Re: ragarding simon development

*Hi all,*
*
*
*I am motivated to implement face Detection and Recognition for simon.*
*For face Detection purpose proposed algorithm is classic haar
classifier.Which is based on haar wavelet concept of describing objects
which is inbuilt in opencv.*
*
*
*secondly for face recognition I prefer to use opentld(track learn detect)
algorithm,which was basically implemented for realtime object tracking.Its
pretty amazing*
*and accurate because of following reasons:*
*Input to this is single template from first frame *
*It is robust to intensity(invariance to illuminations) variations and
rotation and size*
*Feature is combination of haar wavelets and local binary patterns.*
*Feasibility in terms of number of features*
*It provides proper parameters to estimate accuracy in recognition*
*these are some of the filtered advantages*

*generally many questions arises for those who read just abstraction of
paper presented by *Zdenek Kalal,like how can single frame can be used to
train and
model for object detection and tracking.
*Adaptive nature of algorithm is fantastic since it differs from classical
neural network concepts and evolve with memory. *

*Since future ideas of simon like acoustic modelling(which i liked the
most) are based on depth recognition,the above algorithm needs less or no
modification in *
*providing necessary feature for modelling.*
*
*
* *

_______________________________________________
kde-accessibility mailing list
[email protected]
https://mail.kde.org/mailman/listinfo/kde-accessibility