Command line tool to convert page layout files to the latest PAGE XML format. It supports all previous versions of the PAGE format as well as ALTO XML, FineReader XML, and HOCR
I currently evaluating algorithms that I use for page segmentation. The goal of my algorithms is to find texte block in a image.
For now i am able to get my bounding box (x, y, height and weight) detected by my algorithms and I would like to use layoutEval to speed up the evaluation process of my algorithm. Here is an exemple of what I could get:
I know that I am able to convert an image to xml using Tessercat (and then easy to convert to page) but how can I also give the informations about my bounding box found by my algorithms ?
Hello,
I currently evaluating algorithms that I use for page segmentation. The goal of my algorithms is to find texte block in a image. For now i am able to get my bounding box (x, y, height and weight) detected by my algorithms and I would like to use layoutEval to speed up the evaluation process of my algorithm. Here is an exemple of what I could get:
I know that I am able to convert an image to xml using Tessercat (and then easy to convert to page) but how can I also give the informations about my bounding box found by my algorithms ?
Thanks in advance