Ask Your Question

SJ's profile - activity

2014-06-13 03:44:02 -0500 received badge  Supporter (source)
2014-06-13 03:43:55 -0500 received badge  Critic (source)
2014-06-12 00:23:06 -0500 asked a question openCV project working with 3 webcams to capture simultaneously

Hi all, I am trying to do a program to be able to use 3 webcams and capture at the same time. Two side cameras will be tilted to 30 degrees and the center one is 90 degrees (straight).

I would need the photos to be taken at the same time and stored in a specified folder before the photos are going to go through illumination normalization. I also need to eventually make this process all automated... :/

Has anyone done a similar project before? If yes, please give me some advice for me to know how to go about doing this program.

Thank you all

SJ

2014-06-04 19:56:18 -0500 commented question how to increase the number of each detection can detect?

hi sorry about that... basically we are doing a opencv face recognition to monitor viewers mood when watching tv programs.. i am continuing the project so I have quite a number of questions.. the project is working normally now but we have to improve on the total number of people it can detect once the application runs. It can also only detect from the furthest distance of 1.5m. Even within this range the age, mood and gender is not 100% accurate. We are using fisherfaces. I have no idea how to improve on them...?

2014-06-04 09:29:18 -0500 asked a question how to increase the number of each detection can detect?

Currently my project can detect a maximum of 8 people. I would like to increase this number:) May I know what changes do I have to make?

2014-06-04 04:36:05 -0500 asked a question how to improve distance of monitoring face and allow application to open faster?

Currently my program works best for any distance within 1.5m and takes quite long to run the application. It is also quite laggy when running on laptop. Is it a laptop problem or the codes can be altered to improve this issue?

2014-06-04 03:27:08 -0500 commented question how to improve the accuracy when detecting mood and age?

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!

2014-06-04 03:15:26 -0500 commented question how to improve the accuracy when detecting mood and age?

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? :)

2014-06-04 00:47:47 -0500 asked a question how to improve the accuracy when detecting mood and age?

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?