Deep Learning Image Classifier
deeplearning.cs.toronto.edu
Deep Learning Image Classifier
1–10 of 33 posts
Re: Deep Learning Image Classifier
#2
Re: Deep Learning Image Classifier
#3Didn't give me results at all to the three images I uploaded. Might be broken.
Re: Deep Learning Image Classifier
#4Didn't give me results at all to the three images I uploaded. Might be broken.
I think it's rescaling all images to fit the training size. If that is the case, then when your image has very different dimensions it gets distorted and confused. Try something with a height/width ratio like the samples.
Re: Deep Learning Image Classifier
#5tried two images:
http://kephra.de/Dampf/IMG_20140620_133839_800x600.jpg http://kephra.de/pix/Snoopy/thump/IMG_20130822_135928_640x48... Tried some other images from the lifestyle section of my homepage, but it looks as if the system newer saw a sewing machine before as it gives "Low recognition confidence", and no tags.
Re: Deep Learning Image Classifier
#6Are there actually any image feature detectors and descriptors involved (like blob, edge and texture detectors) or is this solely based on artificial neural networks?
Re: Deep Learning Image Classifier
#7Are there actually any image feature detectors and descriptors involved (like blob, edge and texture detectors) or is this solely based on artificial neural networks?
AFAIK, it's using a Deep Neural Network; which means, the inputs are, basically, pixel values (possibly normalized), and all feature detection, etc. is done in the layers of the network.
Re: Deep Learning Image Classifier
#8Are there actually any image feature detectors and descriptors involved (like blob, edge and texture detectors) or is this solely based on artificial neural networks?
AFAIK, it's using a Deep Neural Network; which means, the inputs are, basically, pixel values (possibly normalized), and all feature detection, etc. is done in the layers of the network.
yep, they try to learn an image's high level features by learning an autoencoder (that is a transform that takes an image and tries to produce the same image) via a sandglass shape multi layer network. Here is a very readable paper by Hinton himself that describes the approach:
Re: Deep Learning Image Classifier
#9My results (yeah, a tough image) http://imgur.com/pbH52xW
Re: Deep Learning Image Classifier
#10Earlier quoted context omitted.
AFAIK, it's using a Deep Neural Network; which means, the inputs are, basically, pixel values (possibly normalized), and all feature detection, etc. is done in the layers of the network.
yep, they try to learn an image's high level features by learning an autoencoder (that is a transform that takes an image and tries to produce the same image) via a sandglass shape multi layer network. Here is a very readable paper by Hinton himself that describes the approach: http://www.cs.toronto.edu/~hinton/science.pdf
Could it maybe be worthwhile to augment the data with simple image features? E.g. the human visual system is believed to rely on high-level/top down as well as on local/bottom up features (although that might also be simply because of the necessity to compress things for the low nerve count in the optical nerve).