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

[steve B]

Originally Posted by sportscardtheory

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.

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.


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

[rdwyer]

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

[dealme]

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

Originally Posted by steve B

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.


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

[hilgum]

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.

[CardboardCollector]

Originally Posted by hilgum

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?

[Eric72]

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.

[parkerj33]

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.

[Bruinsfan94]

Originally Posted by parkerj33

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.

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.

[Peter_Spaeth]

Originally Posted by Eric72

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.

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

[sportscardtheory]

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.