Is it possible to create a laser-scan card grading machine?
 

Looking for a serious discussion here. What would it take to create a machine that uses harmless lasers to scan, grade and seal trading cards? It seems as though it should be possible in this day and age. It could scan the front and back surfaces, edges, front and back centering and corners better than any human eye ever could. The human element should be taken out of TPGs and a machine like this would be game-breaking. Can it be done and how? Thoughts?

Like the automated strike zone, I am against it. There is a human element to card collecting and no card is the same regardless of what the number on the top might say. Quantifying a grade is good for convenience and establishing a market value but I no longer rely on it as much as I used to.

The machine would freak out trying to tell Mint from Gem Mint and blow itself up.

pretty sure someone on this board is/was in the process of creating such a business model.

Probably not with a laser, but a scanner and some software could do some of that fairly easily. Centering and size for sure, corners would be a bit more challenging. Edge quality more challenging, and picking up finer elements of the surfaces might be really tough.

As much as we complain about them, a bit of training maybe a week or so can get a motivated 20 something about 90% of the way there. And they're almost always going to be faster than the machine. Business wise that's an ok tradeoff compared to development costs plus a slower machine.

Changing the overall business model away from rushing things would be a much bigger improvement.

Steve B

John Henry, he drove fifteen feet
The steam drill only made nine

I am sure that if it was possible, PSA would have already used it and laid off all the humanoids. Dave Hall has plenty of money to devote to R&D (research & development).

Yep - I remember seeing that mentioned before.

It would have to be graded by both a human and a machine. I feel the machine will Also have errors.So maybe have the machine grade it and the person has no idea of the results. Then after the human inputs it's data the machine will also display.

In my hunt for a engagement ring for the wife. I heard that GIA has 15 people grade a diamond and a X-ray of sorts. Then they go with the lowest grade.

Then John Henry died. :eek:

Only after making his point. :D

And buying a baseball team :)

Hah. Not to mention a wife 40 or however many years younger.

I think you would just need a "mold" card, ie a gem mint original (common from the set) to scan and then program into the computer. The dimensions/centering should always be the same, allowing slight size/centering differences caused by different printing techniques. The scan would look for any imperfections and/or deformities in the surface paper/chrome/plastic, again allowing for slight, allowable imperfections. Then corners. I don't agree at all that these things should be left to subjective, human factors. This isn't a game. It's a grade. It either is or it isn't.

Frankly I don't see the point. Whatever algorithm determines where one grade stops and the next one starts is going to be subjective anyway. What do we care more about, centering or corners, etc. And some machine is going to inspect edges for trimming/filing?

Yes, it's possible.

Thousands upon thousands of under-graded and over-graded cards is the point. Human greed is the point. Fraud is the point. Favoritism is the point. Trust is the point. Do you trust the TPGs? I certainly don't. I would trust a computer's take on absolutes.

Grading is inherently subjective, or there is a subjective, eye appeal element anyhow and how various issues on any given card should be weighted is to me ultimately at least in part a matter of judgment.

http://www.kurzweilai.net/why-i-think-i-will-win

http://www.kurzweilai.net/a-wager-on...ink-i-will-win

while a perfect...robotic card grader sounds great in theory...I don't think there will be any major additions to the vast array(2-3) legitimate card graders in the hobby...ever!

MOst cards have been graded...who is going to incur the expense to grade them again. I just dont see it!

Well, maybe.

Let me give you a brief tour of just a few of the challenges you'll be up against.

Size - Until die cutting became the standard, there is some size variance on all cards. So while you can measure size accurately with existing technology, you still have to determine what the allowable tolerance is. Too much and people will get the impression you miss trimming. Too little and you'll turn customers off and get very little business.

Edge quality - A major challenge. And the biggest factor in spotting trimming. So for each set, the computer will have to know how it was cut. And while many modern cards are die cut, some have edges that appear crisp(1988 score), while others look more like a T206 with the beveling and ridge. (Most recent Gypsy Queen) Some cards in some sets have BOTH sorts of cuts. (Some but not all cards in the Gypsy queen set from I think 2014 or 2015 maybe others I'm too lazy to dig the box out. )

How do you treat cards that were perforated? Like 51 Topps. Are the little torn nibs counted as damage or a proper edge?

And even if the card looks good, can you scan it quickly at high resolution to see the tool marks that should be on each edge.
I have a hard time spotting them under 40X magnification, and they're not always obvious.

Surface - Under high magnification, cardstock isn't actually "smooth" Telling a spot where a fiber came out from a scratch isn't always easy. And seeing some stuff like that depends on the angle of the light. I don't know of an existing 3d scan technology with enough resolution to even detect a slight scratch.
And older cardboard sometimes has what are called "inclusions" or bits of stuff that got into the cardstock during manufacture. One of my T206s has a small but obvious inclusion, which I believe kept it from getting a high grade. The white spot is the area of the inclusion, and the raised are caused ink loss, but not paper loss. After some thought I figured the 40 was a fair grade. But that's a judgement call, as the inclusion has been there since before it was a card.
http://www.net54baseball.com/picture...pictureid=3031

Modern glossy cards have even more complications. Some gloss comes out very smooth, some doesn't. That slight difference is visible on cards from at least the 70's until now. (Some Topps from the 70's into early 80's have a gloss that yellows over time, some a re glossier, but I can't tell if it's smoother because there's more, or if the cardstock absorbed some or if the actual gloss is different. Some very glossy cards can be found with gloss that isn't smooth, but should be. Probably a result of the gloss being sticky in the press and leaving tiny raised points. (Sort of like textured paint) Telling that apart from damage I believe would be a challenge for a machine, not so much for a person.
Or.....93 upper deck, where the gloss was applied three different ways on about 1/3 of the set. Picture only, entire back, and picture only with the entire back done later. It's visible, but by a machine? Maybe maybe not.

And will the machine kick back all the batter ups because of the die cutting in the center of the card?

So you not only need some scanning technology that doesn't currently exist, you need a database of the minutia of every card set you'll try to do. And software that can compare what's being scanned to the database. Not "hard" but that will be a HUGE database, and people will have to enter the information. And unless you program it to identify every card in every set, even through what might be very heavy damage, people will have to tell the machine what it's looking at.

Oh yeah, and you'd need to constantly upgrade it as technology improved and operating systems changed.

And that's only the tip of the iceberg I believe the SS computergraded Titanic will run into.

Or someone could train a kid who likes old stuff for maybe a week, have them start with cheap commons to get a feel for things, and gradually teach them more. Whoever it was would be much faster, but wouldn't be 100% accurate. They'd probably cost a lot less too.

Steve B

I'd be happy with an eBay app that filters out bogus fake cards.

I agree. People, like Dmitri Young, will keep sending cards in hoping to get that person that will grade it a 10. Right now hope is what PSA and SGC are selling, that would be lost with a perfect grader.

If you have the "perfect" grader than no one would have hope for a bump, therefor they would not use that grading company and there would be no return customers with the same card(s).

Steve as usual thanks for the insight.

I think you bring up some very valid points, especially relating to the aspects of the card that are more qualitative such as the gloss or the edge. It's fairly common in the industry that I work in to employ a system where a camera and software package analyze items coming off a production line. The camera and associated software can detect surface flaws, physical defects, etc in the product. I would think that similar technology would lend itself to the more qualitative aspects of card grading.

I can't say that I would be in favor of completely eliminating the human element with respect to card grading (or calling balls and strikes for that matter), but the technology to do so (or at least provide additional assistance) doesn't seem to be that far off.

Mark

Don't underestimate the technology
 

Wow - so much faith in quickly trained 20-somethings, and so little faith in established technology.

The problem with computerized card scanning and grading is not a technical one—it’s a business-case one. Computer-aided visual inspection has been a part of quality control in manufacturing for decades. You’d be hard pressed to find a sophisticated manufacturing enterprise that doesn’t utilize it. And meanwhile, the folks at Google and elsewhere are developing driverless-car technology based in part, and heavily reliant on underlying edge-detection and pattern-matching algorithms. I can use Digital ICE on my flatbed scanner to remove dust and scratches detected in scanned images, and then do further image editing in Photoshop, relying on its sophisticated image-analysis tools (think Magic Wand!). My iPhone camera focuses automatically. And a lot of this is virtually instantaneous. I would argue that the only real technical problem for card grading is that you would risk ending up with a system that would find—and make grading decisions on—details that are not actually visible to the naked eye.

Look at the grading standards for the major TPGs: centering, focus, sharpness of corners, breaks in surface gloss, stains, print or refactor lines. The numerical grades simply quantify the measurements of these features. If these features can be seen—and they can!—they can be quantified and factored into an evaluation function that can be tailored to any specific subgroup of cards you want to define (machine-cut, perforated, hand-cut, … T206, ’52 Topps, ’71 Topps, etc.).

But what’s the business case for such a system tailored to sportscard grading? Like everything else, it’s expensive technology, even when a lot of the hard technological work has already been done. As Pete (ullmandds) has mentioned, most cards have already been graded. This is an interesting observation, and I think largely true (ignoring all the cards now and forever more being produced, obviously). What’s the motivation for people to submit already graded cards to a computerized TPG? Andy (bn2cardz) is also right - there isn’t any “hope” for an anomalous upgrade from a deterministic algorithmic process. Why risk obtaining a lower rating on an existing PSA- or SGC-graded card. Why spend money to have a mid-grade card boosted, when it’s generally the case that a mid-grade card is a mid-grade card for an obvious reason. It would be a questionable business decision to rely on your revenues solely from PSA 7.5s. And lastly, I don’t see the motivation for existing TPGs to change their grading model.

While I too might be reluctant to submit a hundred-year-old ungraded card to a computerized grading system, for fear that it might not receive randomly generous treatment but instead be analyzed dispassionately (and accurately), factoring in warts and all, I’d certainly be more inclined to favor purchasing computer-graded cards over those graded by a “kid” who’s been trained in the art for a matter of weeks. 8->

Cheers,

- David.

+1 Completely agree. This is not really a technology issue, it's business issue. Are you going to develop the capability and license or sell it to a TPG? What's the cost of developing the software and hardware? What's the cost of using existing technology (i.e. scanners, software, color matching, colorimeters, spectrophotometers) How many graders are employed by a TPG? How much do they make? How many cards can a grader review in a work day? What's the turnover rate of graders with a TPG? Are you going to start your own TPG?

I think a machine could provide consistent grades. However, it would only be a matter of time before the scammers were able to slip fake cards past RoboGrader1000.

I would like to chime in here. I lead a software R&D team and we have some of the brightest Machine-vision software engineers around. We solve problems like these every day. We are involved with medical applications, not sportscards, but i can assure everyone here that the technology exists to identify card issue and to identify flaws (or perfections) quite easily. We do things like detect cancerous cells from normal cells via software algorithms. As many have said, the technology to detect or analyze will not be a show-stopper.

Its just a matter of effort and dedication to build the card-specific application of known algorithms. I am developing a user-friendly tool that allows non-machine-vision people to build their own algorithms out of our technology. Its possible this could be used to identify and classify cards by issue, and to also do some analysis of surface, corners, wear, scratches etc. Like someone said, this kind of stuff is done in manufacturing every day. Your iphone screen gets to you without scratches because of these types of systems in manufacturing to weed out the bad units.

I would add that detecting reprints from real could be very tough to do. the feel of card stock might be very difficult to assess. But the software could easily detect the printer "dots" if it came from a laser printer or photocopy and not a real print process.

Or the guy in Mexico would get his own and reprogram it. :D

I would believe that this would only be valid if done through a reputable company with their reputation on the line. Just like now, people who grade their own cards have no rep or brand name to put behind their cards, so they would be an afterthought, just like they are now. It would have to be a valid start-up or a company like PSA, SGC or BGS to get the ball rolling on this concept.

So if it could be done fast enough, the best way would be to have a live person check the authenticity, and then have the machine double check things like print lines, and grade the card? Seems like that would be great. Saying as how we are in the early days of all this technology and card grading is very small, but baseball, and some other sports are getting bigger, I bet we end up seeing something like this sooner or later. Maybe one of the companies trys to make it a high end product or something. I doubt baseball grading is a huge business but there are three companies with huge followings, so competition must be fairly fierce.

Interesting stuff.

I have no doubt at all that current technology could easily handle the easy things.
Size, no problem.

Corner wear also no problem. With exceptions on stuff like 88 score with three different die cuts. The first left tufts of torn cardstock on each corner, the second left those about 1/4 inch in from the corners on each edge. I'm sure that could be programmed around.

Edge wear - Tricky, but only because of the physical handling required to scan edges. Yes, even a hobby level robot could do it, but I'm not sure I'd trust a really expensive card to even a really nice commercial/industrial machine.

Identification would be possible, and probably fairly easy. The hard bit as I mentioned would be building the database. I know some of the automated systems can discern between a variety of objects on a conveyor, but as far as I know those systems are limited to picking out a known object from a group of other known objects, with maybe a few hundred different? The one I've seen only had to deal with about 10 different objects. How many cards are there? Just Topps base cards between 1970 and now is around 32000 not counting variations. And that's just base cards from one company.

Determining fakes from real based on the printing? Maybe easy, maybe not. You'd need fairly high resolution scans, I'm not sure how fast commercial scanners can do that. Certainly faster than my home scanner, but how fast? And that's where I think the data problems would get really troublesome. I would believe that adjusting for registration issues can be done simply. The same would probably be true for over/under inking, print lines smeared ink, etc. However once you're comparing dot patterns, the number of different cards goes up a lot. Some sets that had multiple print runs are different when seen at that level. Some sets have cardstock differences that are maybe challenging to tell apart from toning/staining. One of the earlier Topps Allen and Ginter sets had printed on "tobacco stains" (I learned about them when I was opening packs and eating a chocolate bar, I thought I'd ruined an entire box until I realized those stains were part of the design.

Presumably you'd need a known good example to compare the new image to.
That's a LOT of images and pretty big database. Yes, the storage isn't a problem, and a good system is fast enough that it's not really a problem. But the time to create that database and library of images with fairly high resolution seems a bit daunting to me. yeah, the junk wax era could be run through a really automated scanner, but you might have trouble getting access to the more expensive or rare cards.


Surfaces - Ok, I may have to surrender this point. I'm not positive, only because stuff like a scratch on glass usually changes the color where the scratch is, and that's easy for a machine. I'm not sure about something like fine scratches on a very glossy card, or a scratch on the back of a card where it's maybe a thousandth deep, and the same color as the surrounding cardstock, and can be similar to natural imperfections of the material.


I mentioned it poorly, others have said it better that it's more of a business case. How much do the really good systems cost for the physical machine and the development? And how fast can the cards be imaged on all 6 sides and compared? It's probably not hard to hire 3-4 people who can reasonably accurately grade a card in a few minutes for about the same as one good developer. And their hardware/technology cost is far lower, a decent magnifier is under a hundred maybe under 10 depending on how fancy you want. A top quality ruler and usable caliper under 50, and however fancy a computer you want for data entry.

Steve B

Actually if the lowest company on the totem pole were to offer something like that it would possibly render psa to be like gai currently and devalue psa cards because people would wonder why the seller didn't reholder.

It was the VCP guys that were working on this. I love the idea, especially if they did multiple sub-grades like Beckett. Been thinking about it since I saw this post. Any update Bobby?

http://www.net54baseball.com/showthr...=202183&page=4

That's awesome. Yes please let me know when your done with it.

[REMOVED] This forum is done.

I have to agree on this. There are so many subtleties to grading that I don't think Artificial Intelligence (machines) can/could pick up. Subjectivity (and probably relativity too) is indeed not a characteristic of computers. So that being said, I know they are getting better all of time. My freaking car takes over my steering, on the road, if it goes over a solid line. It puts on the brakes if I don't. So I know technology is getting more advanced.
I think if a machine were to do it you would have all sorts of disagreements on the software used in one machine versus another, parameters used etc etc... Where does it stop? That being said, I am not naive enough to think machines might not do it in the future, I just can't imagine it right now or see how it could be done.

.

I will just say at this point in time there is 1 machine that is capable of doing a vast majority of the work for the grader. Authenticating will always need human experience no doubt, and is the first step in the process before the machine gets its turn. From there all the data compiled allows the grader to chart the grade accurately and also will be able to detect if a card has ran through the system before. This stops multiple attempts at trying for different grades as well as being able to detect if the card was altered in any way from break out till re-attempt at grading.

With this being said I would highly suggest that if anyone is attempting this be very cautious!! You are more than 99% likely to infringe on proprietary software and processes in place for this.

Agreed.

By that post we'd moved on from lasers to current scanning technology and machine vision. Which can do some amazing things. The easy stuff I was referring to is stuff like centering and size. There's stuff out there for stamps that will measure the perforations (The hole they used to punch to make them easy to separate) So I'm sure size and centering and maybe corners are no problem at all.

Steve B

If you have an issue with the use of the word lasers, you are missing the point entirely. I'm not explaining the blueprints on manufacturing the machine, I'm asking if it's possible for a machine to grade cards. Relax. I never claimed to be an expert on machine card grading. I asked if people think it's feasible. I do love the "get off my lawn" responses though. Close-minded people are funny. In this day and age... railing against technology. lol

Not railing against technology, amusing that's what you got from it.

I trained in CAD/CAM 1984-86, and was doing computer stuff before that. Let it go because times changed while I was in school and the couple computer drafting jobs I interviewed for paid less than McDonalds. Got back into things a few years ago, and a lot has changed.

CNC milling machine 1984- Hard programming and cost about 250K for what's now a fairly simple one.
Today? You can get a decent tabletop machine for under 3K and running it is pretty easy. Full size only around 8400, and they do way more than the one I learned on.

CAD stuff? 1984 - not really any 3-D systems unless you were a major corporation. Saw one on a field trip that was 2d, but did all 3 views at once. Cost 50K for the workstation, plus whatever the software cost, plus a mainframe to run it on.
By 1987 there was AutoCAD which did that but on a PC that cost maybe 4K
Now? A couple years ago I downloaded a so-so 3d program for free. And a really good 2-D program also for free.

The first self driving car I was film of couldn't stay on a closed well marked road at anything over a brisk walking pace. I hear they're pretty good now.

3D printing was a lab experiment in about 1986 or so. Now you can get one in the bookstore for about $300

Technology is a wonderful thing, a lot of what we take for granted was insanely impossible a decade or two ago.

But the current stuff has limits to what it can do just like the old stuff had, just different.
What does bug me is silly use of technology where it's unnecessary or makes things less reliable. Like having a switch tell a computer to turn another switch to turn on my headlights. Just a wire and switch worked really well for oh...a century, and will still be reliable and less expensive.
or
One of the guys at the makerspace wanted to drill a hole in a metal bar. Just a simple 3/8 hole with a lot of tolerance for location "about here, maybe within a 16th of an inch" He wanted to know how to program the CNC machine. And was shocked when I told him I could get it done far faster than I could program it. Took under 5 minutes, most of which was finding the drill bit.


So can someone make a card grading machine right now? Probably.
Would it be all that good at it? Probably not.
Could someone make a card grading machine at some future date? Certainly
Could they make one that would be good at it? Someday, I just don't think that time is now.

And-- Could it involve lasers?

YES!:D It's possible to make really fine measurements with lasers. That's how they detected gravity waves earlier this year. Something like 4 Kilometers of distance for the laser paths which have to be perpendicular. And the difference that made for a detectable event was so small I don't have an easy way to explain it. Of course, that cost a LOT of money.

These are pretty cool. And may be cheap enough for me to get one. https://www.youtube.com/watch?v=bKhbEz00ksM


Now git offen my lawn ya pesky kid :D:D:D


Steve B

Several factors that are not taken into account is that there are so many anomalies in any specific given card. To design a program that would eliminate the chance of anomaly would also result in losing many of the key flaws that the program would be designed to identify.

Is the white speck in the background of the crowd a print dot, a cola cup or a design on the fan's shirt?

Was the program designed to identify the cut characteristics of each specific issue or only measure for specific size?

What tolerance would be acceptable for size and what method would be used to determine if a card was original, filed, trimmed or otherwise made to the exact size for the issue.

How would the program recognize variations in registration or focus given that many issues have portions that are purposely out of focus and have different shading.

In theory, the database would require a perfect specimen of every card to utilize as a baseline reference. Since this is not feasible, I'm assuming that some poetic license would have to be taken to complete the database or otherwise the database will be incomplete and the application will still be more human based than mechanically structured.

My premise would be that you can design programs that will assist in grading cards, but anyone that is naive enough to think that a few cameras and programs can provide consistent and accurate results is underestimating the complexity involved in authenticating and grading cards. Additionally, the dirty underbelly of the hobby would quickly identify and abuse the loopholes in the system.