ASK THE EXPERTS
More Answers From Tom Brennan
I have a number brand new LED machine vision lights that I would need to sell. I have numerous ring lights (including dark field), spot lights, Light lines, coaxial, and diffuse dome illuminators. I would prefer to sell the whole lot for a bargain price. Does anyone have a suggestion as to who might be interested or where I might be able to sell them?
Carl, We're always interested in expanding our machine vision lab. What do you have? Can you send pictures and a list? Thanks, Tom
I am in the textile business. I am looking for some type of vison that can help me identify the corners of products, that are all white. Any thoughts would be greatly appreciated. -Jeff
Jeff - What flexibility would we have to change the background? We could also do something with a 3-D triangulation if needed. Feel free to send me an email or give me a call and happy to talk through the application.
Looking for a Vision system capable of defect inspection, Overall part inspection, and part present inspection. This will be in a foundry with Kuka robots in the cell. Also this will be sending the information to the Allen Bradly PLC and the MAIN HMI. Thank You I appreciate any feedback
Stuart - You could design a system to do this with many different brands of smart camera or a PC based system with regular cameras. Your options would be to buy hardware and do it yourself or hire a system integrator to design, build, integrate and test a solution and deliver it to you turnkey. Our company or another system integrator would be able to offer you the latter. If there's a vision engineer in house you could definitely pursue the former. Feel free to get in touch if we can be of any assistance.
I am brand new to this site. I have a need for some type of vision that can identify the edges of textiles (mostly all white) such as sheets, towels, Wash Clothes, etc. I would envision two types of robotic arms that would be able to fine (grab) the two ends on a side, not opposite ends, and spread them out. I understand that the vison may now be able to identify white textile. Any help or a company that may have the vison to do this would be greatly appreciated. Thanks Jeff Nichols
Jeff - I would second David's recommendations. Choosing a certified integrator is always a good choice. I would also add that as you consider integration companies, make sure to ship samples of the different textiles and different sizes. Most integration companies will have a lab, and be willing to take a preliminary look at the application free of charge assuming there's a budgetary fit to solve the problem. Sometimes if there's doubt about a particular aspect of the project, a feasibility study might be necessary to mitigate risk on both sides and make sure you get the best solution at the end of the project. First step would be two or three calls and getting some samples in the hands of a company or two. If we can be of assistance feel free to reach out either to me or our North Carolina sales office.
We are producing refrigerant, and we would like to make a visual inspection at the end of the process, so we are searching for a proper light color or intensity.
Deniz, Happy to talk through that with you. What's driving the requirement to control color and intensity? Is it so people don't perceive there to be a difference? or is color and intensity correlated with a concentration of a particular chemical you are looking to control? The first approach leads us down a road of full spectrum illumination and computing delta E (human perceptible differences in color), and the second is more spectroscopy and trying to take a chemical measurement via photonics. In that latter approach we might use only one specific wavelength of light to measure just the targeted response that interests us. Either is possible with vision, and the approach will largely depend on the end goal you are looking to achieve. Tom
Hello, I have a GigE camera from THE IMAGING SOURCE and I need to build a program in c++ in Linux that can communicate with the camera, change settings ( iris and exposure time ), capture an image and saving it to a specific place. Firstly I need one library to do my job and secondly I will need some help building the program.
Marios, This is something we could write for you. We've built a handful of custom camera viewer applications for other customers. We also have a GigE vision viewer we've built. We've not used it with Imaging Source GigE cameras but as it's a common standard it should work equally well. Tom
I am looking for a camera or video system that can be displayed to a Monitor. I would like to have a bulls eye or some sort of target system to be displayed on the monitor that can zoom in or out to focus. The purpose is to put a small pin through a hole. Thank you.
Bill, I think it depends on to what extent you want a DIY project. If you buy a camera from a vendor with a basic SDK they'll likely have video viewer sample code. I know Basler and the Imaging Source do. To implement zooming and draw the target I'd do it in software. You can stitch in an external library to your application and leverage that code. I'd suggest OpenCV or Emgu CV (an OpenCV wrapper) to do that heavy lifting. You could build it yourself or you could hire us (or someone else) to do it. For basic zooming and a target, it'd take a software guy about 5 days to put together in C++ or C#. You'd likely want to modify and rebuild OpenCV or Emgu CV to always put your target in the middle of your zoomed image. You could also buy something more off the shelf like John suggests below and set that up. I really don't know if the exact product you want exists though. If it's a fixed station you need something by Scienscope could work.
Most examples I have seen for use of vision systems in inspections are for repetitive manufacturing operations or first piece inspections. Are vision systems capable of being used to verify mixed parts of multiple types and configurations at a rate of multiple parts per minute? Specifically trying to identify and qualify the components yielded from disassembling complete goods for remanufacture. So challenges are that the part being examined may have wear or damage, but we still need to be able distinguish which part it is and whether it should be re-used.
Duane, That is possible. The system would need to be programmed to recognize a critical feature on each part, and then perform a set of inspections based on which critical feature was found. I don't know exactly what parts you have, however let's say you had gaskets of various sizes you wanted to check for cracks, and couplings you wanted to check for wear and cracks and fuel valve assemblies you wanted to check for completeness. A system could be programmed to recognize certain gaskets and look for edges and irregularities (cracks), recognize certain couplings and measure wear (thickness) and recognize a fuel valve assembly and check each component was in the proper place. One place you may run into issues is scaling this up as each part and the corresponding inspection(s) would have to be programmed separately. How many different potential parts are you talking about? Feel free to call or email.
Would like to know if vision based inspection is feasible for large parts and assemblies like axles of a truck. What we are looking to inspect is the "toe" of the stub axles as theses come out of the assembly line. "Toe" is the relative inclination to each other. These stub axles are pivoted at either ends of the main axle and tied to a bar by means of a threaded rod and nut assembly. If you may please let us know, we would appreciate your help. Thank you.
Sanaulla, It sounds like the overall assembly is large but there are two smaller areas of interest. If this is the case your best solution is likely a two camera system. One camera aimed at one "toe" and other at the other "toe". A vision inspection running on a nearby computer would analyze both images and output the difference in the two alignments along with whatever else you needed. That said, we'd need to see pictures of the toe, the alignment to be measured and have some idea of the precision you need. Let me know if we can help you out. In general large assemblies aren't a problem, it's the size of the "area of interest" relative to the defect that matters most. If there are multiple areas of interest far apart from each other a multi camera system is likely best. Tom
Hello, I am looking for way to photo id different anode blocks. In identifying the blocks, I also need a way to Quality control the anode blocks (detect them for cracking, discoloration, and spalling). I am not very well versed in this field so any advice would be greatly appreciated.
Greg, If there are more than two or three types of blocks the easiest way to ID the blocks is going to be by adding a barcode or datamatrix to the blocks (if that's possible). This will also give you downstream serialization and traceability. Pattern matching and Identification via vision can get finicky when there's a lot of variety. Do you have any pictures of these blocks you can share as far as the other defects? Depending on the pictures I would recommend shipping samples to 1-2 integrators for some testing and take things from there.
Hello Vision Experts, I am looking for a very professional System Integrator for visual inspection of integrated circuits. Which System Integrator in the US do you recommend? Thank you in advance.
David, AIA offers professional certifications to integrators. I would select someone who has received an advanced certification and ask for customer references. We'd hope you'd select us, but anyone on the list of Advanced integrators can help you. Tom
I am looking for a vision inspection system that could be mounted outdoors (on bridges for example) looking at the surface of a flowing water body to measure invasive plant fragments that are flowing by the camera. The measurement does not have to be absolute quantity, but some relative measurement of the "flux" of fragments in the frame. This is for use in measuring the effects of invasive plants infestations flowing from streams into lake water bodies. Do you have any recommendations for a vision inspection system?
Mike, Are there other types of green plant matter flowing through and the system needs to distinguish invasive from non-invasive? Alternatively can the system detect green matter and apply a rule of thumb for how much is likely invasive?
I am looking for a system that would inventory similar wooden products and identify them according to distinguishing features - such as wood grain. Any products out there that would work on this scale?
Jana, How many different products are to be identified? Would the device need to be handheld or are these products in board form on a conveyor? We'd be happy to talk through a solution directly. I'm not aware of an off the shelf product. Tom
I am a concrete construction quality professional active in many industry associations, but I know very little about image capture and analysis. I am looking for a combination of hardware and software to measure voids in concrete surfaces after the formwork is removed. Our industry currently has only subjective measurement of surface to void ratios and color uniformity; both important aesthetic attributes. I would like to build a device to capture images under controlled lighting and reflectance, and then use software to determine void / surface ratio and color uniformity. Several white papers have been written on this subject using Matlab or ImageJ for analysis of greyscale images, but the devil appears to be in the details - controlling variables.
John - This sounds like an interesting problem that would likely need an engineered solution. Would the end goal to be to get to a handheld unit an operator could use in field or would this unit analyze specimens taken to a lab. To do accurate color analysis we'll want to use full spectrum white light. For the voids a low angle of light could be best as that's typically used to pick up scratches, dents and other non-uniformities in surfaces. We'd probably also need to come up with a calibration to make sure we're providing consistent readings over time. Happy to discuss further. These are always interesting problems to talk through. Send me an email or call at 303-832-1111x101.
I am looking for a low cost solution to sort golf balls by make and model. We intend to use OCR as part of this solution. Since most ball manufacturers use alpha/numeric model numbers and logos. The challenge is getting the right orientation of text and logo for reading. Is it possible to read in multiple orientation?
Chris, We've looked at something similar in the past. It never moved forward as there were a few issues that drove the costs up: Variety: 29 types of Titleist balls alone. Many other brands as well with many ball types. Ball Condition: A lot of these balls were recovered from ranges / courses and being sorted for resale so they weren't in mint condition. Portions of the logos could be scraped off. Other Logos: Many balls are given away with tournament logos, corporate sponsor logos, etc. as well as marks people put on them so there are many features added that we don't want to sort on. We'd be happy to assist. We spent a lot of time studying the problem last time free of charge. From that prior effort I don't think there's a cheap way to solve it, but simplifying assumptions could be made to reduce the cost.
Which machine vision systems can be used to affordably accomplish these two objectives: a) Simply detect the presence of a car within a defined space b) Determine the exact location and 3D dimension (length, width, and height) of the car within that space. Bear in mind that is objective b) the solution must detect small projections from the car such as trailer hitches off the back, mirrors off the sides, and roof racks & antennae off the roof. The distance may be from as far as 12' away and it is certainly possible to use multiple cameras to view the car from multiple angles. The solution would need to communicate with a PLC system. We currently use lasers, but they are expensive, so I am wondering if cameras would be more affordable and equally reliable.
Woody - If your primary interest is in finding maximum dimensions in each axis a system that silhouetted the vehicle from different angles could work. If you have the vehicle in motion in one axis this could actually work like a scanner. The vehicle would simply pass through a tunnel that took dimensions via scanning a silhouette. Anyway, just some thoughts, happy to talk through the problem at your convenience.