Hi Fabio! Ach, you just gave me flashbacks to the time someone broke my car window when I was holidaying in Lido di Ostia. =P Cool work though! =) What do you mean by "using a homography" to detect the Si/No boxes? Could you provide maybe a sample image and working code? It's hard to tell what is going wrong without that context. I understand that there's privacy concerns but maybe you could fill in a blank form as test data? (Or your code to try to find the two si/no boxes that are not masked in the image below.) One thing I'll say though is that neural networks require lots and lots of ground truth data to train effectively, and is probably overkill for what you want to do. In your case, you can probably align the car images very accurately, and detecting marks outside of that should not be too hard. Good luck! Juan. On 26 May 2017, 4:42 PM +1000, Fabio <fdalforno@gmail.com>, wrote:

Hi all, my name's Fabio Dal Forno.

...

I'm a basic scikit user and i have many question too.

I've a lot of scanned document like this

And i want to extract a particular area (si no, yes or no in english) see image below

After that i want to train a neural networ for detect the data compiled by people, y,x coordinate for detect the means of the area (materials damage ecc ecc) and a fixed dimension image for a neural network

I started to work with the following step:

1) Homography for detect document orientation after that i transform the document for rectify that 2) Homography for detect si/no area and coordinate once

the first step work wery well but the second doesn't detect anything.

Am i wrong reasoning ?

Thanks a lot and sorry for my beginner english :)

_______________________________________________ scikit-image mailing list scikit-image@python.org https://mail.python.org/mailman/listinfo/scikit-image