You are not logged in.
Hi model;
and total probability is
2/5+ 4/5 + 5 /5 = 2.2Let me help you out here. A probability can never be greater than 1. So what are we computing here?
ohh yes . the same question i have .
I do't know but i read out the formula of combination for finding probability from book.
if yes then I have another formula for Binomial probability
Pr(X= r) = nCr(p^r)q^(n-r) where n and p are binomial parameters and q = i-p .
What is the purpose of this ?
What is the actual meaning of that ?
Is combination not just enough for finding probability ?
Hi;
to chose 2 times out of 3.
nCr(2,3) = 3! /2! (3-2)!Hold it for a second. Not nitpicking here but we have to speak the same language if we are going to communicate.
Ncr(3,2) means 3 choose 2. From 3 objects choose 2 of them. Ncr(2,3) means 2 choose 3 which can not be done and equals 0.
ohh sorry i wrote is wrong.
but anyways , logically the probability from combination and the way that i did for histogram of some pixels .
Logically both have same meaning . Right ?
thanks for the link .
ohh cool Thanks Bob from me too .
hmm yes ..
Example of binomial random variable :
How many ways are there to chose 2 times out of 3.
nCr(2,3) = 3! /2! (3-2)!
The above way is called combination .
Now suppose we have some values or pixels values like
pixels frequency accumulative frequency
1 1 is repeated 2 times 2
1 2 is repeated 2 times 4
2 3 is repeated 1 time 5
3
2
and total probability is
2/5+ 4/5 + 5 /5 = 2.2
Hy one second,
I read out binomial random variables can be solved from combination nC(r) for finding the probability and i successfully represented probabilities in form of histogram .
On the other hand, I maked histogram of some pixels using this way .
Data : i have pixel values ./
frequency : the repetition of pixel values
Accumulative frequency : add current and previous frequency .
probability : divide each accumulative frequency by total number of data or class interval width .
Now My question is combination and the other way that i explained . both are same logically .
Right ?
Hy ,
17078 is my question thread . and where is diagram as you said in your posted reply ?
Are probability density function and accumulative frequency same thing ?
Hy guys ,
I did not understand the basic meaning and purpose of Bayes' Theorem . Could any one please elaborate a bit .
Thanks
hy Bob,
but i did the same .
I have current and previous position with x and y .
so just calculated deltaX = x2 - x1 and deltay = y2 - y1
double angle = arctanDegree( deltaY ,deltaX );
and i have converted it in degree, too .
Is that not same as you said ,
hy All,
I calculated angle . but when i move to up side . My angle inverted and show direction to down side .
and when i move to down side . my angle direction showed to upside . So angle is inverted .
Does any one have idea how to solve this angle inversion problem .
Thanks
Hy All,
I am trying to detect fast , slow and running objects in the video .
I have calculated distance between current and previous position.
so based on distance i detected slow . and fast and running object s /like in my work show that
if dis < 10 and dis > 0 --> crawling
else if dis > 10 and dis < 70 --> fast
else --> object is running .
and when i calculated speed which is tooo small either object is in slow speed or fast speed . Its near to 0.0454523 or 1.02424
or 2.54545 but if object run then speed showed by my program is near to 11 ..
Its too small either object run , slow or fast .
So Please tell me what is the purpose of calculating the speed which is = distance / time .
after calculating the speed i realize that its useless .
Please guide me Thanks
ah you meant do calculation in double but show your ans in int form by casting double to int .
I see.. ok Thanks Bob .
Hy Bob ,
if floating point i meant double is best to use then how to get rid from very large and very small numbers ???
since i am using double for speed and distance . and this output
Distance : 1.1219e+006
speed :47.1996
is terrible or not understandable specially for me .
so i want the output that user should easy to understand . and also should work for my project requirement .
yes .. I want output in more readable or understandable form for user .
I am using c++
yes so i think i should try to handle very large and very small numbers . but any idea how ?
Hy all ,
Since i am trying to detect slow and fast motion of my moving object . ,Conceptually , When i move slow then my current and previous motion almost about near ,., not much difference ... so probably less difference and speed would be low . .
but if i move fast then more distance will cover at the same time . so speed will be more .
But some time i get distance some thing like
get this value
Distance : 1.1219e+006
speed :47.1996
Distance : 1.1219e+006
speed :47.1996
Distance : 1.1219e+006
speed :47.1996
Distance : 1.1219e+006
speed :47.1996
Distance : 1.1219e+006
speed :47.1996
i do't understand this reason .
any one could guide me please thanks
What does mean by compactness ?
There is image : http://imageshack.us/photo/my-images/190/42484776.png/
In the image , 1st figure shows the compactness whose value is less may be 1 or 0.754 some thing .
Note : according to the 1st figure as circle presented in the image .
that shows more thickness and compact and while in the 2nd figure , it shows less compact and more thicknesss
What does that mean actually . Compactness is based on what thing ? ?
Please clear this concept thanks
Hi Bob , I like that . i meant your message .
Bob, I am reading book and have seminar so present this all.
Well , now my seminar is going to start so let see what happen . and my ans to the above question is ellipse . because eccentricity of circle is 0 . so we can't approximate boundary of complex numbers as a circle .
well, we can represent the boundary of complex plane as a circle ?
no ?? if yes then why in the above statement he said ellipse /
what does mean by normalization .
like ( sum of all values )/total number of points .
That mean normalization . what does that mean ?
can some one tell me via vitalization about normalization refer to what thing ?
Well i came to know that
My 1st question' ans :
1D Function : weighted sum of many different complex exponents
So rotated image is may be difficult to recognize . while in 1D since Fourier descriptor as 1D ( i-e weighted sum of different complex exponent and DC == average sum of points ) that mean rotated or scaling will not effect in recognizing the image. so problem solved from 2D to 1D as a function .
So smaller the fourier co-efficient : lose of details and global shape of boundary of an object .
higher the Fourier co-efficient : more details and high frequency components .
So less Fourier descriptor , loss of details but since " The boundary in the complex plane is approximated by an ellipse with minimum Fourier descriptor 2 . Although resultant shape will be lose of details but approximated to original shape .
As a result , Fourier descriptors are invariant to scaling and rotation.
yes , last figure shown in the linked image ,retain the original shape
because boundary in complex numbers are approximated to an ellipse ( but why ellipse may be because circle have no boundary and after circle we get ellipse ; )
That's all my thinking and understanding ,.
and i do't know more than that