Projects

Reading best-before dates on yoghurt pots is a challenge for classic image processing systems, as the writing on a curved background is often distorted and varies in size and contrast. With the help of deep learning, letters and numbers can be read reliably in different light and background conditions.

A dual camera system with mirror deflection enables the reading of part numbers on so-called turbocharger guide vanes by means of OCR. For this purpose, two Cognex In-Sight 8000 smart camera systems were integrated into a senswork VisionUnit with mirror deflection.

Our camera system inspects automotive labels in a robot cell from a distance of more than 1 m. With a powerful spot lighting, the label can also be illuminated intensively and still homogeneously from this distance. The test program checks texts via OCV, the quality of data matrix codes using AIM-DPM and the quality of printed symbols 100 percent.

In a labeling machine, the product labels are applied with up to 20 applications per second. An incorrectly inserted type of label or incorrectly applied labels can mean recalling entire batches or laborious re-labeling as long as the error is noticed in good time. Barcode scanning systems provide a remedy here: Our barcode technology based on Cognex Dataman reads up to 20 barcodes per second effortlessly and with absolute reliability.

As part of a fully automated production, one and the same system should test various connector geometries such as connector strips, Fakra connectors or other HF connectors and their labels. Features such as pin positions, wobble circles and coding features are to be checked. As part of the label inspection, textual content is automatically read and compared using OCV, and symbols and graphics are checked for completeness and print quality / legibility.

Varying the font and character size on a non-homogeneous background is very difficult for conventional OCR. With a robust training set, ViDi Read can accurately read letters in a variety of lighting and background conditions.

Varying opacity and bubbles in the liquid create a very inconsistent background in the bottle. The imprinted date and batch codes are difficult to recognize for ordinary image processing. ViDi Read can read letters accurately under a wide range of light and background conditions.

Different liquids create inconsistent backgrounds under the transparent bottle. Plastic seams and difficult reflection angles pose another challenge. ViDi Read can accurately read letters under diverse light and background conditions.

Stamped metal at different angles of reflection presents a challenge for rule-based image processing: No two features look exactly alike,especially on curved surfaces. ViDi Read can accurately read letters under a wide range of lighting conditions.