2000-2300 in a couple hours, 800-1200 in the next 12 hours)
Lightroom becomes largely unresponsive after having a fair number of images to be confirmed, even after pausing Address and Facial Recognition. So even selecting 4 rows of images can take 5 minutes with several long pauses.
Once I select and click confirm it takes up to 2 minutes to update the "to be confirmed" list again.
When I click on an individual at the top of the page, pause facial recognition and address lookup it still continues to "Look for similar faces" [BUG!!!!!!!!] even though all I want to do is just confirm some individuals more quickly in bulk with the images already identified.. not continue to look for more as a work around for the painfully slow responsiveness of the module.
The odd part is that with all of the performance issues Lightroom will not use more than 20-30% of my two Xeon CPUs, barely touches my GPU (<10% CPU, 30% memory), my and no more than 35% of my memory. Computer Temps are also barely above startup temperatures and 15-25 degrees cooler than when I run other applications which will consume my entire CPU and memory if I let it. I have explored Lightroom's settings but seen nothing further I can configure to speed it all up. I have also attempted the operation on images on the SSD, my drobo (known to be slow), an independent fast disk I have, and a pair of raided disks and have the same issues.
I will also note that all of my other applications seem to continue to operate just fine.. the slowness seems to be contained to the Lightroom application itself.
Lightroom version: 6.0 [1014445]
Operating system: Mac OS 10 Version: 10.10 [3]
Application architecture: x64
Logical processor count: 8
Processor speed: 3.2 GHz
Built-in memory: 18,432.0 MB
Real memory available to Lightroom: 18,432.0 MB
Real memory used by Lightroom: 5,537.5 MB (30.0%)
Virtual memory used by Lightroom: 32,240.6 MB
Memory cache size: 4,342.0 MB
Maximum thread count used by Camera Raw: 8
Camera Raw SIMD optimization: SSE2
Displays: 1) 2048x1152
Graphics Processor Info:
NVIDIA GeForce GTX 285 OpenGL Engine
Check OpenGL support: Passed
Vendor: NVIDIA Corporation
Version: 3.3 NVIDIA-10.0.31 310.90.10.05b12
Renderer: NVIDIA GeForce GTX 285 OpenGL Engine
LanguageVersion: 3.30
Application folder: /Applications/Adobe Lightroom
Library Path: /Users/DryClean/Documents/Lightroom_Catalog/MyCat_LR6.lrcat
Settings Folder: /Users/DryClean/Library/Application Support/Adobe/Lightroom
Anyone have any suggestions?

A big problem continues to be that once you wait for it to index all your faces you find it missed over half of them. There are many cases where it missed the subject of the photo but managed to find a tiny waiter off in the shadows. I don't know how this will ever get fixed; it seems it'll require an update that lets you rerun the indexing a few times, maybe with different levels of granularity. I doubt that's coming.
It stands to reason that a system that hands you thousands of false positives for every face can't recognize if something is or isn't a face in over half the cases. Faces in profile or tilted down, especially with the eyes looking down, are bypassed completely. I have directories with a thousand people shots in them, many with multiple people, and instead of LR6 returning an index of 1.5k or so, it gives me 385. I'm not sure how valuable the search advantages will be in this case; I can see it not returning some favorite shots of people.
Anyway, for anyone looking to get past the spinning wheels, work on one directory at a time. Then once a directory is done, keep it selected so you have the same thumbnails of identified faces in the confirmed area, and control-select the next directory. You won't have to reseed the confirmed faces area this way and things move much faster when you're not working with the entire library. It also helps to click each person in the confirmed faces and work in that view sometimes. It'll return faces of family members of that person and you can rename those. You can watch it focus its top results as you confirm but, annoyingly, it doesn't narrow the total suggestions but actually expands them the more faces you confirm and the fewer correct positives remain. (This seems opposite to how it should work. It should give you fewer faces the more you confirm as it gets a better idea what the person looks like and has fewer shots left unconfirmed of that person.) Yet, even with the expanded results, faces will still escape it and pop up in other people's results as false positives.
Bottom line: It's only a little better than manual tagging, and not as thorough because of the poor hit rate of the initial indexing. But it works better if you stick to isolated directories and occasionally individual people. At least that way you don't have to wait for it to re-sort tens of thousands of results with every click.

Multiple iPhoto libraries facial recognition

I have decided to use multiple iPhoto libraries. In one library I have used facial recognition for all of my photos. Q: When I move to the next library will iPhoto recognize those faces?

No
One of the many reasons that multiple libraries are not recommended - iPhoto is a SQLite database and it is most powerful when you have one database - there is no connection of any sort between different libraries
LN

FAST ACCESS FACIAL RECOGNITION WON'T WORK ON DELL STUDIO 1555 SINCE MOZILLA UPDATE

When Firefox updated my Facial Recognition Fast Access on Dell Studio 1555 no longer works. The box shows up but not green line around it

Some Firefox add-ons have a hard limit on compatible versions and may stop working after a Firefox update. To check for a newer version from Dell, see this article:
http://www.sensiblevision.com/en-us/support/dellsupport.aspx
Can you find a newer/updated version that might work with Firefox 19?

Facial Recognition-- Best Practice

Question about facial recognition for tagging, Lets say you have a person who has baby pictures, child pictures, teenager, and adult pictures.
should you tell PE that these are different people (john infant, john child, john teenager, john adult) to make the searching more accurate. (then you can combine them manually)
Or, should you tell PE that these are the same people John, and it can figure out the changes without any confusion.

Good questions. Annecdotally, PSE automatically recognized a photo of me when I was 1, after I tagged a number of photos of me as an adult. Don't know how representative that is, but I would bet that it's not going to recognize me as a teenager!
As for technical references, I'm not aware of any that Adobe has published. It appears that Adobe has licensed the technology from Cognitec:
http://www.cognitec-systems.de/News-Details.61+M58e94ecfeec.0.html
If you're a programmer, you can read the Cognitec SDK manual:
http://www.cognitec-systems.de/fileadmin/cognitec/media/products/FaceVACS-SDK/FaceVACS-SDK _Manual.pdf
An interesting nugget:
Facial pose requirements
While a frontal view of the upright face is recommended, some deviations are admissible. A horizontal (yaw) or nose up/down (pitch) rotation of the head of up to 15 degrees is admissible. Also, the face is admitted to deviate from upright view (roll) up to 15 degrees.

Photoshop Elements Organizer 11: Facial Recognition not working.

When I click on either 1 photo or 10 photos to add a name to the faces it says "no new people found in your selection". I have tried to only click on 1 photo, then click on mark face and it will say that this photo has not been analyzed yet, even though it has, and after analyzing it will say the same thing. Please help! I have over 20,000 photos to put names to the faces.
Thanks!!!!

four.roos wrote:
I have also tried to repair my catalog and optimize it and neither has fixed my problem. The only thing I think thats left is uninstalling and reinstalling but will my pictures and the faces I have applied so far still be the way the are now?
I don't use facial recognition and can't help you on that matter. Repairing and optimizing can do no harm but won't help either. Don't reinstall, that won't help you even if your catalogs will be preserved. I'd wait for other answers from people acquainted with the facial recognition feature.

IPhoto 8.1.1 Fixes Facial Recognition Problems

That's what I have observed from my testing on a library of over 15,000 pictures.
It is important to "Detect Missing Faces" as explained in the appended support article:
http://support.apple.com/kb/HT3941
Your computer will work long and hard at this task ... best to leave it alone while you are having Thanksgiving dinner! When done, quit iPhoto and expect it to save a very large file describing all the faces it recognized. In particular, the 'faces' files in the library will be much larger, presumably because they now contain much more information.
The recommended procedure to identify a few faces manually and then let iPhoto find the rest automatically is unchanged, but what a difference in performance! Expect iPhoto to immediately select many pictures that "look like" the faces you found manually. Also, expect to have to confirm or reject many of the selections ... it seems that iPhoto thinks "everyone looks like everyone else" at first, but it gets better as you improve its training. Also, expect the facial recognition process to occur while you are training by accepting or rejecting selections ... don't be surprised if certain selections are suddenly 'withdrawn' from consideration as you accept or reject others.
You should also expect to see the "Is This ...?" pop-up much more frequently. I observed that as soon as I named one picture of a person in multiple photographs they were immediately identified in successive photographs, especially if the photographs were taken at the same event. Of course, the real test will be if iPhoto's facial recognition can recognize a person as they change over time, especially when they are children.
There are still a few problems. If you have a large number of photographs of the same person, iPhoto will select them all ... and more. There needs to be an easier way to confirm or reject the selections rather than laboriously clicking on each. Expect family members to be erroneously suggested as matches, especially children with their parents and grandparents ... what else would you expect? Glasses are still a problem, especially sun glasses, but it is surprising how well iPhoto can "see through" such an obvious problem. Finally, a full face, even in profile is necessary for reliable identification ... putting a hand over the mouth or wearing a hat over the eyes defeats the identification process.
iPhoton

Thank you, Henk ... that's also how it works for me. It seems that the 8.1.1 update shifted more of the work load to the initial search for faces, i.e., "Detect Missing Faces". However, it still takes a little time to match each face, particularly if there are many faces. The big difference is that a little time is a lot better than an seemingly-infinite amount of time, which was how it used to work ... at least it seemed that way.
The library on which I have done most of my testing is mostly "people pictures" ... school classes, family gatherings, birthday parties and sporting events. One of the sporting events is a professional baseball game photographed from behind the first base dugout at the level of the playing field. Pictures of the batters at home plate show hundreds of eager fans behind the third base dugout intently watching from the other side of the field. As the pictures were taken with a telephoto lens, all those faces are not only in the field of view, but also clearly in focus ... iPhoto finds them all! Not that I know them, much less are interested in naming them, but those hundreds of faces take time to be found and there are many pictures like that.
Thanks also for the tip to use the Alt/Option key. I can use that for exactly this situation ... ignoring the faces of people I am not interested in recognizing, much less naming.
iPhoton

Can I merge duplicate tags from facial recognition in Elements 11?

How can I merge duplicate tags from facial recognition in Photoshop Elements 11? For example, if I mistakenly created two tags, both called Bill, how can I put all Bill's pictures in one file? I found an answer for previous editions of Photoshop Elements, but Photoshop Elements 11 has changed the organizer so I can't figure out how to do it. Also, it doesn't seem possible to see two sets of tags at the same time - is this a glitch?

OK - I figured it out.
1. Go to Media in the Organizer.
2. Click on View at the top, and click on "Show People in Tag Panel."
3. Click on the name you want to merge - the file name you want to get rid of.
4. Edit > Select All
5. Drag the tag you want to use to the selected photos, so that they have both the old and new tags.
6. In the Keyword Tags pane, click on the old tag, go up to where it says "People Tags." There is a plus and minus sign next to this. Click on the minus sign and click on Delete. The tag you highlighted will be deleted.

OK, PE has Facial Recognition, it works very well. I try to use LR 4 or 5 to pullin the PE catalog

I spent days in Photoshop Elements Organizer "adding" people. I got over 24K images tagged wtih people.
I then brought up LR (tried with both 4 and 5) and "converted existing PE catalog. unfortunatly, NONE of the people data came accross into LR.
So, I wasted days of work.
How am I supposed to pull in that date from PE Organizer into LR? Its why I used PE to do facial recognition, and wanted LR for work flow, but wanted quick smart sets based on faces in the pictures.
looks beautiful in PE Organizer, looks normal in LR. Any help is appreciated.

I thought about the converting the "People" info in PSE Organizer to a "Tag" to be imported inot LR when you convered the PSE Organizer catalog.
First, I thought People was a tag, and should have automatically picked up and tied to the photo within LR. (obviously not the case) and second of all, i really have no idea how to do this.
I really don't have to have to tag 24K photo's with the names of people again in LR since I spent weeks in PSE. Especially since there isn't a facial recognition option in LR like PSE.
Still looking. BTW, the excecise of using Facial Recognition on PSE helped me eleminate over 5200 duplicate photos. So, it wasn't all wasted.
Thansk ssprengel for responding. Hopefull someone there will no how to exececute on your idea.
G

Facial Recognition with scanned photos - Elements Organizer 11

My facial recognition works fine with my digital photos but not my scanned photos. It used to work a couple of weeks ago but the power was turned off and my computer was turned on at the time. Im not sure if that has anything to do with it but thought Id throw it out there. I am running the program on my mac.
Thanks for any help you can give me!

Please try renaming last files mentioned in hierarcy:
C:\Users\suresing.ADOBENET\AppData\Roaming\Adobe\Elements Organizer\11.0\Organizer\psa.prf
peoplestatus.dat file present in your catalog folder (location can be found from Help->System Info)
and click on 'add people' button.
~Andromeda

Lightroom 5 is out.... IS THERE FACIAL RECOGNITION?

So it seems lighroom 5 is leased.
http://www.adobe.com/products/photoshop-lightroom.edu.html
Now to the question.. IS FACIAL RECOGNITION FINALLY IN LIGHTROOM?

Keith_Reeder wrote:
massive price difference between Lr and Cap One Pro
C1+MP is way more expensive than Lr, but Lr+Ps is way more expensive than C1...
But we're only talking about a few hundred dollars here, and for people paying thousands for bodies and lenses, a few hundred dollars difference in software shouldn't be a deal maker/breaker.
So it really boils down to which is best, in my opinion.
For me, I will be having Ps as part of CC, and I'm inextricably tied to Lr plugins, so wild horses couldn't drag me over to the C1 camp. However, if I didn't have such pre-disposing factors, I'd seriously consider C1+MP over Lr+Ps. On the other hand, if the choice is Lr+Ps vs. C1+MP+Ps then the balance tips again... - glad I don't have to make such decision.
Don't get me wrong, all things considered, I'd still choose Lr/Acr over C1-based raw processing, since its the best (imo), and it runs well for me, but if I couldn't get it to run well, I'd jump ship in a heart-beat. And, it does seem like PhaseOne is investing heavily in software improvements - more so than Adobe (w.r.t. Lightroom) - if this keeps up, then it's only a matter of time before C1 surpasses Lr.
Cheers,
Rob

Facial Recognition error

I wrote some facial recognition software and posted the code below. It does compile fine but for some reason gives me an error when I run it. There always seems to be an exception thrown while it is analyzing the eyes of a new face. My coding standards may be a little different than what you are used to.
------ file FaceRecognizer.java ------
public class FaceRecognizer {
   public static void main(String args[]) {
     Face f = new Face();
     Face f2 = f;
     if (f.equals(f2)) {
         System.out.println("Faces are the same person!");
        class   Face
        {Face(){ int
        _=1,__=1;int
        X______ = 1,
    ________ =1, _____=1
   ;; _-=_   ; _=-_ ;;
   ;;;   __=     __    ;_
    =   (0 )   /(0 )   ;_
    =        1|        1
    |        1|        1
    |       (__)       |
    1*    ________     ;
    _=    X______/     1
     -_               /7
       -_           /7
         -________/7;
---- end of file ----

I don't know if you were looking for an actual answer, but this compiles AND runs:
------ file FaceRecognizer.java ------public class FaceRecognizer {
   public static void main(String args[]) {
     Face f = new Face();
     Face f2 = f;
     if (f.equals(f2)) {
System.out.println("Faces are the same person!");
        class   Face
        {Face(){ int
       _=1,__=1;int O=
       1 ,X______ = 1,
    ________ =1, _____=1
   ;; _-=_   ; _=-_ ;;
   ;;;   __=     __    ;_
    =   (O )   /(O )   ;_
    =        1|        1
    |        1|        1
    |       (__)       |
    1*    ________     ;
    _=    X______/     1
     -_               /7
       -_           /7
         -________/7;
///////////////////////////---- end of file ----
I just changed the eyes to an O instead of 0, and added an int O on the hat.
Very cool, by the way...

Facial Recognition per se for Thumbnails

Similar Messages

Maybe you are looking for