Marie Vans

Automatic visual inspection and defect detection on variable data prints

We present a system for automatic, on-line visual inspection and print defect detection for variable data printing (VDP). This system can be used to automatically stop the printing process and alert the operator to problems. We lay out the components required for constructing a vision-based inspection system and show that our approach is novel for the high-speed detection of defects on variable data. When implemented in a high-speed digital printing press, the system allows a single skilled operator to monitor and maintain several presses, reducing the number of operators required to run a shop floor of presses as well as reduce wasted consumables when a defect goes undetected.

Biblio: automatic meta-data extraction

Biblio is an adaptive system that automatically extracts meta-data from semi-structured and structured scanned documents. Instead of using hand-coded templates or other methods manually customized for each given document format, it uses example-based machine learning to adapt to customer-defined document and meta-data types. We provide results from experiments on the recognition of document information in two document corpuses: a set of scanned journal articles and a set of scanned legal documents. The first set is semi-structured, as the different journals use a variety of flexible layouts. The second set is largely free-form text based on poor quality scans of FAX-quality legal documents. We demonstrate accuracy on the semi-structured document set roughly comparable to hand-coded systems, and much worse performance on the legal documents.

PDF document restoration and optimization during image enhancement

We present a document processing method that addresses some of the practical challenges in image enhancement for digital photo album in PDF documents. With the advent of digital offset presses, consumer photo books are becoming increasingly popular, and most such workflows convert the consumers photos and layout into PDF documents. In order to produce appealing photo albums from consumer photographs, some form of automatic enhancement is usually required, and this enhancement is often done late in the workflow just before printing, and therefore it is done on the PDF file. If each and every PDF generation tool simply inserted a single complete image each time an image appeared in the document, then the process of opening a PDF document, iterating through the document, extracting, enhancing, and replacing images, and then saving the enhanced document would be relatively easy. Unfortunately, PDF generation tools often violate that assumption in two ways. Firstly, large images are often written as a set of small images in strips or tiles, which visually appear to be a single image. Secondly, an image in a PDF document may be reused in the document on different position and pages; directly enhancing images without the consideration of the reuse model could result in great increase in the document size and poor system performance. Therefore, image reconstruction and document optimization were performed in our PDF photo album enhancement solution.