Ask Your Question

how to improve the accuracy when detecting mood and age?

asked 2014-06-04 00:47:47 -0500

SJ gravatar image

I am trying to do a project to analyze user's expression (i.e. Happy, sad, frustrated, etc. ) Currently only the detection of gender is accurate. For the mood and age it is not very accurate yet. Does anyone have any idea how to improve accuracy?

edit retag flag offensive close merge delete


what are you using ? fisherfaces ? how large is your trainset ?

berak gravatar imageberak ( 2014-06-04 02:28:45 -0500 )edit

yea i am using fisherface. currently 20 for trained set... gender is working well, but for the detection of age and mood is really quite inaccurate! Any advice how to increase accuracy? :)

SJ gravatar imageSJ ( 2014-06-04 03:15:26 -0500 )edit

more train images then. say, 100 for each label.

gender is the most easy one here, just 2 labels.

berak gravatar imageberak ( 2014-06-04 03:23:03 -0500 )edit

so you mean i have to have bigger trained sets to improve accuracy for age and mood? so it means for happy/sad/angry etc. I have to ensure I have larger number of such images to improve accuracy? sorry i am new to this project and do not have much background information. Thanks for the help!

SJ gravatar imageSJ ( 2014-06-04 03:27:08 -0500 )edit

yes, exactly.

berak gravatar imageberak ( 2014-06-04 03:32:30 -0500 )edit

@SJ: Which kind of database is used for gender detection? Currently, I used AT database, but it is very bad result. Hence, I changed to other database.

john_1282 gravatar imagejohn_1282 ( 2015-03-24 03:56:06 -0500 )edit

AT is too small. try adience or faces94

berak gravatar imageberak ( 2015-03-24 04:13:22 -0500 )edit

Hi @berak , I tried adience but the X, Y, DX, DY is not working for me. Were you able to crop the faces using the data provided? Could you give me any help? Thank you.

brjapa1 gravatar imagebrjapa1 ( 2015-06-07 19:26:03 -0500 )edit

@berak , here some samples I'm reading from the file 3 samples

brjapa1 gravatar imagebrjapa1 ( 2015-06-07 19:33:02 -0500 )edit

hmm, it seems, the face detection already failed on those images

berak gravatar imageberak ( 2015-06-07 23:25:34 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2015-06-08 10:03:30 -0500

brjapa1 gravatar image

Hi, thank you for your reply. Actually it failed in several images. I'm going to try the faces94 instead. Looks like more robust. If you get any update about it please could you tell me? Thank you

edit flag offensive delete link more
Login/Signup to Answer

Question Tools

1 follower


Asked: 2014-06-04 00:47:47 -0500

Seen: 233 times

Last updated: Jun 08 '15