Abstract: A system that measures deviation of printed color at selected locations on a moving substrate from a target color. The system comprises using a printed test image of target color, a calibrated spectrophotometer to provide spectral response values of the target color on the test image, a photonic device that provides tri-stimulus values from inline printed images and a computing device. The computing device compares the tri-stimulus values to spectral response values for the test image to calculate a spectral transformation matrix at each location selected to remove variations in optical and mechanical parameters. The spectral transformation matrix is applied to future mapped sets of tri-stimulus values of printed colors captured by the photonic device from selected locations to determine in real-time the deviation of color and thereby control color quality.

Abstract: A new method and system applying the method inspect printed documents that have regions of variable content, the regions having variable locations from document to document in a print job, to ensure that predetermined criteria are met. The locations of the regions of variable content are determined by monitoring a print datastream, and the locations are used to analyze images of the regions of variable content. The images are captured by an optical imaging system mounted in a printer, print media out equipment, a finishing system, or other appropriate location with a suitable view of the printed documents. If a document does not meet its specific predetermined criteria, for example, if an account number does not match the desired account number for that document, then the inspection system takes an error notification action ranging from simply logging the error in a log file to removing the document to stopping the printer.

Abstract: An iterative application of an optical object recognition method, such as an OCR method, with enhancements and modifications yields improved speed and accuracy. In the exemplary embodiment, after an initial pass of the OCR method on a document image, unrecognized blobs are grouped into unknown regions to which the OCR method is applied via an analysis window. If the contents of the analysis window remain unrecognized at a starting position in a given unknown region, the window can be moved within the unknown region to provide more opportunities to recognize the unknown region's contents. Recognized characters are recorded, and the portions of the unknown regions in which they appeared are removed. This pass of the OCR method recognizes characters in blobs containing multiple characters.