Facial Morphing Software/Techniques? 31
scraps asks: " I am assisting an evolutionary psychologist who is researching how symmetry and size of facial features affects how others perceive a person's personality. I am looking for is a way to increase and decrease the symmetry of faces (digital images, not the living flesh), as well as increase and decrease the size of facial features while maintaining a "normal-looking" face. In the days of yore, Gryphon's Morph software seemed to be the weapon of choice, but they seem to have slipped into obscurity. I am using Mac OS X 10.2, and have Photoshop 7.0. Any ideas would be most welcome."
An alternative method. (Score:3, Informative)
An alternative method (not sure how viable or expensive for you on a Mac) might be to take the image in a 3d animation package (like 3dsmax, XSI) and then create a 3D model based on the displacement. There are tutorials and even more specialized tools that show you how to do this. dvgarage.com has some info about them.
This 3D model should then be much more flexible to model your new face than an image.
The drawbacks of this method is that your model will need to be tweaked to be a more accurate model of a face. After that, it shall have to be textured and shaded. Depending on your skill and tools, it might not be photo-realistic enough for your subjects or whomever shall be seeing these new faces.
where are you working? (Score:1, Interesting)
Black Belt Systems (Score:2, Insightful)
Yes, I know this is a windows program, so get Virtual PC to run it. There's a sale on WinImages, it's now $50. This is one of the best morphing programs, it's scriptable, and does a hundred other effects besides morphing. And since this is slashdot, I'll need to mention that their credits page includes X-Men
Why try something new? (Score:5, Interesting)
I believe there may have been a 2.0 version of Morph at some point, but I never got a copy.
Re:Why try something new? (Score:1)
MorphX (Score:2)
Re:MorphX (Score:1)
That is from the first line of the Usage section on Morph X webpage.
Again, if I understand the submission correctly, this is not what is wanted.
The submitter does not want to morph between two images (of faces or anything else)
Rather, what the submitter wants is a software capable of taking the picture of a face, recognising it as a face, then being able to manipulate facial structure and expressions to create new faces. Morph X is just an image-morphing program where you need the source and result.
What I proposed in my post above is to convert the image to a 3D model which can then be manipulated at will.
Eyetronics (Score:2)
One of the things they are doing is just that. It has some nice demos [eyetronics.com].
btw, they did also some work for "Die another Day" and "xXx",
Thoughts on morphing algorithms... (Score:5, Informative)
Without any additional control points, this was nothing more than a crossfade between the two sources. Individual control points had a correlation on both the first and last image, so you could map important things like the point of a nose, corners of a smile, etc. With control points in place, the pixels generated for the interim states would be calculated both by what frame in the sequece they were for, and where the pixel was, radially, from the nearest control point. Obviously, the more control points, the better looking the morph.
The next thing it added was the ability to draw vectors between pairs of control points for added smoothing. Draw all around the outline of a face, the eyes, mouth etc, and you'd not only have radial calculations from the control points, but points a distance off the line as well. Not sure exactly how they did that... maybe just right angle to the vector and adjusting influence proportional to proximity.
All that said, it seems the toughest thing would be the input method for defining control points. The calculations based off RGB of individual pixels could probably be done with ImageMagick or any other comprable graphics library...
Not that I have the chops to build an application with GUI, and I'm sure the technique I just described is probably patented by someone, but it doesn't seem like the type of app that should have dropped off the face of the earth...
What about Photoshop's Liquify? (Score:1)
Morpheus (Score:1)
Its not for Mac, but its only 19.95
Arguably the best facial morphing technique (Score:3, Informative)
EA Sports NHL '97 (Score:1)
PCA analysis (Score:4, Informative)
http://www.stir.ac.uk/Departments/HumanSciences/P
FaceGen (Score:4, Informative)
http://www.facegen.com/modeller.htm
Real time 3D tweaking of every possible facial parameter.
I'm the author of Gryphon Morph (Score:1)
Re:I'm the author of Gryphon Morph (Score:2)
Whoa. I was looking for you some time ago when I was attempting to morph retinal images for a presentation I made. I finally managed to locate an old boxed copy of Morph for Classic MacOS and accomplished the task that way. Perhaps someone like Ambrosia software [ambrosiasw.com] would be interested in distributing it for you? How can I get in contact with you as I would love to talk to you further about this?
Re:I'm the author of Gryphon Morph (Score:1)
Truespace 6 and facial animator (Score:2)
Truespace 6 has a facial animator tool. With it you can map your own face onto a model, then there are preset controls to set the expressions. Compared to other 3d packages TS6 is pretty cheap.
More info at
http://www.caligari.com
Program your own! (Score:2, Interesting)
Maybe you could implement the algorithm, and then run it on the original picture, plus a reduced size image of the subject with all the lines in the second picture proportionately smaller. Your in between morphs should have the look you desire (unless i'm reading your request wrong). Implementation of anti-aliasing using supersampling with a gaussian convolve before cross-dissolving does help!
Something not mentioned (yet)... (Score:1)
The methods of morphing already discussed are mainly simply distorting the image, and that's easy enough.
If you are running with high-resolution pictures, and using computer monitors as your setup then the effect will have to be very natural looking. I'm running 1280x1024 on an 18inch/457mm (viewable) NEC and I can easily pick out single pixel details. But then it's a friggin bright CRT and I do have my eyes about 18inches from the glass.
I suspect that beyond a certain point people will see where the skin [i.e. image] is distorted, by the sharpness of details, clarity, shadows, wrinkles etc. For more natural looking images with higher distortion I would suggest you find a way for the program to either clone sections of skin to cover wider ares, or cull certain areas to reduce size, without the actual scale of the image being to badly affected. Things like hairs, blemishes, skin tone and shadows might be a problem, but shouldnt be impossible to sort out.
Witha bit of luck and smart coding, that should help features look smaller rather than shrunk, and bigger rather than stretched.
Ali