I am wondering the meaning of the outputs. I understand that the images with "vertica" and "horizontal" titles are the seperators, but what does "block" title mean?, It is captured right after the block extraction step. Is there an output after the VIPS algorithm is completed giving the segmentation results in various colors as presented in the paper?

Why the generated blocks have a flat structure? Shouldn't blocks have names like block 1, block 1.1., block 1.2, etc.?

I am curious whether Vips approach work for the images containing text (like document images), where it can segment the text in different regions based on its visual presentation

@wushuartgaro
Hi. I'm working on a project where I need to extract contact info of personnels from webpages and I found your work to be very impressive and useful for my project.

But it would be really helpful if you could help me with a few issues I'm facing,

1. I want the whole block of a person's contact information as a segment instead of 'name','email id',etc., as separate segments. How do I make this happen?
2. How do I get the segmented blocks as output images instead of the whole web page in segmented form?

Thanks in advance.

theres no explanation of how to use this. I tried python Vips.py but nothing.