More applications. More opportunities.

High-speed cameras, sometimes known as troubleshooting cameras, in industrial applications are used mainly to troubleshoot high-speed events and machinery where speeds are such that the human eye can't see what's happening. The fastest high-speed cameras tend to have image memory inside the unit enabling them to record up to 10,000 frames per second. A camera for video troubleshooting applications not only needs speed but needs specialist triggering modes. It's important in some applications to know the cause of the triggered event so pre-event recording is common in high-speed cameras which capture continuously and when the event happens data from both before and after is stored. Another key feature in troubleshooting cameras is the ability to self-trigger through the lens. This feature monitors a small region of the image for a change and when this happens makes a trigger point. The resultant image sequence includes images before and after the trigger region changes. Modern high-speed troubleshooting cameras are normally controlled via a laptop which makes them portable and provides the ability to store and play back videos using standard technology.

One challenge with very high-speed cameras is light. With very short exposures a lot of light is needed to get good quality images. Many of the providers also have a good solution for lighting to address many applications.

High-speed cameras without memory also exist but these are generally integrated into PC systems where the image data is recorded into PC memory rather than the camera memory. The limit here is the interface speed which tends to typically be ten times slower than cameras with inbuilt memory. These systems tend to be used less in troubleshooting applications rather than in high-speed inspection applications.

Industrial robots have been around for over 50 years with the first officially recognised device being created in 1954. It wasn’t until 1960 though that the first robot company was formed and of course, all robot guidance was by control systems with known coordinates whose accuracy was highly critical with any deviation in either product variation or position errors causing major headaches for the end customer. This state of affairs continued for some time - until at least 1983 when the first commercial vision systems became available.

Machine vision has had a long period of development since it became a viable technology and has been very widely deployed within many industries over time. Vision brings benefits to many sectors but robotics is one of the big winners for many reasons. One key point is the fact that it can be seen as an enabling technology in robot guidance. Robots are good at repetitive tasks but they cannot accommodate changing parameters, so when a location changes or a product is not where it is supposed to be, the robot system will fail.

Machine vision enables robots to ‘see’ an object and calculate its  X and Y position, with the robot picking arm. But it also enables the robot to ‘see’ the correct placing position. More recently, robot guidance has evolved with 3D machine vision. So a third coordinate is also available, typically the height of an object.

There is a steadily increasing range of smart cameras to add to the list of established image sensors and software packages, there are robot guidance systems for any application. With the advent of low-cost multi-core processors, more can be done.

3D imaging has opened up a host of opportunities for the manufacturing industry. The ability to make real-time measurements in the X, Y and Z axes at production line speeds not only allows volumes of product to be calculated and defects to be detected but also pass/fail decisions to be made on far more parameters than would be possible for traditional 2D measurements. 3D imaging provides automated inspection solutions for both simple and complex objects and gives the user all of the traditional benefits associated with 2D inspection, such as reduced reliance on manpower for quality control; availability of live production data for monitoring systems; improved consistency of product; increased throughput and reduced wastage, as well as 100% inspection. Decisions can be made on product shape, proportions and even surface quality (indentations scratches, dents etc). The use of 3D matching tools enables 3D models to be compared to a known 3D or ‘golden’ template for product verification.

Not surprisingly, 3D inspection has applications in industries as diverse as food and beverage, pharmaceutical, automotive, packaging, electronics, transport, logistics and many more. In the food industry, 3D measurements have been utilised for applications, such as portion control and potato sorting by shape. They have also been used extensively in the baking industry on products  such as pizza, pies, bread, pastries , cakes and biscuits to check for shape, size, edge defects and thickness, for example.

Assembly verification, especially of metal or plastic parts is critical in many industries, especially in the automotive industry. For example, checking the height of components can be used to verify assemblies such as bearings, and 3D matching can confirm the surface integrity of parts. In final vehicle assembly, making gap and flush measurements on automotive panels allows correction and even rejection of the vehicle if the panels are badly mis-aligned.

In the pharmaceutical industry, 3D inspection can be used to detect shape defects in tablets including chips as well as reading embossed details on the tablet. Tablets can be checked in blister packs, with the 3D offering benefits for low contrast imaging to recognise grey products in aluminium foil as well as detecting deformations and tablet fragments. Height measurement allows the detection of tablet capping and upright tablets.

There are a host of applications for 3D inspection in general packaging applications from measuring the height of items in the packaging before it is closed to make sure that it is not too high, to checking that final packages are properly closed, with no flaps sticking out, or dents in the packaging. Rims of containers that will have foil lids applied can be checked for defects in the surface that would affect seal integrity.

Automation is a key factor in improving productivity and competitiveness in world markets and the use of 3D vision to guide robots (pick and place) is key in maximising this competitiveness, particularly in the automotive and pharmaceutical industries, where 100% inspection is critical. Using 3D robot vision to pick unordered parts enables manufacturers to save a lot of time and resources shiſting or organising parts in the manufacturing process or feeding robots and machines with parts.

The challenge lies in acquiring images in 3D, building a mathematical model, analysing the position of something in 3D space and then transmitting 3D picking coordinates to a robot, all in just a few seconds to meet the cycle time of the robot and avoid it having to wait for the next set of coordinates. Fortunately, complex 3D images do not necessarily have to be created to achieve this feat. It is possible to do this using stereo vision imaging techniques, where features are extracted from 2D images that are calibrated in 3D.

As a rule of thumb, if there are a minimum of four recognisable features on an object, it is possible to create 3D measurements of the object and therefore generate the X, Y and Z coordinates of any part of the object, with a level of accuracy that allows the robot to grip it without causing any damage. If, however, there are not enough features, or no features at all that can be used for the 3D calibration, features can be ‘created’ using laser lines or dots to illuminate the area.

A good example of this is the 3D de-palletising of sacks, which could contain anything from concrete to grain or tea. As the sacks are rather featureless, the whole pallet is illuminated with lasers and the laser lines are located in 2D images. The sacks are also recognised in the 2D images and all the information is combined to get 3D picking data - all well within the cycle time of the robot. So most of the work is done in 2D, with far fewer pixels to process, yet a high level of accuracy is maintained due to the lens and camera calibration that can achieve sub-pixel measurements.

UKIVA members can offer further advice on the different camera formats and technology.

Product defects

Inspection of products for defects is an important aspect of high-speed inspection applications, The key areas are verification, measurement and flaw detection. Verification ensures that a product, assembly or package has been correctly produced. Applications range from simple presence checks such as ensuring that all the caps are in place on a bottling line or components such as clips, screws, springs, and parts are in place, to checking that seals and tamperproof bands are in the correct position and that no product has been trapped in a packaging seal. Other verification examples include solder joints, moulded parts, assembly and blister packs. The accurate measurement of component dimensions to ensure that they are within pre-defined manufacturing tolerances is also extremely important, both from the point of quality control for the end-user and from the point of monitoring the manufacturing process to keep it within tolerance and therefore minimise waste. Products or components also need to be inspected for flaws such as contamination, scratches, cracks, discolouration , textural changes etc.

Labels and marking

Mislabelled products account for the highest percentage of recalls across all industries. Vision systems are also used extensively to check labels. Code reading tasks can include fully validated character recognition, character verification and robust 2D data matrix handling and grading. Code verification systems can help eliminate variables that affect the readability of a code and confirm that the printing is good from the start. Reading tasks could include simultaneously detecting changing batch code orientation and differing quantities and locations of characters on a label. Vision is also closely involved in the implementation of the 2011 EU Falsified Medicines Directive which requires manufacturers to apply safety features to verify the authenticity and identity of individual packs of medication rather than just batches. Vision systems are also used for code reading of directly marked components for product identification and traceability, especially in safety-critical industries such as aerospace and automotive. Tracking a component and all the processes it has gone through, from manufacturing and assembly right through to end-user requirements for spare parts replacement (from the cradle to the grave) helps compliance with industry guidelines and standards and quality assurance used in the manufacturing supply chain.

Web inspection

High-speed line scan imaging is used extensively for industrial web inspection applications on fast moving continuous product in a variety of industries including printing, the manufacture and subsequent processing of paper, the manufacture of steel plate, glass tape or textiles. Applications generally involve the identification and classification of faults and defects in these materials. In the food and packaging industry high-speed inspection systems have been developed to inspect laser-perforated holes in flexible modified atmosphere packaging films. The vision system can locate and measure hole sizes ranging from 30 – 120 μm diameter (approximately the diameter of a human hair) on a web running at a speed of 350m/min.

High-speed vision systems can significantly improve the accuracy of diagnostic analysis and maintenance operations in industrial manufacturing applications. Users can record and review a high-speed sequence, either frame by frame or using slow-motion playback to allow perfect machine setup and system synchronisation. Alternatively, the system can be used as a 'watchdog' by continuously monitoring a process and waiting for a pre-defined image trigger to occur. These troubleshooting systems are generally portable and can be used in a wide range of manufacturing applications including bottling lines, packaging manufacture, food production lines, plastic container manufacture, pharmaceutical packaging, component manufacturing, paper manufacture and printing.

Troubleshooting applications can require short exposure times so high-intensity illumination is required. Camera frame rates of thousands of frames/second generate a lot of data at high speed, especially if they have high spatial resolution. Rather than try to transfer this data to a PC, in-built highspeed ring buffers may be used for image recording. Image sequences can be replayed in slow motion on self-contained image displays after the event has been recorded or transferred to the hard disk of a PC for later review. Image sequences can be recorded in standard video file format.

Specialist triggering is used for troubleshooting because generally, it is important to see what is happening both before and after  the trigger event. The system continuously records into a ring buffer and once full, the system starts overwriting the first records. Once a trigger event has occurred, the system records until the ring buffer is filled up and stops. In this way, both pre-and post-event recording information is acquired. Sequences can also be triggered by monitoring either changes in intensity or movement in the image, meaning that the camera triggers itself to send an image or sequence, removing the need to generate a trigger using hardware. This is particularly useful for capturing intermittent or random events.

Web materials

Line scan imaging is used in continuous web inspection systems to perform 100% inspection to detect defects such as dirt, debris, pinholes, roll-marks, holes cracks, tears and scratches on materials such as paper, foils, films, nonwovens, metals etc. Web inspection is possible for web materials with a uniform or textured, glossy or matte surface or transparent materials. It is generally carried out on wide rolls of material (for example some 8m wide) and at high speeds so it is frequently necessary to use multiple line scan cameras to cover the entire width. Depending on the particular material, incident or transmitted illumination can be used. Defect classification is based on size range and contrast type – for example a contaminant may show up dark and a hole bright in transmission. Typically defects down to around 50μm can be detected. Because the material is on a continuous roll, it is not possible to carry out an instant rejection system when a defect is detected. Instead, a roll map is produced which shows the defect type and location on the roll so that it can be identified and removed when the material is actually used.

Print

Numerous defects can occur during printing processes such as ink spot marks, embossing defects, mis-registered colours and colour variations. 100% print inspection on materials as varied as banknotes, and pharmaceutical and food packaging is a challenging application which frequently makes use of line scan cameras and software utilising the ‘golden template’ or an ’intelligent template’ model to compare the item under test with a standard image and measure the differences. Other applications include continuous verification and/or quality inspection of numbered print and inspection of symbols and labels on web, sheet or single documents, as well as inspection of security features by checking the presence, position and integrity of applied features such as foil and hologram devices and base paper inserts like security threads.

Curved surfaces

Line scan is an excellent way of imaging cylindrical components. A line scan camera records the same position across the whole cylinder and as the cylinder rotates an ‘unwrapped’ image of the entire surface is generated without the distortion that would result from imaging a curved surface with an area scan camera. This technique allows labels to be unwrapped, allowing the reading of codes and human-readable characters. It also allows the inspection of surfaces for defects such as pits, scratches, holes etc.

Sorting

Inspection systems equipped with line scan cameras can be used for sorting a large variety of objects, such as food, waste, mining products, mail, parcels, etc. Typically these objects are moving past a camera system on a conveyor. Line scan systems can also be used for sorting free-falling products such as rice, vegetables, postal, molten glass, steel, pharmaceutical products, rocks etc which cascade past one or more cameras like a curtain.

High-resolution imaging

Since the ‘length’ of the image produced by a line scan camera is determined by the number of lines recorded for each image, very high-resolution images can be produced. This is particularly useful for the inspection of a host of products including flat panel displays, solar panels, pcbs, silicon wafers etc.

UKIVA members can offer further advice on the different camera formats and technology.

Since machine vision can make simple or complex repetitive measurements accurately, at speed and objectively, it is used in a wide range of end-of-line inspections in a host of different industries.

Product conformity

This is perhaps the most traditional application where the final product must be inspected as part of the quality control procedure. Typically, this involves checking parameters such as shape, size, volume, geometry, surface finish, colour etc to ensure that the final product meets the required specifications. Products that fail the inspection will be rejected, and can be reworked depending on the application. The speed and accuracy offered by the latest vision technology mean that in many applications, 100% inspection can be carried out, and the quality of the final product can be controlled to demanding standards. Almost any product manufactured on a production line is a potential candidate for this type of inspection.

Package integrity

Ensuring that packaging is “right” is of paramount importance, ranging from consistency in colours and logo positioning to checking the integrity of packaging enclosures for product purity and shelf-life.

Typical applications include:

• Packaging defects e.g. rim damage on tins, straightness of bottle caps, presence of tamper-proof bands, correct application of foil seals
• Packaging contents checking e.g. fill levels, dimensional checking of end-of-line packaging to ensure inclusion of correct contents, positioning of product within packaging

Supermarkets, in particular, can impose stringent requirements on suppliers with regards to packaging appearance.

Consumer safety

Correct package labelling is critical for consumer safety, especially in the food, beverage, pharmaceutical and medical industries. Ingredients must be listed accurately, together with nutritional information. Omitting a warning that a product could contain nuts could be catastrophic for a consumer allergic to nuts. Inserting the wrong patient information in a medicine packet could be equally catastrophic. Other applications include checking the presence or absence of labels, character recognition and print verification. A huge array of products are tagged either by a stick-on label or by information printed directly onto the packaging, with information such as bar codes, lot details and best-before codes being the most common ones that need to be checked with total accuracy. Vision-based code readers and optical character recognition systems are an essential requirement, given the potential variables in the codes themselves.

These include

• Regularity of code or label orientation on the product or package
• Regularity of the codes or characters themselves
• Possible damage to the code
• Contrast between the code or characters and the background

It is not just enough to read these codes but also verify they have been printed to a quality that will allow for robust reading later in the supply chain.

Additional articles, Technology and Systems Integration will take a more in-depth look at line scan technologies and their applications.

UKIVA members can offer further advice regarding End of Line Inspection.