The Imaging Source blog

The World's Machine Vision Trade Fair: VISION 2016

Published on November 29, 2016

From November 8 to 10, The Imaging Source took part in the world's largest machine vision trade fair, VISION, Stuttgart. Naturally, the topics 3D vision, web-based integration and embedded vision dominated the show as machine vision becomes increasingly central to the newest developments in industrial robotics and automation. Booth visitors enjoyed refreshments while acquainting themselves with the new USB3 Vision-compliant, industrial cameras featuring Sony Pregius global shutter sensors. Available from 2 - 5 MP, these sensors ensure high resolution and excellent image quality: For example, the DFK 33UX250 color and DMK 33UX250 monochrome cameras.

Industrial cameras featuring Sony CMOS sensors

Presentation at Industrial VISION Days

In addition to the trade show floor, VISION also offered visitors the Integration Area and the forum, Industrial VISION Days. As part of this forum, Business Development Manager, Patrick Gailer, gave the presentation "Modern Camera and Machine Vision Interfacing Concepts" which outlined The Imaging Source's modular web-based approach to vision system integration.

The Imaging Source at VISION 2016

VISION in Numbers and What's Next

According to VISION's own sleek little info-graphic, the show claims over 9,000 visitors - an almost 13% increase over 2014's numbers - from 58 countries most of which came from the fields of imaging and machine vision, automotive and electronics. Dr. Olaf Munkelt, CEO of MVTec Software and Chairman of the Board of VDMA Machine Vision, himself noted "...machine vision technology is no longer confined to a factory environment but is now an integral part of our everyday lives" meaning that we can expect continued growth and paradigm-shifting innovations from machine vision technologies. Thanks to all who stopped by.

Versatile, user-friendly machine vision technolgy

Vision China Show Beijing 2016

Published on November 4, 2016

The full name of the Vision China Show Beijing says it all: 13th China International Machine Vision Exhibition and Machine Vision Technology & Application Conference 2016. Over 20,000 visitors interested in the latest machine vision technology and hardware attended the show at the China International Exhibition Center (CIEC) from October 17 - 19. The Imaging Source and its local reseller, Beijing United Scientific Camera & Imaging Corp, displayed the new 33 series of GigE and USB 3.0 cameras. Thanks to show organizers for a successful show.

Discovering the latest in machine vision technology: Vision China Show Beijing 2016

AOI Forum & Show 2016

Published on November 3, 2016

The Imaging Source attended The AOI Forum & Show on October 20 and displayed its latest 33 series GigE and USB 3.0 cameras. Every year, AOIEA (Automatic Optical Inspection Equipment Association) organizes the on-campus event and this year also promoted a series of seminars which proved very popular. Comprised of a group of researchers and industry professionals, the AOIEA focuses on bringing academia and industry together.

33 series of HDR cameras featuring the highly sensitive Sony Pregius CMOS sensors (IMX 264/265/252/174)

The National Chiao Tung University in Hsinchu, Taiwan, hosted the event. As a leading university for electrical and computer engineering studies and research, the campus serves as a perfect venue for the one day show. Integrators, component suppliers, equipment manufacturers, academic researchers and students acquainted themselves with the latest industry developments in hardware and software. Many thanks to AOIEA for organizing the event.

HALCON 13 - Preview

Published on October 28, 2016

The new major version of MVTec's standard machine vision software, HALCON 13, will be released on November 1, 2016. It introduces some noteworthy innovations which we would like to acquaint you with.

Algorithm Improvements

Algorithm speed-ups have advanced consistently - achieving an average 14% improvement on all tools as compared with HALCON 12. Two outstanding examples of this are shape-based matching and 3D reconstruction with speed-ups of up to 3 and 4 times respectively.

Additionally, many functions of the algorithm have been added to or improved. Two new edge-preserving noise filters offer significant performance enhancement and can also be used for image stacking as in HDR applications.

The MSER algorithm, which has proven to be more robust than threshold and region-growing methods for segmentation, has been implemented in order to simplify the segmentation of sharp-bordered foreground objects against contrasting backgrounds.

Developments for 3D Applications

High quality 3D reconstructions can now be created using the combined image data from a calibrated multi-view camera system. In comparison with previous methods, outliers and mismatched point correspondences are reduced and multiple correspondences are adjusted to create a closed surface. With additional image data from a color camera, the surface can be texture mapped in order to produce a realistic 3D rendering. The resulting image data can also be directly uploaded to a 3D printer.

Surface-based matching has been expanded with 3D edge detection. This enables considerably more precise surface-based matching with fewer false matches and is especially useful for the matching of objects with large uniform surfaces and little surface detail.

Additionally, a new 3D point filter has been included which is particularly effective in eliminating outliers in edge areas.

Simplified and Enhanced Classification Processes

In 2D imaging, a new significantly simplified texture classification process for the training of surface features will be available. The new texture classification can return classified areas directly as regions.

For better control, Barcodes/2D code recognition can be taken from other threads. The QR-code reader features a more robust handling of distorted and low-contrast codes.

For text recognition there will be a new OCR classifier which is enhanced by deep-learning classification algorithms. HALCON 13 achieves recognition rates of up to 3 times higher than those from HALCON 12 without sacrificing the incredibly fast reading rates.

More Debugging Flexibility and Simplified Rendering

Soon, it will be possible to debug the HdevEngine directly in Visual Studio. This can also be carried out with multithread applications. The connection between application and script is accessed via an IP socket, thereby making it irrelevant whether the application is run locally or on another computer in the network.

Finally, the visualization function has been improved for simplified rendering. Text and other overlays can now be inserted as transparent or non-transparent and displayed flicker-free in live-mode. The image area can also be zoomed into without loosing the overlay.

Test HALCON 13 for Free

HALCON 13 will be available for purchase as either a new license or as upgrade starting November 1, 2016. You can also test HALCON 13 at no charge. Please contact our sales department if you are interested in an evaluation license.

Automated Inspection of Artificial Corneas

Published on September 7, 2016

The following is a summary of the article, Vision checks optical characteristics of artificial corneas. The original article, written by Gary Livingstone, was published in Vision Systems Design in July 2016 (Vol. 21, 27-30) and appears here with permission of the publisher.

Thousands of low-vision sufferers could be helped every year with a corneal graft. But with comparatively few donor corneas available, synthetic corneas are a medical necessity. Oxford MEStar, a bioengineering products and solutions company produces such artificial corneas. Gary Livingstone, Managing Director of LG Motion explains in his article, "Vision checks optical characteristics of artificial corneas," how his company developed a semi-automated inspection system for MEStar to tackle a demanding quality inspection task involving these delicate transparent prostheses. LG Motion's vision-based motion control system features The Imaging Source's DMK 23UP031 USB 3.0 industrial camera (USB 3.0 Mono, 5MP, 15 FPS).

Fig. 1: LG Motion's vision-based motion control system featuring the DMK 23UP031 monochrome camera.

Translucency Poses a Challenge to Efficient Inspection

Because the artificial corneas are medical implants, they are of course subject to strict controls. One of the most critical aspects of the control process is the transparency measurement of each cornea which is performed via laser analysis. But exactly this important characteristic, transparency, had made an in-line inspection process problematic. The corneas and their support scaffolds are suspended in a transparent medium in a Petri dish and vacuum packed into sterile blister packs (Fig. 2, below). Locating the transparent cornea within the packaging proved difficult which meant a trained operator was needed to correctly position them for optical analysis in the laser's field of view. Wishing to semi-automate this inspection task as part of an in-line production process, MEStar contacted LG Motion.

Fig. 2: The artificial corneas and their integral supporting scaffolds are suspended in a transparent gel and sealed in clear plastic blister packs.

Solution: Structured Light and a Monochrome Industrial Camera

An integral part of the vision-based motion control system created by LG Motion is Scorpion Vision's Compact Vision System. In order to differentiate between the transparent substances within each blister pack, the inspected samples are first illuminated by a patterned, red LED (0.25mm grid pattern from wire mesh) (Fig. 3). The built-in USB 3.0 monochrome camera captures the grid pattern image and transmits the image data to the Scorpion Vision Compact Vision System for analysis. The distortion of the light pattern allows the software to identify the edge of the Petri dish thereby creating a region of interest in which the cornea can be found. Edge detection and geometry tools are then further used to precisely locate the cornea. Once the cornea has been detected, the system determines its center coordinates and then optimally adjusts the package in preparation for optical analysis.

Fig. 3: The inspected samples are first illuminated by a patterned, red LED (0.25mm grid pattern from wire mesh).

Semi-automation for Continuous In-line Inspection

The optical analysis is executed by an Arduino single-board computer which is interfaced to an Arcus Technology stepper motor controller. If the vision system fails to detect the presence of a cornea, or if the analytical system confirms a cornea does not meet the required tolerance, the Arduino processor receives a fail signal and instructs the Arcus controller to move the gripper over to a chute where the defective product is rejected. If the system confirms a cornea meets all requested parameters with a pass signal, the processor instructs the controller to move the gripper over to a chute where the product is accepted. The processor instructs the controller to return to the home position where the next item awaiting inspection can be loaded into the gripper for continuous in-line production.

Learn more about camera options for inspection systems: USB 3.0 monochrome industrial cameras, USB 3.0 color industrial cameras, GigE monochrome industrial cameras, and GigE color industrial cameras or contact us.

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, frame grabbers and video converters for production automation, quality assurance, logistics, medicine, science and security.

Our comprehensive range of cameras with USB 3.0, USB 2.0, GigE, FireWire 400, FireWire 800 interfaces and other machine vision products are renowned for being innovative, high quality and constantly meeting the performance requirements of demanding applications.

Automated Imaging Association ISO 9001:2008 certified

Contact us