XSane is a graphical scanning frontend for SANE (Scanner Access Now Easy). It uses the SANE-library to talk to scanners. XSane is designed for acquiring images with scanners (there are other devices like cameras and videodevices supported by SANE, but XSane is not designed for that purpose). You can scan to file, do a photocopy, create a fax and start XSane from the GIMP as gimp plugin. Read more hot
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched. new
Eikazo is a frontend to SANE, an application programming interface that provides standardized access to many image scanners. It features plugin mechanisms to support special device features, image processing, and output modules. Currently available image processing plugins include automatic threshold, "dirt removal", and image rotation. More than one output option can be enabled.
A new frontend for the Scanner Access Now's Easy (best known as SANE) libraries and dlls.
geniusvp2 is a SANE backend for the Genius® ColorPage-Vivid Pro II flatbed scanner. geniusvp2 is released under the GNU GPL License.
gscan2pdf is a GUI to ease the process of producing PDFs from scanned documents. You scan one or several pages in with File/Scan, and create a PDF of selected pages with File/Save PDF.
This is a backend to control HP Scanjet 3900 series scanners in Linux (hp3970c and those that use the RTS8822l-01 chipset). Written in C using libusb libraries, it runs as a stand-alone application and includes a SANE backend.
An omnifont OCR software for KDE. Due to the fact that each step of the OCR process can be visualized you can get a quick idea of how OCR works and where the problems lie. However the program may be of minor/no use for end users in its current state.
Kooka is an intuitive, easy to use open source GNU/Linux scan program which is released under the GNU General Public License with exceptions.
Kooka is the scan application of choice for the KDE project and thus it is official part of the KDE Graphics Package. Kooka helps you to handle the most important scan parameters, find the correct image file format to save and manage your scanned images. It offers support for different OCR modules. Libkscan, a autonomous part of Kooka, provides a scan service for easy and consistent use to all KDE applications. Read more
linux-intelligent-ocr-solution (Lios) is a free and open source software for converting print into text using either a scanner or a camera. It can also produce text from other sources such as PDFs, images, or folders containing images. Read more
OCR Shop XTR
(commercial) OCR Shop XTR is a flexible tool for fast and accurate OCR. Built for Linux and UNIX, OCR Shop XTR is ideal for scripting and programmatic applications, as well as stand-alone usage. Extensive command-line parameters allow for sophisticated pre-processing, recognition, and output optimization. The OCR Shop XTR base package supports numerous standard input and output formats, including TIFF, JPEG, and RGB input images, and ASCII and Unicode text output. OCR Shop XTR also provides access to detailed XDOC output with metadata.
OCR Shop XTR Lite
(commercial) OCR Shop XTR Lite for Linux and UNIX is an economic alternative to the fully featured OCR Shop XTR and OCR Shop XTR/API products. Using a simplified front-end and based on powerful ScanSoft® recognition technology, OCR Shop XTR Lite is a command-line interface driven program which generates a single output file. The output format is ASCII text.
OCR Shop XTR/API
(commercial) The OCR Shop XTR/API is a high level SDK for developers, OEMs and systems integrators to embed robust OCR functionality into custom applications. Based on Scansoft recognition technology, our SDK provides unsurpassed recognition accuracy for Linux and UNIX production environments.
ocropy is an OCR system written in Python, NumPy, and SciPy focusing on the use of large scale machine learning for addressing problems in document analysis. Read more
A graphical frontend to the driver for the Primax Colorado Direct 600 under Linux. It supports previewing, batch scanning, tuning of brightness-contrast-gamma-resolution, and exporting of images to .tiff, .pnm, .png, and .ps.
Pyocr is an optical character recognition (OCR) tool wrapper for python. That is, it helps using OCR tools from a Python program.
Tesseract Open Source OCR Engine was originally developed at Hewlett Packard Laboratories Bristol and at Hewlett Packard Co, Greeley Colorado between 1985 and 1994. Read more
tiffscan is an advanced SANE frontend. It has batch mode capabilities and can generate compressed multi-page TIFF files. It handles from bw to color plus infrared scans.
(commercial) VueScan supports over 500 flatbed and film scanners and 142 digital camera raw file types, and is available for Mac OS X, Windows and Linux. It automatically adjusts images to optimum color balance, which reduces the need to manually do this in Photoshop. VueScan includes built-in color calibration of scanners, producing colors that look true to life. Supporting more than 100 brands of negative film, VueScan offers options for scanning faded slides and prints, batch scanning, IT8 color calibration and other advanced scanning features.
YAGF is a graphical frontend for the Cuneiform OCR tool. It lets you open already scanned image files or obtain new images via XSane (scanning results are automatically passed to YAGF).