Minimization of bounded multidimensional function

Hello, I have a certain number of points (around 100) in a box of a size of 1000. I want to apply some transformation on those point : translation, rotation (the rotation center is the point (0,0)) and a scaling (dilatation). So I have a function unsing four paramter (TransX, TransY, alpha, scale) which apply the transformation on all my points. Then I compute the mean values (x and y) and the standard deviation (x and y) of the results. I want to find the good translation, rotation and scaling to minmize the mean and the standard deviation. I know that the translation should be limited to certain value as weel as the rotation and sclaling. I need bounded minimization. I use fmincon(f,ScaleRotTrans0,zeros(size(ScaleRotTrans0)),0,zeros(size(ScaleRotTrans0)),0,ScaleRotTransMin,ScaleRotTransMax); Where f is a function which return the sum of the means and standard deviation values (abs values), so I have a scalar output. ScaleRotTrans0 is my starting point, ScaleRotTransMin and ScaleRotTransMax are the bounded value. In fmincon I do not need A.x<=b so I put 0.x<=0... Is it the best way to do this? I have some strange return : Warning: Trust-region-reflective algorithm does not solve this type of problem, using active-set algorithm. You could also try the interior-point or sqp algorithms: set the Algorithm option to 'interior-point' or 'sqp' and rerun. For more help, see Choosing the Algorithm in the documentation. > In fmincon at 472 In Gemini>BoutonTracer_Callback at 328 In Gemini at 33 In @(hObject,eventdata)Gemini('BoutonTracer_Callback',hObject,eventdata,guidata(hObject))

Local minimum possible. Constraints satisfied.

fmincon stopped because the predicted change in the objective function is less than the default value of the function tolerance and constraints were satisfied to within the default value of the constraint tolerance.

criteria details

Active inequalities (to within options.TolCon = 1e-006): lower upper ineqlin ineqnonlin

Can I use a better minimization function. i do not care at all about the time needed to optimize the tansformation values.