> > 2. Is it possible using LUA scripts to analyse the layout of an image > > of a document and output the result to an image (with boxes around > > paragraphs present etc.)? > > Yes. Or you can write a very small C++ command line tool. > > Either way, the pixel-accurate format for page segmentation output is > described in this document: > > http://docs.google.com/Doc?id=dfxcv4vc_92c8xxp7 > > Tom
Hello, Thanks for the reply. I will have a proper look at the supplied document. One thing I would love to achieve at this stage is something similar to http://ocrocourse.iupr.com/layout-analysis/rast-layout.png?attredirects=0. I went through all LUA test scripts and applied the following workflow: 1. Open image 2. Deskew image 3. Binarize image 4. Segment image using the RAST method 5. Extract regions ... And this is where I get stuck. I know that the object of the RegionExtractor class has a method called bbox() which outputs the coordinates of the bounding box in a rectangle-data type. I went through IUlib and even found something called bounding_boxes(), but I'm still struggling to use it in LUA. I would really appreciate your help, Thanks again for the earlier answer, Sending kind regards, Bill --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "ocropus" group. To post to this group, send email to [email protected] To unsubscribe from this group, send email to [email protected] For more options, visit this group at http://groups.google.com/group/ocropus?hl=en -~----------~----~----~----~------~----~------~--~---
