• English
  • Deutsch

The Imaging Source blog

New 37 Series Cameras Featuring Sony STARVIS IMX462

Published on December 1, 2021

The Imaging Source announces the addition of the Sony STARVIS IMX462 to its 37 Series cameras. The Imaging Source announces the addition of the Sony STARVIS IMX462 sensor to its 37 Series industrial and board-level color cameras.

    These new rolling-shutter CMOS sensors display the following characteristics:
  • Resolution: 2.1 MP, (1,920px × 1,080px)
  • Sensor Format: 1/2.8"
  • Pixel Format: H: 2.9 µm, V: 2.9 µm
  • Excellent image quality in visible and NIR light regions

DFK 37AUX462 - Industrial Camera

DFK 37BUX462 - Industrial Camera

DFM 37UX462-ML Board Camera

Cameras featuring Sony's IMX462 STARVIS sensors are ideal for low-light applications in security, inspection and microscopy.

Please feel free to contact our sales team with any questions or inquiries.

Deep-learning-based OCR: Casing Inspection Saves Labor and Reduces Errors

Published on November 22, 2021

Headstamps are ammunition markings which serve as a classification system to account for the use, safe transportation, storage and quality control of ammunition. Police departments register all movements of ammunition into and out of their armories using ammunition control databases. These inspection and entry tasks are performed by officers themselves and cost police departments hundreds of hours every year. Taiwan's National Police Agency (NPA) cooperated with The Imaging Source reseller, Nevis Technology, to create a machine vision system with deep-learning-based optical character recognition (OCR) to inspect and catalog the ammunition. The project engineers selected The Imaging Source's DMK 33GP031 GigE monochrome industrial cameras to be used in conjunction with the system software which was developed by Nevis Technology specifically for the application. The new inspection system has allowed the NPA to fully automate the cataloging process, saving labor and reducing errors.

Trays of ammunition must be inspected and cataloged before distribution to officers. Via optical character recognition (OCR), machine vision ensures that the task is performed accurately and efficiently

Monochrome Industrial Cameras Deliver Contrast-rich Images for OCR

The NPA had been looking for ways to automate the inspection of new and used ammunition for years and this was the first time the NPA had worked with a vision-based inspection system of any kind. Finding a reliable and highly accurate system seemed to pose the biggest challenge.

Nevis Technology devised a system whereupon two of The Imaging Source's monochrome cameras capture images of ammunition trays from differing angles. Ideal for machine vision tasks like OCR, monochrome cameras offer improved image contrast and resolution delivering sharp and contrast-rich images which ensure robust character localization, segmentation and extraction.

The software algorithm compares the extracted data with the pre-trained dataset. Any empty cells or casings not meeting the set standard (NOK) are indicated in red (see image below). The system fully inspects one tray of ammunition (typically 50 rounds per tray) every 5 seconds, satisfying the NPA's project requirements. Nevis reports, "By using the machine vision system to automatically identify, report, and pick out the bullets with different specifications, the police units have successfully reduced the manpower by about 60% and saved up to NT$2 million per year."

The OCR system uses deep learning for defect and presence detection. Nevis Technology reports police have reduced the labor used for the inspection tasks by up to 60%.

MVTec Releases MERLIC 5: Save on Deep Learning Functionalities until December 7, 2021

Published on October 6, 2021

MERLIC 5 to be released on October 7, 2021 MERLIC, MVTec's all-in-one software solution for the design and execution of complete machine vision applications, is set with a new release for October 7, 2021.

MVTec's new MERLIC 5 release will make rapid implementation of machine vision applications more flexible, more powerful and simpler than ever before. In addition to the new machine learning features listed below, MVTec has introduced a new licensing model. The new Packages model allows users to select only the features matching the scope of their particular application and replaces the Editions licensing model. Based on the number of image sources and features ("add-ons") required, users can select the packages Small, Medium, Large and X-Large.

    New release highlights include:
  • "Detect Anomalies" tool performs all training and processing steps directly in MERLIC
  • "Classify Image" tool enables the use of classifiers for easy classification in MERLIC
  • Image Source Manager (ISM) decouples the image acquisition source from the tool flow.

Special Offer - New & Existing Customers Save on MERLIC 5 Packages until December 7, 2021

To celebrate the release of MERLIC 5, MVTec is offering discounts on new packages: For the launch, Deep Learning functionalities will be included for free with every package until December 7, 2021.

To take advantage of the special discounted price, or for a free trial version of MERLIC, please contact our MERLIC support staff.

GigE Industrial Cameras & HALCON: A Proven Imaging Solution

Published on August 2, 2021

TIS Cameras: "Easy to Work with in a Complex Automation System"

Industrial automation solutions provider Teomsi Electric Company recently worked with Ecolor and WIP Industries Romania, manufacturers of flat-pack furniture, in the development of inspection systems to detect drill holes on furniture components. For the vision systems, Teomsi selected The Imaging Source's DMK33GX264, GigE industrial cameras, and MVTec's comprehensive machine vision software, HALCON.

Sergiu Vais, project manager at Teomsi, noted that his company selected The Imaging Source's industrial cameras for the projects' vision systems because the cameras are "easy to work within a complex automation system." The new inspection systems have enabled the manufacturers to significantly reduce the error rate, increasing customer satisfaction for the companies' largest customers, including a global furniture retailer.

<strong>Five-camera automated visual inspection system</strong> for a large furniture manufacturer uses <strong>DMK33GX264 GigE industrial cameras</strong> and <strong>HALCON</strong> to inspect for the presence of drill holes on flat-pack furniture pieces.

Reducing Product Error Rate

Furniture manufacturing is a multi-stage process, but perhaps the most crucial step comes during milling and drilling as the correct arrangement of drilled holes means success or failure for the consumer when assembling the final product. Manual inspection of such pieces is often time-intensive and prone to error due to human and environmental factors on the shop floor. An automated visual inspection system, on the other hand, provides a persistent and highly-accurate solution with replicable, and rapid results. The challenge: deliver a proven and reliable, automated visual inspection system to reduce the product error rate.

Four-camera system

It Starts with an Image

A robust inspection process begins with a quality image, and the 5 MP, global-shutter CMOS cameras Teomsi selected are ideal for imaging moving objects while delivering sharp, distortion-free images. The GigE-Vision-compliant industrial cameras also ensure efficient camera upgrades with no additional programming. In the four-camera system developed for WIP Industries Romania (left), specially-positioned monochrome cameras capture the drill holes from different viewing angles. HALCON further processes the images, returning an "OK"/"NOK" value for the part.

HALCON's rich feature set and well-defined architecture allowed for a fast, flexible development process. Fully leveraging The Imaging Source's HALCON support team and 30 years of machine vision experience, Teomsi has delivered automated inspection systems, which now consistently provide higher throughput and improved product quality for Ecolor and WIP Industries Romania.

Updates (July 2021) to the TIS Linux SDK: Linux for Embedded

Published on July 20, 2021

tiscamera SDK, an open-source project, now fully supports camera modules for embedded applications.

For years, The Imaging Source has continuously maintained and developed its Linux library including the tiscamera SDK for Linux, an open-source project published under the Apache 2.0 license. The Imaging Source has just released updates for tiscamera SDK as well as for the MIPI CSI-2 and FPD-Link III module drivers (NVIDIA® Jetson™ platform). These updates will advance and simplify development of applications on embedded platforms. The following points highlight the release's major improvements:

  • Full integration and support of MIPI CSI-2 and FPD-Link III cameras in tiscamera and tcam-capture
  • Dedicated GStreamer source providing raw image data for MIPI CSI-2 and FPD-Link III cameras on NVIDIA Jetson platform
  • Improved and unified access to embedded camera parameters on the NVIDIA Jetson platform
  • Added trigger support for selected sensor modules and embedded platforms

All changes to the tiscamera SDK can be found in the changelog.

This blog post is an update to an April 2021 post listing other additions and changes.

Looking for older posts?

We have been blogging since 2007. All old posts are in the archive and tagcloud.

About The Imaging Source

Established in 1990, The Imaging Source is one of the leading manufacturers of industrial cameras, video converters and embedded vision components for factory automation, quality assurance, medicine, science, security and a variety of other markets.

Our comprehensive range of cameras with USB 3.1, USB 3.0, USB 2.0, GigE, MIPI interfaces and other innovative machine vision products are renowned for their high quality and ability to meet the performance requirements of demanding applications.

ISO 9001:2015 certified MVTEC | Edge AI + Vision Alliance | EMVA

Contact us