Cognex presents a smart industrial camera powered by deep learning software. This association increases the possibilities of efficient and precise inspection within the framework of industrial automation.
Deep learning and artificial intelligence (AI) are buzzwords in industry and many other fields. The principle of deep learning, a type of AI that uses neural networks, is quite simple: like the human being who learns what a house is from a large number of examples, a deep learning system ends up identifying the nature of an object from images. Whether it's a car's bumper, a package wrap, or something else, deep learning offers an example-based method of solving inspection problems. In addition, each inspection can be continuously improved by feeding the algorithm with more example images. This new data improves the system, resulting in more accurate results.
Pushing the limits of automated inspection
Manufacturers continue to rely on human inspectors throughout the production process, as traditional machine vision systems are unable to handle the complexity or variability of certain tasks. Human beings, on the other hand, produce varying results from person to person, and can get tired throughout the day. In addition, for a variety of reasons, many aspects of production still go uninspected. Both of these realities expose manufacturers to quality control issues or the risk of recall.
An integrated artificial intelligence vision system is able to combine the judgmental capabilities of a human inspector with the robustness and consistency of an automated inspection or quality control solution. According to Cognex, this is precisely the main benefit of the new In-Sight D900 vision system from Cognex.
The first of its kind, according to the manufacturer, this solution integrates In-Sight ViDi, Cognex's deep learning software, into an industrial-grade smart camera. This association increases the possibilities of industrial inspection online.
The material: unparalleled versatility
The In-Sight D900 hardware is a compact, industrial-grade smart camera, which can be easily installed and deployed on the line without the need for a PC. Highly modular, the IP67 vision system includes lighting, interchangeable lenses, filters and covers that can be customized to meet the needs of each application.
High Dynamic Range (HDR +) imaging system creates images at consistent exposure, an LED indicator allows remote control of inspection success or failure, and results can be stored locally on an SD card . The built-in inference engine has been added to specially run deep learning applications. While the hardware is some of Cognex's most advanced, it's the In-Sight D900's ability to run a new class of deep learning-based applications that makes it stand out.
Deep learning and easy application development
The In-Sight D900 is based on a familiar and easy-to-use spreadsheet interface, which simplifies application development and factory integration. Technical sales engineers have access to a full range of classic machine vision tools such as PatMax, edge probes and measurement tools. However, with In-Sight ViDi, the D900 consists of three deep learning tools which all target specific and widespread applications: ViDi Read, ViDi Check and ViDi Detect.
These new inspection tools help industrial automation customers easily solve applications that are too time-consuming or complex to deploy with traditional rule-based machine vision tools.
For all three application tools, the user can take advantage of In-Sight's intuitive spreadsheet interface, which enables rapid configuration of deep learning applications without programming. The In-Sight spreadsheet simplifies application development and factory integration with a comprehensive set of I / O and communication features. It also allows Cognex's classic rule-based vision tools (like PatMax Redline) to be combined with deep learning tools as part of a single task, speeding up deployments.
Because In-Sight ViDi requires much smaller image sets and shorter learning and validation times than other deep learning solutions, applications are quick and easy to configure, train, and deploy.
The In-Sight ViDi Read tool enables complex OCR applications to be solved in minutes. This module decrypts severely distorted and badly engraved codes using optical character recognition (OCR).
Ready to use, this tool reduces development times, thanks to a library of fonts preformed via deep learning. The user only needs to define the desired region and the character size. If new characters are introduced, this robust tool can be trained to read application-specific characters that cannot be decoded by conventional OCR tools. Compared to traditional vision systems without deep learning, this feature has obvious advantages.
The In-Sight D900 ViDi Check Tool enables manufacturers to perform quick and accurate verification of assemblies. This system is able to detect complex features and objects. It checks if parts and kits are assembled correctly based on their location within a user-defined layout. The tool can be trained to create a large library of components, which can be located in the image even if they appear from different angles or vary in size.
A third tool called ViDi Detect was designed to analyze complex fault detection tasks. He is able to learn from images of compliant parts in order to identify defective ones. In-Sight ViDi Detect is ideal for locating anomalies on complex parts and surfaces, even in situations where the defects may be seemingly unpredictable.
A new deal in visual inspections
Integrating deep learning-based In-Sight ViDi vision software with a smart camera helps industrial automation customers solve complex OCR, assembly verification, and fault detection applications that are often too difficult to deploy with traditional rule-based machine vision tools and demand reliable, fast and consistent results not achievable with human inspection.
With the introduction of this system, Cognex covers three application areas: optical character recognition (OCR), assembly verification and fault detection. While others should follow, these three areas open up a wide range of possible tasks that the new system can handle efficiently, with more precision than a conventional vision system. When it comes to markets, the In-Sight D900 can be used in multiple industries including automotive, consumer electronics, consumer goods, packaging, food, medical equipment, and logistics. .