Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

To resolve issues starting MATLAB on Mac OS X 10.10 (Yosemite) visit: http://www.mathworks.com/matlabcentral/answers/159016

I want to find the difference between all the features to get a difference vector for any two face of image.

Asked by nik on 4 Dec 2012

I am doing face recognition using matlab software. I already managed to get the interested features (L_eye, R_eye, nose, mouth, center_eye). From here i have calculated the distance and ratios.

from the calculated ratios, i want to , for any two pair of faces, find the difference between all the features to get a difference vector.

Can anyone guide me how to calculate it?

0 Comments

nik

Products

1 Answer

Answer by Image Analyst on 4 Dec 2012
Accepted answer
differenceVector = face1Vector - face2Vector;

8 Comments

Image Analyst on 6 Dec 2012

I don't know what those first two paragraphs are doing, but it does not look like proper MATLAB syntax. I have no idea what any of those numbers or variables mean.

As far as the vectors in the third paragraph go, yes you are creating vectors and yes, you are subtracting them but that's about all I can say. They seem to be created with just some arbitrary numbers, and you don't do anything after that with them other than subtracting them. What did you expect to happen?

nik on 7 Dec 2012

thank you for your reply.

firstly i am sorry, its looks like those first two paragraph does not appear like list item like i want it to be.

Yes, it is not a matlab syntax, it were just the value that i want to use in my vector.

actually i want to find the difference between face images in order to find the right image (face recognition). since i already got the coordinates for the interest area that i want. from there i calculate the distances, ratios, and standard deviation. then i compare it with another face image. the minimum differences should be the same face image.

i try to find other better way for the recognition step.. like formula or something.. in order to come out with a better recognition rate.

Image Analyst

Contact us