Download PDF version Contact company

High demands on products as well as high time and cost pressure are decisive competitive factors across all industries and sectors. Whether in the food or automotive industry quality, safety and speed are today more than ever before factors that determine the success of a company. Zero-defect production is the goal. But how can it be guaranteed that only flawless products leave the production line? How can faulty quality decisions, which lead to high costs, be avoided? In order to test this reliably, a wide variety of methods are used in quality assurance.

A visual inspection with the human eye is possible, but it is often error-prone and expensive: the eye tires and working time is costly. A mechanical test, on the other hand, is usually accompanied by complex calibration, i.e. setting up and adjusting all parameters of both software and hardware in order to detect every error. In addition, product or material changes require recalibration.

Furthermore, with the classic, rule-based approach, a programmer or image processor must program rules specifically for the system to explain to the system how to detect the errors. This is complex and with a very high variance of errors often a hardly solvable Herculean task. All this can cost disproportionately much time and money. In order to make quality inspection as efficient, simple, reliable and cost-effective as possible, the German company sentin GmbH develops solutions that use deep learning and industrial cameras from IDS to enable fast and robust error detection. A sentin VISION system uses AI-based recognition software and can be trained using a few sample images. Together with a GigE Vision CMOS industrial camera from IDS and an evaluation unit, it can be easily embedded in existing processes.

Defect recognition software

The system is capable of segmenting objects, patterns and even defects. Even surfaces that are difficult to detect cannot stop the system. Classical applications can be found, for example, in the automotive industry (defect detection on metallic surfaces) or in the ceramics industry (defect detection by making dents visible on reflecting and mirroring surfaces), but also in the food industry (object and pattern recognition).

Depending on the application, the AI is trained to detect errors or anomalies. With the latter, the system learns to distinguish good from bad parts. If, for example, a surface structure is inspected, see metal part in the automotive industry or ceramic part, errors are detected by Artificial Intelligence as deviations from a comparison with reference images. By using anomaly detection and pre-trained models the system can detect defects based on just a few sample images of good parts.

The hardware setup required for the training and evaluation consists of an IDS industrial camera and appropriate lighting. The recognition models used are trained using reference images. For example, a system and AI model was configured for the error-prone inspection of fabric webs in the textile industry. A difficult task, as mistakes can be very subjective and very small. The system camera for optimum image material of textiles and web materials was selected together with IDS on the basis of specific customer requirements. A GigE Vision CMOS camera (GV-5880CP) was selected, which provides high-resolution data, triggered with precise timing, for accurate image evaluation.

IDS Vision CP camera

Slippage is the proportion of products that do not meet the standard but are overlooked

The system learns what constitutes a "good" fabric structure and knows already from a few shots of the fabric what a clean and flawless product looks like. For quality inspection, the image captured by the IDS Vision CP camera is then forwarded via GigE interface to an evaluation computer and processed with the recognition model. This computer can then reliably distinguish good/bad parts and highlight deviations. It gives an output signal when an error is found. In this way, slippage and pseudo rejects can be reduced quickly and easily.

Slippage is the proportion of products that do not meet the standard but are overlooked and therefore not sorted out, often leading to complaints. Pseudo rejects, on the other hand, are those products that meet the quality standard but are nevertheless incorrectly sorted out.

Both hardware and software of the system are flexible, for multiple or wider webs, additional cameras can easily be integrated into the setup. If necessary, the software also allows for re-training of the AI models. "Experience simply shows that a certain amount of night training is always necessary due to small individual circumstances. With pre-trained models from our portfolio, you need fewer reference images for individualisation and post training," explains Christian Els, CEO and co-founder of sentin.

GV-5880CP GigE Vision CMOS camera

Extremely accurate image acquisition and precise image evaluation are among the most important requirements for the camera used. Perfectly suitable is the GigE Vision CMOS camera GV-5880CP. The model has a 1/1.8" rolling shutter CMOS sensor Sony IMX178, which enables a very high resolution of 6.4 MP (3088 x 2076 px, aspect ratio 3:2). It delivers frame rates of up to 18 fps at full resolution and is therefore ideal for visualisation tasks in quality control. The sensor from the Sony STARVIS series features BSI technology (backside illumination) and is one of the most light-sensitive sensors with a low dark current close to the SCMOS range (Scientific CMOS). It ensures impressive results even under very low light conditions.

"In addition to resolution and frame rate, the interface and the price were decisive factors in the decision for the camera. The direct exchange with the IDS development department has helped us to reduce the time needed for camera integration," says Arkadius Gombos, Technical Manager at sentin. The integration into the sentin VISION system is done via GenTL and a Python interface.

Advantages of AI over human inspection or applications

The human brain is beaten by artificial intelligence in terms of consistency and reliability

Automated, image-based quality control with Artificial Intelligence offers many advantages over human visual inspection or conventional machine vision applications. "In AI-based image interpretation, the aim is to create images on which humans can see the error, because then the AI model can do it too," concludes Christian Els. The system learns to recognise the requirements of the product similar to a human being. But the human brain is beaten at any time by an artificial intelligence in terms of consistency and reliability.

Even if the brain is capable of remarkable peak performance, an AI can recognise much more complex error patterns. The human eye, on the other hand, cannot stand up to any camera in terms of fatigue and vision. In combination with deep-learning recognition software, the image processing system therefore enables particularly fast and accurate inspection. Depending on the application, image acquisition and evaluation can take place in just a few milliseconds.

Deep learning

The system can also be applied to other areas such as surface testing. Similar applications are e.g. the testing of matte metal/coatings surfaces (automotive interior), natural materials (stone, wood) or technical textiles such as leather. Scratches, cracks and other defects on consumer goods can thus be detected and the respective products sorted out. Exclude quality defects and produce only good stuff, an indispensable process within the framework of quality assurance.

IDS cameras in combination with the deep learning supported software of sentin GmbH significantly optimise the detection of defects and objects in quality control. This allows the personnel and time expenditure for complaints and rework, as well as pseudo rejects, to be significantly reduced in a wide range of industries and areas.

Share with LinkedIn Share with Twitter Share with Facebook Share with Facebook
Download PDF version Download PDF version

In case you missed it

How smart technology is simplifying safety and security in retirement villages
How smart technology is simplifying safety and security in retirement villages

James Twigg is the Managing Director of Total Integrated Solutions (TIS), an independent life safety, security and communication systems integrator, specialising in design & consultancy, technology and regulatory compliance. Total Integrated Solutions work primarily with retirement villages, helping to ensure the safety of residents in numerous retirement villages across the country. In this opinion piece, James shares how smart technology is helping security teams and care staff alike in ensuring the safety and security of their spaces, amid the COVID-19 pandemic and beyond. Impact of smart technology Smart technology is having an impact on pretty much every aspect of our lives Smart technology is having an impact on pretty much every aspect of our lives. From how we travel, to how we work, to how we run our homes. It’s not unusual to have Alexa waking us up and ordering our groceries or Nest to be regulating the temperature and energy in our homes. And while there’s a popular misconception that people in their later years are allergic to technology, retirement villages and care homes are experiencing significant innovation too. And the result is not only improved quality of life for residents, but also improved safety and security systems for management teams. Switching to converged IP systems I’ve been working in the life safety and security industry for over fifteen years. When I first joined TIS, much of the sector was still very analogue, in terms of the technology being installed and maintained. Slowly but surely, we’ve been consulting and advising customers on how to design, install and maintain converged IP systems that all talk to each other and work in tandem. I'm excited to say retirement villages are some of the top spaces leading the way, in terms of technological advancement. Improving the quality of life for residents A move into a retirement village can be daunting and one of the key concerns that we hear about is the loss of independence. No one wants to feel like they are being monitored or to have someone constantly hovering over them. One of the ways we’ve used smart technology to maintain residents' independence is through devices, such as health monitors and motion sensors. For example, instead of having a member of staff check-in on residents every morning, to ensure they are well, sensors and analytics can automatically detect changes in routine and alert staff to possible problems. Similarly, wearable tech, such as smart watches give residents a chance to let staff know they are okay, without having to tell them face-to-face. As our retirement village customers have told us, a simple ‘I’m okay’ command can be the difference between someone feeling independent versus someone feeling monitored. Simplifying and improving security systems Smart technology gives care staff and security oversight of the needs of residents For the teams responsible for the safety of the people, places and spaces within retirement villages, smart technology is helping to improve and simplify their jobs. Smart technology gives care staff and security oversight of the needs of residents, and ensures rapid response if notified by an emergency alert, ensuring they know the exact location of the resident in need. And without the need to go and physically check-in on every resident, staff and management can ensure staff time is being used effectively. Resources can be distributed where they are needed to ensure the safety and wellbeing of those residents who need extra consideration. 24/7 surveillance When planning the safety and security for retirement villages, and other residential spaces, it’s no use having traditional systems that only work effectively for 12 hours a day or need to update during the evening. Surveillance needs to be 24/7 and smart technology allows that without the physical intrusion into people’s spaces and daily lives. Smart technology ensures that systems speak to each other and are easily and effectively managed on one integrated system. This includes video surveillance, which has also become much more effective as a result of advanced video analytics, which automatically warn staff of suspicious behaviour. Securing spaces amid COVID-19 This year has, of course, brought new challenges for safety. COVID-19 hit the retirement and residential care sectors hard, first with the initial wave of infections in mid-2020 and then, with the subsequent loneliness caused by the necessary separation of families. As essential workers, we worked closely with our customers to make sure they had everything they needed As essential workers, we worked closely with our customers to make sure they had everything they needed during this time, equipping residents with tablet devices to ensure they could stay connected with their families and friends. It allowed residents to keep in touch without risking transferring the virus. Thermal cameras and mask detection And now that we’re emerging out of COVID-19 restrictions and most residents can see their families again, we’re installing systems like thermal cameras and mask detection, so as to ensure that security will be alerted to anyone in the space experiencing a high temperature or not wearing proper PPE. Such steps give staff and families alike, the peace-of-mind that operational teams will be alerted at the earliest possible moment, should a COVID-19 risk appear. Thinking ahead to the next fifteen years, I’m excited at the prospect of further technological advancements in this space. Because at the end of the day, it’s not about how complex your security system is or how you compete in the industry. It’s about helping teams to protect the people, spaces and places that matter. I see smart technology playing a huge role in that for years to come.

ASSA ABLOY’s Code Handle protects Fylab physiotherapy practice with secure PIN-operated handles
ASSA ABLOY’s Code Handle protects Fylab physiotherapy practice with secure PIN-operated handles

In all medical settings, people are coming and going all day. Therapists leave their personal belongings in changing rooms, patients want privacy in consulting rooms, open or unlocked doors can be an invitation to opportunists. Yet keeping track of mechanical keys can be a tiresome task for a small practice. There is a solution: the Code Handle PIN lock from ASSA ABLOY. In Irun, in Spain’s Basque country, Fylab sought easy electronic door security for their consulting rooms. These rooms house expensive specialist equipment for the various therapeutic disciplines offered by Fylab. Requirements were straightforward: a simple, secure, keyless access solution designed to work in a facility that gets a lot of daily traffic from professionals and the public. They needed a locking device that is easy to retrofit and incorporates a contemporary device design to match with Fylab’s modern medical workplace. Adding electronic security to room doors The Code Handle PIN-locking door handle added electronic security to three consulting-room doors at FylabThe Code Handle PIN-locking door handle added electronic security to three consulting-room doors at Fylab – without wires or cables. Two screws fit a Code Handle to almost any interior door (between 35mm to 80mm thick). One doesn’t even need to change their existing door cylinder. “I am no artist or handyman, but I managed to fit the handles within 10 minutes,” says Fylab founder, Borja Saldias Retegui. Code Handle adds electronic security to almost any interior door without disrupting its aesthetics. If one needs to secure a door facing a public space, Code Handle does it subtly and with zero hassle. At Fylab, Code Handle devices locks both wooden and glass doors, keeping equipment and therapists’ personal belongings safe. Allows up to 9 different PIN numbers “We like the solution a lot because we can do away with keys,” adds Borja. Code Handle removes the need to track cumbersome keys or install expensive access control. Because every Code Handle allows up to 9 different PIN numbers (4 to 6 digits), all authorised staff at Fylab can have their own security code. Two standard batteries (CR2) slot inside the handle, typically lasting 30,000 lock/unlock cycles before replacement The practice manager cancels or amends PINs at any time using the master PIN. Two standard batteries (CR2) slot inside the handle, typically lasting 30,000 lock/unlock cycles before replacement. It’s simple. “Code Handle is unique in comparison to common code door locks: it has the code function and battery incorporated inside its handle, so you don’t need to make extra modifications to your door,” explains Lars Angelin, Business Development Manager for Code Handle at ASSA ABLOY EMEA. Auto-locking feature of Code Handle Auto-locking is another helpful feature. When the door closes, Code Handle locks it automatically. One doesn’t need to put down whatever they are carrying, and no one can open it from the outside while they are not looking. To keep the door open briefly, one can simply hold Code Handle down for 5 seconds and it remains temporarily unlocked. For convenience, Code Handle always opens freely from the inside. “Code Handle provides the simplest solution for access control in a small facility,” says Borja. To learn more about Code Handle please visit: https://campaigns.assaabloyopeningsolutions.eu/codehandle

What are the challenges and benefits of mobile access control?
What are the challenges and benefits of mobile access control?

There is a broad appeal to the idea of using a smartphone or wearable device as a credential for physical access control systems. Smartphones already perform a range of tasks that extend beyond making a phone call. Shouldn’t opening the door at a workplace be among them? It’s a simple idea, but there are obstacles for the industry to get there from here. We asked this week’s Expert Panel Roundtable: What are the challenges and benefits of mobile access control solutions?