TRUEVIZ: a groundtruth/metadata editing and visualizing toolkit for OCR

摘要: Tools for visualizing and creating groundtruth metadata are crucial document image analysis research. In this paper, we describe TrueViz which is a tool editing groundtruth/metadata OCR. implemented in the Java programming language works on various platforms including Windows Unix. reads stores XML format, corresponding stored TIFF file format. Multilingual text editing, display, search module based Unicode representation also provided. This software being made available free of charge to researchers.