CircumSpect TM 360 Degree Label Verification and Inspection Technology Written by: 7 Old Towne Way Sturbridge, MA 01518 Contact: Joe Gugliotti Cell: 978-551-4160 Fax: 508-347-1355 jgugliotti@machinevc.com www.machinevc.com April 15, 2008
Overview, Inc. is based in Sturbridge, MA and has a lab building in Westborough, MA and an assembly building in Troy, NY. MVC is focused on the integration of machine vision technology to provide automated inspection and process control during the manufacturing and packaging processes in a wide variety of industries. End users come to MVC for complete machine vision solutions. Machine builders and automation integrators work with MVC to develop the machine vision portion of their overall assembly, processing, handling, or packaging solution. OEM s of packaging systems, code printers, robotics, and other process systems work with MVC as an extension of their engineering organizations to design, install, and support vision system options. As the vision industry has matured with easier-to-use products, one thing remains the same - vision projects are inherently complex. The development and deployment of a vision system requires a team of experienced vision engineers that can avoid potential problems that arise when combining high technology from multiple domains (PLC communications, robotics, vision architecture, real world lighting and optics, motion, human intervention). MVC works with its clients to provide a thorough evaluation of the application, a detailed proposal with images, and a complete vision solution per the specifications and system acceptance criteria. works with the client as a partner and provides sound guidance to assure the application is done correctly the first time. MVC has developed turn-key solutions based on its machine vision experience and expertise. One of these solutions is used to verify that the expected label or printing is applied to cans, aerosol containers, bottles, jars, and any round container. This CircumSpect TM solution is discussed in this paper. Introduction to 360 Degree Label Verification and Inspection The focus of this white paper is on using 360 degree imaging for the verification and inspection of labels that have been applied to a cylindrical object. This technology can also be applied to aerosol cans and pre-printed round containers. By verification, the focus is on confirming that the expected label has been applied to the container. This can be based on matching brand logos and flavor patterns (graphics) on the label. Many plants are adding a 2D Data Matrix code to the label artwork and are using that code to distinguish label types and languages. Others have 1D barcodes on the label and use the UPC code to differentiate product labels. With label inspection, a vision system can measure the label skew to determine whether it was applied properly or is tilted. Vision can examine the two ends of the label to determine whether the overlap is acceptable or that the ends are not together vertically. The shape of specific graphics may be examined to determine
whether label damage has occurred. Edge-finding tools may be used to check the label position on the container. 2D codes can be read and output to a database to facilitate e-pedigree tracking. 360 degree label inspection eliminates the need for container handling, does not slow down the line, and provides an extra level of assurance that the correct and expected label has been applied to a container or that the expected pre-printed container is present. MVC CircumSpect TM Technology Primer The MVC solution that can be applied to Label Verification and Inspection is called CircumSpect TM. CircumSpect TM will verify that every container s label matches the product that is expected. o This is foreign part detection. CircumSpect TM will accept the label or container it has been instructed to pass and will fail anything that is not that expected label or container. CircumSpect TM is placed over the conveyor and acquires images of each product as it passes through a multi-camera housing. o The product does not have to handled or stopped. o The product can pass through the imaging station in random orientations. o A reject station can be an integral part of this modular solution. CircumSpect TM is based on technology from Cognex, the largest machine vision technology company in the world. o The system will create a 360 degree view of the label using 4 cameras, a simultaneous camera acquisition, and the calibration of the 4 images to create a single continuous virtual line-scan image. CircumSpect TM will present the image of the container s label for analysis in the same layout every time, despite the fact that the container will be randomly oriented on the conveyor when the images are acquired. o The vision tools, such as the Barcode Reading Tool, 2D Code Reading Tool, Pattern Inspection, Gauging, and Pattern-Matching Tool, can be applied to every un-wrapped label image. The machine vision technology provided by Cognex and integrated by MVC has been applied to this type of application in a production environment in over 50 plants. It is field-proven and offers a unique option in addressing important issues in: Consumer Safety Consumer Satisfaction Distribution Channel Satisfaction
Overview of the Image Formation Process A compact image formation module will be placed over a section of conveyor. The module contains the four side-mounted video cameras, optics, and lighting needed to create 4 distinct images of the product. The containers will be on the conveyor and will be passed through the imaging module. No container handling or specific orientation is required. The primary requirement for image formation is that there is at least a 1 container-width space between every container passing through the CircumSpect TM imaging module. Stainless- Steel Frame Light Reflectors Cameras Conveyor Imaging Module Over the Conveyor, Shown Without Covers. Example Only. Each Application is Different and May Require a Different Imaging Module and Lighting Design.
The lighting is designed to provide a clear image of key label features anywhere in the image and is custom-designed for each application. A sensor will detect that the container is in position and will trigger the CircumSpect TM system for each container. Four camera images will be acquired simultaneously and joined to create a virtual line-scan image. The resolution of the cameras used will be dependent upon the container speed through the system (CircumSpect TM can handle up to 1500 parts per minute) and upon the number and type of vision tools used on the containers. Machine Vision Inspection Tools Included Now that the image has been acquired, it is presented to the application software in a pre-defined start/stop location relative to the beginning and end of the image unwrap process. A selection of primary vision tools designed to address the needs of packaging lines includes: Barcode Verification and Reading (1D) o UPC 2D Data Matrix Code Verification and Reading Optical Character Verification o Lot and Date Codes or other codes printed cleanly on the label in a consistent location and orientation Pattern Matching o Flavors and Types o Special promotional graphics o Brand logo Pattern Inspection o Gross printing errors o Distorted label graphics Pattern Shape Inspection o Key print features missing Brightness and Contrast in a Specified Region of the Image o Basic feature presence Gauging o Label too high o Label angled In general, the more vision tools that are applied, the longer the cycle time for the application. Thus, care should be taken to develop the most efficient combination of vision tools that provide the required inspection tasks. Image resolution also affects the system s maximum speed and should be selected based on the needs of the application.
Sample CircumSpect TM Images In the following examples, a sample label has been trained. The four separate images acquired are shown in the upper section of each image. Note in the following two images that the unwrapped image at the bottom is presented in the same way despite differences in how the containers are presented to the vision system. A Sample Label Is Imaged Any similarity between the sample labels used and any actual product labels is purely coincidental. MVC makes no representation that any particular end user is currently using CircumSpect TM technology. In the sample image above, the label is being imaged in 360 degrees. The vision tools used are verifying that the logo matches the expected logo, the flavor matches the expected flavor, and the 2D code matches the expected value. Note the green graphics around the logo, the flavor, and the 2D code, which is reading and displaying the 2D code that was read. All of these parameters have been pre-trained based on the particular label expected. These pre-trained values can be selected from the operator interface or they can be selected remotely and loaded by a line controller.
In this example, note the orientation of the container and label have changed in the four original images. The un-wrapped image is consistently presented. The Flavor matches the expected one The Logo matches the expected one The Expected Label The 2D Data Matrix code contains the expected value
The Unexpected Label Is Imaged and Will Be Rejected The Flavor does not match the expected one The Unexpected Label The 2D Data Matrix code does not contain the expected value
Conclusions The cost of verifying that the correct label has been applied to a container can be easily outweighed by the cost of a lawsuit or a recall. Safety and allergen prevention are at the top of the priorities list for many manufacturers. Remember that the preprinted containers and labels generally come into a plant from an outside vendor. These containers or labels are loaded into some type of automated batch feeder and if the first few come out OK, it is assumed (without CircumSpect TM ) that all of the containers or labels will be OK. One of MVC s clients operated for over a year before finding that an incorrect preprinted container got into the mix unexpectedly. This was a case of allergen prevention and the cost of finding the problem before the product went out the door pales in comparison to having the product opened and used by an allergic consumer. Whether it s a matter of life and death or a consumer s inconvenience, today s manufacturers are making sure that their product is accurately labeled or that the expected pre-printed container has been filled. Every application is different and may require a different imaging enclosure over the conveyor, may differ in terms of image resolution, may differ in line speed, may require wash-down capability, may differ in lighting required, and can vary in any number of ways. Additional information on, Inc. can be found on its web site, www.machinevc.com. Call Joe Gugliotti at 978-551-4160 or e-mail jgugliotti@machinevc.com to initiate a conversation on CircumSpect TM technology. About the Author: Joe Gugliotti is responsible for Sales & Marketing at and has been a part of the machine vision industry for 22 years. He spent 10 years with a leading distributor of cameras, optics, and lighting systems for use in machine vision applications, working closely with Vision OEM s, Systems Integrators, and End Users across the U.S. to evaluate their image formation needs and provide the appropriate solution. Joe spent the next 10 years as an OEM Account Manager and Senior Sales Engineer for a leading Machine Vision OEM, gaining exposure to hundreds of applications across a wide range of industries and using vision technology ranging from simple sensors to advanced PC-based systems and custom cutting-edge solutions. In his position at MVC, Joe applies all of this experience to providing full machine vision solutions and consulting services.