Author Topic: Clear Tape Detection  (Read 3652 times)

0 Members and 2 Guests are viewing this topic.

Offline PBn

  • Newbie
  • Posts: 2
  • Country: us
Clear Tape Detection
« on: October 03, 2019, 09:09:02 pm »
I'm doing some industrial work and I am looking for some feedback and ideas.
 
The issue is some boxes are getting through without tape on the bottom, someone goes to lift them up and all the stuff falls out.

I am looking for a sensing solution that can detect clear packing tape on a variety of colored boxes.

It looks like there are some sensors for "gloss" detection
keyence CZ-H72 And the Sick OPR20G seem to be good options.

The Keyence seems to do some kind of fancy polarization measurement to determine how much of the light was reflected and how much was defused.

The Sick one simply illuminates the surface and a sensor determines how "Tight" the reflection is

However the painted craft paper boxes we use are very matte.

Looking over the details of how some of the fancy gloss sensors work they just reflect light off the surface at an angle


The steeper the angle the less defuse light will reflect to the photo-sensor.
It seems like one could just angle a tx and rx sensors so they bounce off the bottom of a box at 90° and that would produce a strong signal to noise ratio, perhaps some simple polarization.
It will take some tweaking to get the level right. But I suspect it would work well enough.


It may not be quite as nice as the 2000$ sensor solutions but we can deal with some false negatives.

Anyone have thoughts or other ideas?
 

Offline james_s

  • Super Contributor
  • ***
  • Posts: 16127
  • Country: us
Re: Clear Tape Detection
« Reply #1 on: October 03, 2019, 10:02:57 pm »
You could try viewing the tape and boxes under various wavelengths and see if the tape is dramatically more opaque or more/less reflective at certain wavelengths, particularly in the UV and IR range. You also might be able to detect gloss fairly easily by using a simple reflective sensor with an LED or laser diode and photodiode angled to one another. Or maybe you can try to mechanically sense the gap between the flaps, something like a piece of piano wire on a microswitch? The theory being that if the tape is applied the wire won't be able to spring up between the flaps.
 

Offline PBn

  • Newbie
  • Posts: 2
  • Country: us
Re: Clear Tape Detection
« Reply #2 on: October 03, 2019, 11:38:07 pm »
I thought of the light thing, the tape does faintly glow under uv but not substantially more than the dyes they use in the packaging.
It is kind of shocking to me they don't manufacture tape with UV dye in it for this very reason.

Unfortunately the tape webs across and can dip down and stick to the minor flap pretty easy.
Also the boxes are moving on rollers so it would be very hard to measure.
I don't think mechanical techniques will work very well.
The difference in the coefficient of friction between the tape and the cardboard is pretty high, but I can't think of a reliable way to measure that ether.

I'll try to work out a way to test if the tape looks different in near, ir maybe an old night vision camera or something.
 

Offline Marco

  • Super Contributor
  • ***
  • Posts: 5251
  • Country: nl
Re: Clear Tape Detection
« Reply #3 on: November 21, 2019, 01:44:46 pm »
The angled reflection seems worth a try, just bodge it up with a pot and a scope to see if it works.
« Last Edit: November 21, 2019, 01:48:40 pm by Marco »
 

Offline grifftech

  • Frequent Contributor
  • **
  • Posts: 369
  • Country: us
    • youtube channel
Re: Clear Tape Detection
« Reply #4 on: December 12, 2019, 06:38:28 pm »
different tape ;)
 
The following users thanked this post: cdev

Offline m98

  • Frequent Contributor
  • **
  • Posts: 483
  • Country: de
Re: Clear Tape Detection
« Reply #5 on: December 30, 2019, 08:59:48 pm »
You could use an arrangement of a soft light
source sharply limited across the whole detection length and a camera, both pointing up at the package. Then you can do some image processing, use a high pass filter somewhere, and you can detect wether there is a sharp line in the right orientation or not.
 

Online wraper

  • Supporter
  • ****
  • Posts: 13637
  • Country: lv
Re: Clear Tape Detection
« Reply #6 on: January 04, 2020, 05:24:23 pm »
Does it has to be new? You can get used sensor made specially for the task for about $200. And even new does not cost anywhere close to $2000

https://www.radwell.co.uk/Buy/WENGLOR/WENGLOR/GM04VC2?redirect=true
 

Online ebastler

  • Super Contributor
  • ***
  • Posts: 4009
  • Country: de
Re: Clear Tape Detection
« Reply #7 on: January 04, 2020, 07:48:27 pm »
The steeper the angle the less defuse light will reflect to the photo-sensor.
It seems like one could just angle a tx and rx sensors so they bounce off the bottom of a box at 90° and that would produce a strong signal to noise ratio, perhaps some simple polarization.
It will take some tweaking to get the level right. But I suspect it would work well enough.

I like the "how directed or diffuse is the reflection" approach. To make this robust, you should use one directed source of light (cheap laser pointer?), and at least two detectors (or use a line sensor for multiple detector elements?).

One detector should be arranged to capture the direct reflection (i.e. incident angle of light onto the box surface = exit angle from illuminated spot to the first detector). The other detector should be placed away from the direct reflection angle, but such that it captures enough of the diffuse scatter from a cardboard surface.

Then you calculate the ratio of intensities on detector 1 / detector 2. That ratio will be high for glossy (tape) surfaces, and low for matte (cardboard) surfaces. But it will be largely independent of the degree of overall reflectivity or absorption (i.e. the color) of the substrate.

You could get fancier with a line sensor which covers a range of scattering angles. This might be needed if you deal with multiple different materials and want to distinguish them. But for the simple "glossy tape or cardboard" classification, two detectors should do, I think.
 

Offline Doctorandus_P

  • Super Contributor
  • ***
  • Posts: 1728
  • Country: nl
Re: Clear Tape Detection
« Reply #8 on: January 07, 2020, 07:01:07 pm »
I assume the boxes are moved over an conveyor belt of somse sort.
Is the tape parallel to the conveyor belt, or square to it (What's the word?)

I would not rely on a single sensor, but would do at least 2 measurements and compare those.
One measures a base level of reflection on an area there should not be tape, and another measurement which measures the reflection level of the tape.

If the tape is longitudinal (parallel) to the conveyor belt this would need 2 sensors, but if the tape is at a 90degree angle to the conveyor belt, you can measure refelctivity of both and even measure the width of the tape (assume constant speed of the belt ?)

So if you have your sensor output "change" for a time comparable with the widht of the tape, you have a big chance it's really tape you have just measured.

Also, stuff like reflectivity & transparancy is wavelength dependent. Some time ago I saw a few pictures made with an IR camara of a sowing machine, which had a black rubber timingbelt in it. On the IR photograph, the rubber of the timing belt was almost invisible. You could see right through it, but the strengthening wires in the timingbelt were pitch black.

You could make something with fast blinking laser pointer and a photo diode in a tube.
The tube shields from most of the ambient light, and the blinking of the laser pointer (a few kHz) can also be used to distinguish from other light sources.

Some problems with this approach are with non-uniform color of the box (dirty patches, labels, etc)

A completely other approach is not to detect the tape itself, but the tape dispenser. Put some rotation sensor (encoder) on the roll of tape itself (or with a friction wheel, etc). If a box passes the tape dispenser, and no tape is dispenced, you have a box without tape.
More accurate: Measure the length of tape dispensed, so it also detects if a box is only half taped.
 

Offline GerryR

  • Regular Contributor
  • *
  • Posts: 216
  • Country: us
Re: Clear Tape Detection
« Reply #9 on: February 01, 2020, 10:20:54 pm »
My recommendation would be to get in touch with your local Keyence rep and have them suggest the proper sensor for that application.  I had a situation where I was trying to detect black objects, and they came out with a few different sensors, and we found the sensor that would consistently detect them.  They don't charge for this service and for the many (many) years that I've been doing automation work, Keyence has been my favorite company for difficult sensor solutions, and I have no other affiliation with them other than being a user.
Still learning; good judgment comes from experience, which comes from bad judgment!!
 

Offline TopLoser

  • Supporter
  • ****
  • Posts: 1914
  • Country: fr
Re: Clear Tape Detection
« Reply #10 on: February 02, 2020, 09:10:39 am »
Just go the simple route and get a cheap Sick glare/gloss sensor from eBay (or buy one new, they’re not that expensive). They just ‘work’ detecting transparent gloss tape and banding.

Steer clear of Keyence, their sales engineers are trained primarily in high pressure sales. You’ll get endless phone calls and emails from them about other stuff they sell as well as almost daily calls trying to get an order from you. Can’t tell you how many Birmingham numbers I’ve blocked on my phone... Never yet met one of their engineers that seems familiar with industrial environments either, nice suits though...
 
The following users thanked this post: analogueAdder

Offline GerryR

  • Regular Contributor
  • *
  • Posts: 216
  • Country: us
Re: Clear Tape Detection
« Reply #11 on: February 02, 2020, 12:14:31 pm »
.............

Steer clear of Keyence, their sales engineers are trained primarily in high pressure sales. You’ll get endless phone calls and emails from them about other stuff they sell as well as almost daily calls trying to get an order from you. Can’t tell you how many Birmingham numbers I’ve blocked on my phone... Never yet met one of their engineers that seems familiar with industrial environments either, nice suits though...


I haven't had that experience with Keyence.  I find them to be very knowledgeable and helpful, and their products work and are reliable.  I've been using Keyence products for over 25 years, though not exclusively; sorry you have had that experience.
Still learning; good judgment comes from experience, which comes from bad judgment!!
 

Offline Rohodyer

  • Newbie
  • Posts: 1
  • Country: us
Re: Clear Tape Detection
« Reply #12 on: June 06, 2021, 01:55:19 pm »
.............

Steer clear of Keyence, their sales engineers are trained primarily in high pressure sales. You’ll get endless phone calls and emails from them about other stuff they sell as well as almost daily calls trying to get an order from you. Can’t tell you how many Birmingham numbers I’ve blocked on my phone... Never yet met one of their engineers that seems familiar with industrial environments either, nice suits though...


I haven't had that experience with Keyence.  I find them to be very knowledgeable and helpful, and their products work and are reliable.  I've been using Keyence products for over 25 years, though not exclusively; sorry you have had that experience.

I've had somewhat the same experiences with Keyence.  I had to put the smackdown on my primary Keyence salesman when he started calling me on weekends.  Then I held his feet to the fire on pricing and now he matches Automation Direct on sensors and light curtains.  They make a new safety controller that I absolutely love as well!  Great products if you can get the salesmen to behave.
 

Offline BeBuLamar

  • Regular Contributor
  • *
  • Posts: 169
  • Country: us
Re: Clear Tape Detection
« Reply #13 on: June 07, 2021, 12:28:18 pm »
Spend the money and use the Keyence. For gloss the detection that's the way to do it, comparing diffused reflection vs specular reflection, However, I would still try to find out a different way than gloss detection.
Oh yeah I often get Keyence to drop their initial price in half. I am not comparing to Automation Direct because really no other manufacturers have the kind of sensors they do. I just say that my company can't afford Keyence.
« Last Edit: June 07, 2021, 12:33:42 pm by BeBuLamar »
 

Offline BeBuLamar

  • Regular Contributor
  • *
  • Posts: 169
  • Country: us
Re: Clear Tape Detection
« Reply #14 on: June 07, 2021, 12:42:04 pm »
If your cardboard is always the same color then the higher gloss of the tape will result in higher reading. If you have different color boxes then you would need a sensor aiming straight on to the box to measure diffuse reflection. Subtract this from the reading of the angle sensor to get the gloss.
 

Offline DrG

  • Super Contributor
  • ***
  • Posts: 1034
  • Country: us
Re: Clear Tape Detection
« Reply #15 on: June 07, 2021, 01:40:38 pm »
Interesting challenge and solution discussion. Not sure I have much to add....

I was looking at this video and it is impressive. In a practical sense, the commercial sensors may be the way to go although adapting it to your set up could be challenging.


But using one is no fun (for me) and thinking about alternatives is more interesting.

What about three (it could be done with two) still cameras images taken from a fixed location and each with a matched light source.  The positions are the center of where the tape should be and two positions on the periphery where the cardboard should be. A quick analysis of the "glare" (i.e., brightness) of the photos might identify tape vs. no tape quite accurately, and relatively cheaply. Maybe two or three image sensors in lieu of cameras... and if the comparative difference is large enough, simpler light sensors could be tried, but always measuring a delta between two (or three) sensors.
- Invest in science - it pays big dividends. -
 

Offline BeBuLamar

  • Regular Contributor
  • *
  • Posts: 169
  • Country: us
Re: Clear Tape Detection
« Reply #16 on: June 07, 2021, 05:51:11 pm »
In the video they use the thru beam method which is not possible in the OP case. You can put a reflector on the other side of the tape once you tape the box.
 

Offline evb149

  • Super Contributor
  • ***
  • Posts: 1924
  • Country: us
Re: Clear Tape Detection
« Reply #17 on: June 08, 2021, 07:09:52 am »
Sounds like the problem has a solution with the aforementioned COTS sensors.

But to solve it if you were trying to invent a solution other than buying / integrating the purpose made options I'd consider:

1: Machine vision on the sides and / or bottom of the package with appropriate lighting and looking for the pattern of the differing gloss or the variance in appearance of the edges vs. the taped middle zone vs. the untaped perihpery zone.  If a human under non-optimum lighting conditions can look at the package from a modest distance (e.g. several meters / a few feet) and easily at a glance be able to reliably see that the package is taped or not then the taping must be distinctive enough in appearance vs. the package that a simple machine vision image processing solution can probably get the right result from either feature extraction or ML.

2: The gloss / reflectivity / polarization options as aforementioned using either a 2D image sensor with controlled lighting or possibly just a 1D / 2D sensor or something like a barcode scanner approach with a point / line light source and some photo receivers.

3: I didn't see anyone mention thickness gague or dielectric or sonic based approaches.  Even though tape is thin it usually has a very prominent steep edge to it which is easily felt as an abrupt height variation over a short distance on the surface no matter how invisible the tape may be in optical contrast.  So therefore it is possible you might have some ultrasound or mechanical "feeler" or optical or capacitive range measurement based options that could pick up the change in distance profile / thickness / dielectric constant / sonic reflectivity over the distance.

Another simpler option which might facilitate a machine vision or scanner based solution -- you asked about clear tape, but perhaps it'd be possible to
consider just not using completely clear tape?

You can order printed tape which is either opaque or clear otherwise e.g.:
https://www.uline.com/CustomProduct/CustomStaticTapeSplash.htm

Or you could use plain opaque tape with some differing color than the box.

If the machine vision had something easy to look for like a prominent color difference or a pattern of printing (e.g. logo, bar code, whatever) then that would make the taped status easier to determine than almost invisible clear tape.

 

Offline tszaboo

  • Super Contributor
  • ***
  • Posts: 5618
  • Country: nl
  • Current job: ATEX certified product design
Re: Clear Tape Detection
« Reply #18 on: June 08, 2021, 01:39:05 pm »
Anyone have thoughts or other ideas?
Replace clear tape with brown tape.
Former username: NANDBlog
 

Online fcb

  • Super Contributor
  • ***
  • Posts: 2049
  • Country: gb
  • Test instrument designer/G1YWC
    • Electron Plus
Re: Clear Tape Detection
« Reply #19 on: June 08, 2021, 01:49:32 pm »
Have you checked to see what it looks like under UV.  I'm constantly surprised by what glows and wot don't.
https://electron.plus Power Analysers, VI Signature Testers, Voltage References, Picoammeters, Curve Tracers.
 


Share me

Digg  Facebook  SlashDot  Delicious  Technorati  Twitter  Google  Yahoo
Smf