Smart PDF/A Desktop is an application for home and office use, allowing you to create compact color electronic documents in the PDF/A format from scanned paper documents and document photos. Intelligent image processing algorithms used in the application provide effective compression of electronic documents (up to 20 times, as compared to the original JPEG file) and their high quality, which is important for further transfer and/or storage of these files.
|1. The Smart PDF/A Desktop Office detects document edges on a photograph, using the Smart ReSquare technology.||2. Smart PDF/A Desktop Office software interface. Selecting the options for processing the images loaded.|
The resulting document saved in the PDF/A format is a multi-layer PDF file, the layers of which are processed with optimal compression algorithms. To extract separate information layers, the software uses the color morphological segmentation of images, which takes into account both color characteristics of objects and the morphological relations between them. This allows recognition of text, even if it is partially overlapped by notes, seals, stamps, or other marks.
Results of processing some photographed and scanned documents:
Payment order – Photographed document (4 157 KB) | Smart PDF/A document (67 KB)
Notice – Photographed document (3 252 KB) | Smart PDF/A document (82 KB)
Invoice – Scanned document (1 275 KB) | Smart PDF/A document (55 KB)
Book page – Scanned document (2 644 KB) | Smart PDF/A document (62 KB)
- Intelligent image processing: automatic removal of scanning artifacts (noise, tilt, blur, etc.) in a combination with determination of the original document orientation allow increasing the visual quality of the final result;
- Standardized file format: electronic documents are saved in the PDF/A-1b (ISO 19005-1:2005 standard) and PDF/A-2b (ISO 19005-2:2011 standard) formats, which makes the documents up-to-date for years, from the technological point of view;
- Text recognition: the application provides recognition of text data (with tesseract-ocr installed) followed by embedding the text in a PDF/A document as a “transparent layer”, which ensures high functionality of information search;
- Color morphological segmentation: a document image is being divided into data units with taking into account both color characteristics of objects and the morphological relations between them. This allows recognition of text, even if it is partially overlapped by notes, seals, stamps, or other marks.
- A wide range of user controls for document processing allows achieving optimum results.
- Document photo processing capability (built-in Smart ReSquare technology);
- Two-sided scanning support (for scanners equipped with an automatic document feeder);
- Batch scanning support (for scanners equipped with an automatic document feeder).
Operating systems supported:
Microsoft Windows XP, Microsoft Windows Vista, Microsoft Windows 7, Microsoft Windows 8.
Minimum hardware requirements for PC:
- CPU clock rate of 1 GHz or higher;
- At least 1024 MB of RAM;
- TWAIN-compliant scanner.