correct format for feature matrix in finger print recognition

1 visualización (últimos 30 días)
Dear firiends,
In regarding to correct format for feature matrix in finger print recognition, I have a question.
I have 9 finger prints(for 3 persons) which I want to train my network, and I have 3 finger prints for testing(each person one).
After preprocessing and post processing, I could successfully reach to 2 feature of each finger print which are: Termination=[X Y angel] Biorefication=[X1 Y1 Angel1 Angel2 Angel3] both of the matices for each finger print have different row size.
As I told you I have 9 input, in another words, I have 9 inputs which either of them has 2 matrix which I explained above.
Now , I have no idea how I should put these feature in correct format to feed it into neural network?
I am very thankful in advance for your help. Regards,

Respuesta aceptada

Greg Heath
Greg Heath el 15 de Abr. de 2014
If you have c classes and N I-dimensional feature vectors
[ I N ] = size(input)
[ c N ] = size(target)
where the columns of target are columns of the c-dimensional unit matrix eye(c).
Hope this helps.
Thank you for formally accepting my answer
Greg

Más respuestas (0)

Categorías

Más información sobre Sequence and Numeric Feature Data Workflows en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by