character recognition using NuralNetwork or PRT toolbox

2 Ansichten (letzte 30 Tage)
mamata
mamata am 20 Jun. 2014
I am interested in character recognition. please suggest which approach should I follow:
1 patternnet of Neural Network Toolbox 2 feedforwardnet of Neural Network Toolbox 3 PRT toolbox

Akzeptierte Antwort

Greg Heath
Greg Heath am 21 Jun. 2014
patternnet for classification and pattern-recognition
fitnet for regression and curve-fitting
Both call feedforwardnet which NEVER has to be explicitly called.
Search the NEWSGROUP and ANSWERS for relevant posts on character recognition.
Hope this helps.
Thank you for formally accepting my answer
Greg

Weitere Antworten (1)

Dr Oluleye Babatunde
Dr Oluleye Babatunde am 8 Jul. 2014
Both are good. You must identify the classinformation and the actual features set in the dataset.
You will need these infom to train the network
i.e net = train (net, features, classinfo)

Community Treasure Hunt

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

Start Hunting!

Translated by