Print and Publishing are sectors where user engagement through Image Recognition has had a lot of acceptance.
Print media pages are recognized best when they contain photos, graphics and large titles that make them visually characteristic. However, including a lot of small dense textual paragraphs may worsen the recognition. Therefore, it is often
Currently we do not perform Optical Character Recognition (OCR) of the scene text.
Moreover, all large paragraphs of dense text, without any image or logo, look similar to our system and should be avoided. On the other hand large titles above images or other graphical elements are visually very distinctive and usually help in the page recognition