Re: Siragi OCR project, uml design diagrams

[FDIL Tarik <fdiltarik at yahoo dot fr>]

Ahmad,

> let us not wasting  times in speaking too much I'm
> involved before in a set
> of open source projects that fail because in these
> projects we speak too
> much and works too little though the work was
> amazing but too much speak
> means earlier fail.

Ok. Let's work. There's 3 packages int the project : 

1- main package : includes OCRgui, OCRengine and
OCRparameter classes.

2- image_tools package : includes Image_reader
(abstract), TiffReader, JpegReader, Segmentation
(abstract), Pixelization and Vectorization
classes.JpegReader and Vectorization are optional in
the first release.

3- classification package : includes Recogintion
(abstract), NNPixelRecognition and NNVectorRecognition
classes. The later class is optional in first release.

Which package and which classes in the package would
you like to write. Since you have already wrote a
segmentation program you could be interested in
writing Segmentation and Pixelization classes. You can
choose another class if you want. 

The sole prerequisite before developping a class is to
agree on interface of that class : What methods should
be defined using which prototypes.


> but i have a final question, you tell me that you
> make some tests how ?
> do you use a premade neural network toolbox? or you
> made one?
> if you use a premade one what is this? and if you
> made one by yourself to
> intend to attach it to this project?

I'm using SNNS (Stutgart Neural Network Simulator)
simulator. 
I will upload soon characters patterns defined to
train the network.

Best regards.

Tarik


	

	
		
___________________________________________________________________________ 
Faites de Yahoo! votre page d'accueil sur le web pour retrouver directement vos services préférés : vérifiez vos nouveaux mails, lancez vos recherches et suivez l'actualité en temps réel. 
Rendez-vous sur http://fr.yahoo.com/set