Choosing the most appropriate combination of components needed for a machine vision system requires expert understanding of application requirements and technology capabilities. From this perspective in this month’s blog post we thought we would provide you with enough knowledge and understanding to have richer more rewarding conversations about machine vision and vision systems technology. This quick guide will help you understand the basics of machine vision and vision systems, including components, applications, return on investment and potential for use in your business.
The first thing to understand are the basic elements of a machine vision system. We’ve covered this before in this post, but it’s good to re-iterate it here. The basics of a machine vision system are as follows:
- The machine vision process starts with the part or product being inspected.
When the part is in the correct place, a sensor will trigger the acquisition of the digital image. - Structured lighting is used to ensure that the image captured is of optimum quality.
- The optical lens focuses the image onto the camera sensor.
- Depending on capabilities, this digitising sensor may perform some pre-processing to ensure the correct image features stand out
The image is then sent to the processor for analysis against the set of pre-programmed rules. - Communication devices are then used to report and trigger automatic events, such as part acceptance or rejection.
- What can machine vision be used for?
The applications for machine vision vary widely between industries and product environments. However, to aid understanding, they can be broken down into the following five major categories. As outlined previously, in the section on ‘processor’, these usually combine a number of algorithms and software tools to achieve the desired result.
1. Location, guidance & positioning
When combined with robotics, machine vision offers powerful application options. By accurately determining the position of parts to direct robots, find fiducials, align products and provide positional adjustment feedback, guided robots enable a flexible approach to feeding and product changes. This eliminates the need for costly precision fixtures, allowing different parts to be processed without changing tools. Some typical applications include:
- Locating and orientation of parts to compare them to specific tolerances
- Finding or aligning parts so that they are positioned correctly for assembly with other components
- Picking and placing parts from bins
- Packaging parts on a conveyor belt
- Reporting part positioning to a robot or machine controller to ensure correct alignment
2. Recognition, identification, coding & sorting
Using state-of-the-art neural network pattern recognition to recognize arbitrary patterns, shapes, features and logos, vision systems enable the comparison of trained features and patterns within fractions of a second. Geometric features are also used to find objects and easily identify models that are translated, rotated and scaled to sub-pixel accuracy. Typical applications include:
- Decoding 1D & 2D symbols, codes and characters printed on parts, labels, and packages.
- Direct Part Marking (DPM) a character, code or symbol onto a part or packaging
- Identifying parts by locating a unique pattern or based on colour, shape, or size.
- Optical character recognition (OCR) and optical character verification (OCV) systems read alphanumeric characters and confirms the presence of a character string.
3. Gauging & measuring
Measuring in machine vision is used to confirm the dimensional accuracy of components, parts and sub-assemblies automatically, without the need for manual intervention. A key benefit with machine vision is that it is non-contact and so does not contaminate or damage the part being inspected. Many machine vision systems can also measure object features to within 0.0254 millimetres and therefore provide additional benefits over the contact gauge equivalent.
4. Inspection, detection & verification
Inspection is used to detect and verify functional errors, defects, contaminants and other product irregularities.
Typical applications include:
- Verifying the presence/absence of parts or components
- Counting to confirm quantities
- Detecting flaws
- Conformance checking to inspect products for completeness.
5. Archiving & Tracking
Finally, machine vision can play an important role in archiving images and tracking parts and products through the whole production process. This can be particularly valuable in tracking the genealogy of parts in a sub-assembly that make up a finished product. Data recorded can be used to drive better customer support, improve production processes and protect brands against costly product recalls.
What are the benefits of machine vision?
The economic case for investing in machine vision systems is usually strong due to the two key following areas:
1. Cost savings through reducing labour, re-work/testing, removing more expensive capital expenditure, material and packaging costs and removing waste
2. Increased productivity through process improvements, greater flexibility, increased volume of parts produced, less downtime, errors and rejections
However, just viewing the benefits from an economic perspective does not do justice to the true value of your investment. Machine vision systems can add value in all the additional following ways. Unfortunately due to the intangible nature of some of these contributors it can be difficult to put an actual figure on the value but that shouldn’t stop attempts to include them.
- Intellectually
- By freeing staff from repetitive, boring tasks they are able to focus thinking in ways that add more value and contribute to increasing innovation. This is good for mental health and good for the business.
- By reducing customer complaints, product recalls and potential fines machine vision can help to build and protect your brand image in the minds of customers
- Building a strong image in the minds of potential business customers through demonstrating adoption of the latest technology, particularly when they come and visit your factory!
- Through the collection of better data and improved tracking, machine vision can help you develop a deeper understanding of your processes
- Physically
- The adoption of machine vision can help to complement and even improve health and safety practice
- Removing operators from hazardous environments or strenuous activity reduces exposure to sickness, absence, healthcare costs or insurance claims
- Culturally
- Machine vision can contribute and even accelerate a culture of continuous improvement and lean manufacturing
- Through increased competitiveness and improving service levels machine vision helps build a business your people can be proud of
- Environmentally
- Contributing to a positive, safe working environment for staff
- Through better use of energy and resources, smoother material flow and reduced waste machine vision systems can help reduce your impact on the environment
The costs of machine vision systems?
Costs can range from several hundred for smart sensors and cameras, up to half a million for complex systems. Of course this will depend on the size and scope of your operations and may be more or less.
However, even in the case of high levels of capital investment it should be obvious, from the potential benefits outlined above, that a machine vision system can quickly pay for itself.