neural network image classification (good, so-so, bad)
6 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Francesco Piantedosi
le 9 Mar 2016
Commenté : Francesco Piantedosi
le 17 Mar 2016
I would build a neural network to be feeded with images taken by my cell phone or camera. Starting from that image on some tools, ANN should identify 3 classes: OK, not so good, BAD.
Can someone address me on ho extract correct features from images and the feed my ANN? Any idea on how many layers and nodes per layers? I think I should have same neurons as input as pixel of my image, and 3 neurons as output.
TIA Francesco
1 commentaire
Greg Heath
le 11 Mar 2016
The number of hidden nodes, H, should be the smallest number that will yield acceptable results. I typically use Ntrials = 10 or 20 nets for each value of H in an interval Hmin:dH:Hmax.
For most of the MATLAB examples
help nndatasets
doc nndatasets
I have used numel(Hmin:dH:Hmax) = 10 which may have to be refined with another run with larger Hmin and smaller Hmax.
Hope this helps.
Greg
For examples search BOTH the NEWSGROUP and ANSWERS using
greg Hmin:dH:Hmax
greg Ntrials
Réponse acceptée
Explorer
le 9 Mar 2016
Neural Network images classification works fine. Accuracy of classification also depends on the features of the images. You haven't yet extracted features of images. Without features, you can not proceed.
First find an algorithm from research papers to extract features of images. And then you can ask for help in classification or feature matching using ANN.
3 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Pattern Recognition and Classification dans Help Center et File Exchange
Produits
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!