Advanced Vision Technology (a.v.t.) Ltd.

Advanced Vision Technology Ltd.

Chanan Gazala

Barry Ben Ezra

Dan Zamir

Gilad Golan

Maya Dekel-Klein

Leon Kanelovitch

Haim Kreitman

Alan Then

Ohad Menashe

Shahar Golan

Steven Headley

Brian Gamm

Dani Zamir

A method and system for implementation of quality control includes a machine vision system for capturing images of instances of a product, and a computer system including computer memory containing machine-readable instructions executable by a processor. The processor evaluates the quality control images for a plurality of potential quality defects in the product and generates a defect alert associated with a captured image in which at least one potential quality defect is identified. Information about each defect alert is stored in a database log file in the computer memory. A neural network machine learning algorithm processes the database log file by, in a learning phase, receiving human-initiated input accepting or rejecting each defect alert and storing the human-initiated input in the log file, and, in an automated phase, automatically accepting or rejecting at least some defect alerts without performing the step of receiving human initiated input.

Method and process for automated auditing of inline quality inspection

A system for aligning print-heads in a printing-press, which includes a print-head array which includes a plurality of print-head-rows. Each print-head-row includes a plurality of print-heads and prints print a color associated with therewith. Each print-head includes an array-of-nozzles, which includes a plurality of nozzle-lines. The system includes an imager and a processor. The imager includes at least one imaging-sensor. The imager is configured to acquire an image of a printed first-alignment-pattern and further configured to acquire an image of a printed second-alignment-pattern. The processor is configured to receive the image of the first-alignment-pattern and the image of the second-alignment-pattern and to determine alignment of reference print-heads in at least a reference-row of print-heads from the image of the first-alignment-pattern. The processor is also configured to determine alignment of color print-heads in rows other than the reference-row of print-heads, relative to the reference print-heads, from the image of the second-alignment-pattern.

Method, system and patterns for aligning print-heads in a digital printing press

A method controls the color in a printing press, which includes at least one printing station printing a respective color design. The method includes the procedures of determining a control factor to color model, printing a design on a web and acquiring color characteristics corresponding to the printed design on the web. The method further includes the procedures of determining the color quality of the printed color design and determining a required change to at least one control factor when a correction to the color characteristics of the printed design is required. The change to at least one control factor is determined by determining the at least one control factor with respective color related information, which results in a reference color characteristic, according to the control factor to color model. The method returns to the procedure of printing when a correction is not required.

System and method for controlling color characteristics of a printed image

A method identifies at least one malfunctioning nozzle in a digital printing press, the digital printing press including a plurality of nozzles. The method includes printing a design on a substrate, acquiring at least one image of the printed design and identifying at least one artifact in the acquired image. The method further includes identifying the malfunctioning nozzle and classifying the at least one malfunctioning nozzle according to the at least one of the acquired image of the printed design, at least a portion of a nozzle pattern and at least a portion of a uniformity pattern.

System and methods for detecting malfunctioning nozzles in a digital printing press

Method for generating a test-set for inspection of a design being printed by a printing-press, each color-unit in the printing-press prints a respective color. The design is composed of original-layers. Inspection includes determining the origin of at least one defect in the printed-design. The method includes the procedures of generating defective-layer or layers of the design, by introducing at least one selected defect to at least one selected original-layer, in a selected location or locations and combining layers using a trained-synthesis-neural-network. The layers include the defective-layer or layers and remaining ones of the original-layers. The trained-synthesis-neural-network provides a plurality of features respective of each pixel. The method also includes the procedure of generating the test-set from the output of the synthesis-neural-network. The test-set includes at least one synthesized-test-image. The synthesized-test-image includes at least one synthesized-defect at the selected location. The test-set is employed to determine the origin of the defect.

System and method for generating images for inspection

A method of identifying at least one malfunctioning nozzle in a digital printing press including a plurality of nozzles. The method includes the procedures of printing a design on a substrate, acquiring at least one image of the printed design and identifying at least one artifact in the acquired image. The method further includes the procedure of identifying the malfunctioning nozzle and classifying the at least one malfunctioning nozzle according to at least a portion of a combined pattern.

A method for registering a printing press, said printing press including a plurality of printing stations each for printing a respective color-image on a web, each said printing stations being associated with a respective different color, at least two pairs of said printing stations being un-registered, the method includes the procedures of identifying at least two regions-of-interest in the image to be printed, each including a respective different pair of two partially overlapping color-images, acquiring an image of the common area on the web, for each region-of-interest, chromatically separating the acquired image to determine two monochrome images respective of each region-of-interest, for each region-of-interest registering the two monochrome images respective thereof, registering a monochrome image respective of one region-of-interest with a monochrome image respective of another region-of-interest and determining a registration correction for each printing station according to the registration between the monochrome images.

Growing community of inventors

Kfar Saba, Israel

Chanan Gazala