GNU Ocrad 0.24 Description:
GNU Ocrad is an open source command-line software designed to act as an OCR (Optical Character Recognition) daemon for Linux-based operating systems. It is implemented as a filter and itís based on a feature extraction method, but it can also be used as a standalone program or as a backend to other OCR applications. Key features include the ability to read images in PBM (bitmap), PPM (color) and PGM (grayscale) formats, which are collectively known as PNM. It produces text in UTF-8 or byte (8-bit) formats and includes a layout analyzer, which is capable of separating the blocks or columns of text that are normally found on printed pages. Command-line options include the ability to append text to output file, choose specific filters and characters, force overwrite of output file, inver image levers (black and white), perform layout analysis, place the output into a specific file, suppress all messages, scale the input image, threshold for binarization, cut the input image by a given rectangle and export the results to the ORF file format.