TAG Grading

[toledo_mudhen]

Completely automated (no human intervention)

https://www.taggrading.com/

What do you think?

[wazoo]

What could go wrong

[bnorth]

Originally Posted by toledo_mudhen

Completely automated (no human intervention)

https://www.taggrading.com/

What do you think?

Got to be more accurate and consistent than PSA.
Someone had to post it.LOL

Looks like they only grade 2000 to present standard sized cards. That is when they start grading.

[parkplace33]

Very interesting, would like to learn more about this.

[iwantitiwinit]

If there is one using this technology there will be more. Someone else can go first, Ill wait a year or two to see what shakes out before committing to what might be one of many.

[JustinD]

I have to admit I love the features and the descriptions.

However, like ordering a pizza from a new place...I'll wait till I see what gets delivered.

[Baseballcrazy62]

Jeremy Lee from Sports Card Live has a multiple part series on TAG. It’s on both YouTube and his podcast. A very interesting watch. They are taking in submissions this weekend in Toronto.

[Snowman]

I gave a pretty lengthy overview of the challenges of grading cards using AI in the thread linked below. I work in this field and write similar code to solve other similar problems in a different industry.

The biggest challenge facing AI grading is the ability to accurately grade the surface of a card because typical high-def scans simply aren't adequate for the task (we've all had cards show up in the mail with hidden creases that are not visible from a scan). When TAG arrived on the scene, I was pretty skeptical at first, but I always try to remain open-minded, so I looked into their process more deeply. They utilize an imaging technology known as photometric stereoscopic imaging (they didn't invent the technique, but they did create their own imaging device that uses this) to scan cards with. It allows them to capture the surface from multiple angles using different light sources. Then, they convolve those images into one image using some fancy math. The result is an image that appears 3D and which shows surface flaws like scratches, dimples, tears, creases, etc. Honestly, it's pretty cool, and it's a significant breakthrough for AI grading.

That said, there are still some major hurdles that I'm not sure they'll ever be able to work out for grading vintage cards. It probably works great on modern shiny cards where the variation in surface flaws is much smaller than it is with vintage. But for every card type that they want to grade, they will have to tune an algorithm and taylor it to that card type/set. This is much easier with modern cards that are super cheap and very plentiful. But if they want to start grading low-pop high-end vintage, it's a huge mountain to climb because the AI models they're building will need large training sets of data for each set (thousands of card images if they want a high degree of accuracy) for the algorithms to learn from. Then, they'll have to manually fine tune the results to ensure that the output aligns with market expectations. This is a very labor-intensive process, and it has to be done by a data scientist, and they're not cheap.

I expect to see them slowly dipping their toes into vintage over the next couple years, beginning with sets like 1970 Topps baseball or something like that, but it'll probably be a long time before they ever attempt to grade our more obscure vintage cards. Perhaps they'll take a crack at T206s, maybe 1952 Topps and 1933 Goudeys one day, but I wouldn't expect to see anything out of the mainstream being graded by them any time soon (if ever).

Very cool tech though. Just probably not for what most of us collect.



My lengthier thoughts on AI grading (note, the first post was written before I knew about TAG Grading and photometric stereoscopic imaging, so some of the challenges I mention have been resolved):

https://net54baseball.com/showthread...35#post2132535

https://net54baseball.com/showpost.p...2&postcount=46

[rjackson44]

Lets see the resale value wish thrm the best but ill pass

[BobC]

One of the biggest problems/issues I see is that once again it is another TPG taking it solely upon themself to decide on behalf of everyone else what something should grade as. They have their own specific grading and measurement standards, which though likely close, will probably still differ somewhat from those of every other TPG. Plus, as has been pointed out before, the effective use of AI grading is still ultimately based on human perception, input, and adjustment, and to even begin to be truly effective, will likely require an enormous database of each and every different type of card the system is to grade. This might be better with modern cards printed with modern technology, equipment, and materials. How will it handle vintage and other non-normal or standard card type issues though that can have all types of variances or anomalies within cards in the same set.

As others have already said, I would not go rushing out to be among the first to completely embrace and totally rely upon this new service. But it is an interesting concept and at least worth adopting a "wait and see" attitude.

[jingram058]

Originally Posted by Snowman

I gave a pretty lengthy overview of the challenges of grading cards using AI in the thread linked below. I work in this field and write similar code to solve other similar problems in a different industry.

The biggest challenge facing AI grading is the ability to accurately grade the surface of a card because typical high-def scans simply aren't adequate for the task (we've all had cards show up in the mail with hidden creases that are not visible from a scan). When TAG arrived on the scene, I was pretty skeptical at first, but I always try to remain open-minded, so I looked into their process more deeply. They utilize an imaging technology known as photometric stereoscopic imaging (they didn't invent the technique, but they did create their own imaging device that uses this) to scan cards with. It allows them to capture the surface from multiple angles using different light sources. Then, they convolve those images into one image using some fancy math. The result is an image that appears 3D and which shows surface flaws like scratches, dimples, tears, creases, etc. Honestly, it's pretty cool, and it's a significant breakthrough for AI grading.

That said, there are still some major hurdles that I'm not sure they'll ever be able to work out for grading vintage cards. It probably works great on modern shiny cards where the variation in surface flaws is much smaller than it is with vintage. But for every card type that they want to grade, they will have to tune an algorithm and taylor it to that card type/set. This is much easier with modern cards that are super cheap and very plentiful. But if they want to start grading low-pop high-end vintage, it's a huge mountain to climb because the AI models they're building will need large training sets of data for each set (thousands of card images if they want a high degree of accuracy) for the algorithms to learn from. Then, they'll have to manually fine tune the results to ensure that the output aligns with market expectations. This is a very labor-intensive process, and it has to be done by a data scientist, and they're not cheap.

I expect to see them slowly dipping their toes into vintage over the next couple years, beginning with sets like 1970 Topps baseball or something like that, but it'll probably be a long time before they ever attempt to grade our more obscure vintage cards. Perhaps they'll take a crack at T206s, maybe 1952 Topps and 1933 Goudeys one day, but I wouldn't expect to see anything out of the mainstream being graded by them any time soon (if ever).

Very cool tech though. Just probably not for what most of us collect.



My lengthier thoughts on AI grading (note, the first post was written before I knew about TAG Grading and photometric stereoscopic imaging, so some of the challenges I mention have been resolved):

https://net54baseball.com/showthread...35#post2132535

https://net54baseball.com/showpost.p...2&postcount=46

Summarized very nicely, sir. Even someone as dumb as I am can get it after reading this. And I am not even a graded card collector.

[JollyElm]

When I read this type of thread, all I can think of is EOS (Eye of Sauron) Grading. Man, you thought PSA gave bad grades...

sauron.jpg

[Yoda]

Well now, I guess it is finally time to grade my raw T206 Honus. I hear the value has gone way up since I bought it in 1909 for my Dad who smoked Sweet Caps. Dad's gone now.

[brianp-beme]

I have a cheesy tagline for the company that they can freely use:

TAG, you're IT!

Brian

[luciobar1980]

Not sure but I think their slabs and labels look great

[Leon]

Originally Posted by jingram058

Summarized very nicely, sir. Even someone as dumb as I am can get it after reading this. And I am not even a graded card collector.

+1 Nice summation by the Snowman.
It is interesting and some of those slab features will hopefully make their way into the industry... Someone needs to come up with UV proof and not UV resistant. The "resistant" always makes me a bit leery.
.

[robw1959]

Originally Posted by brianp-beme

I have a cheesy tagline for the company that they can freely use:

TAG, you're IT!

Brian

Since companies are always trying to draw commercial attention to themselves, maybe a good variation on that phrase could be the slogan, "TAG . . . We're IT!"

[clamendo]

Originally Posted by Snowman

I gave a pretty lengthy overview of the challenges of grading cards using AI in the thread linked below. I work in this field and write similar code to solve other similar problems in a different industry.

The biggest challenge facing AI grading is the ability to accurately grade the surface of a card because typical high-def scans simply aren't adequate for the task (we've all had cards show up in the mail with hidden creases that are not visible from a scan). When TAG arrived on the scene, I was pretty skeptical at first, but I always try to remain open-minded, so I looked into their process more deeply. They utilize an imaging technology known as photometric stereoscopic imaging (they didn't invent the technique, but they did create their own imaging device that uses this) to scan cards with. It allows them to capture the surface from multiple angles using different light sources. Then, they convolve those images into one image using some fancy math. The result is an image that appears 3D and which shows surface flaws like scratches, dimples, tears, creases, etc. Honestly, it's pretty cool, and it's a significant breakthrough for AI grading.

That said, there are still some major hurdles that I'm not sure they'll ever be able to work out for grading vintage cards. It probably works great on modern shiny cards where the variation in surface flaws is much smaller than it is with vintage. But for every card type that they want to grade, they will have to tune an algorithm and taylor it to that card type/set. This is much easier with modern cards that are super cheap and very plentiful. But if they want to start grading low-pop high-end vintage, it's a huge mountain to climb because the AI models they're building will need large training sets of data for each set (thousands of card images if they want a high degree of accuracy) for the algorithms to learn from. Then, they'll have to manually fine tune the results to ensure that the output aligns with market expectations. This is a very labor-intensive process, and it has to be done by a data scientist, and they're not cheap.

I expect to see them slowly dipping their toes into vintage over the next couple years, beginning with sets like 1970 Topps baseball or something like that, but it'll probably be a long time before they ever attempt to grade our more obscure vintage cards. Perhaps they'll take a crack at T206s, maybe 1952 Topps and 1933 Goudeys one day, but I wouldn't expect to see anything out of the mainstream being graded by them any time soon (if ever).

Very cool tech though. Just probably not for what most of us collect.



My lengthier thoughts on AI grading (note, the first post was written before I knew about TAG Grading and photometric stereoscopic imaging, so some of the challenges I mention have been resolved):

https://net54baseball.com/showthread...35#post2132535

https://net54baseball.com/showpost.p...2&postcount=46

I working with networking products that use AI. You are 100% correct, you need the training data. Why do you think PSA and others are scanning cards, for their health? The stuff that makes the “cloud” work is all the data centralized in one place. That’s why Amazon has such an advantage over brick and mortar retailers

At this years National, I was at a booth when someone from CSG asked the dealer I was talking to for low grade cards from regional obscure football issues. They wanted them so the graders could get a “feel” for the issue, coloring, stock, size, etc. So, a type collection like Leon’s baseball would have been perfect.

So, in my opinion is Genamint is probably really good at picking up on defects, etc on mainstream issues, but I question what it’s effectiveness would be on difficult issues.

Finally, I spoke to the guy in Toronto for TAG. Only newer cards, but you left out one important thing that the guy mentioned to me. All new cards are usually high grade, however what they are trying to pick up is counterfeits.


Sent from my iPhone using Tapatalk

[ClementeFanOh]

Thank you, Snowman, for such a lucid and useful explanation...

I am all for TAG should their approach be consistent. Lots of folks- heck, all
of us probably- have a pecking order of what features or flaws should most
impact a slabbed card's grade. If a TPG can provide reliable grades using
this tech- those we can predict even if we don't agree- color me intrigued.

Trent King

[mq711]

At least they are exploring a different technique to accurately authenticate and grade cards. Seems like all the other start-up TPG use the same techniques and try to get business with fancy slabs and quick turnaround times. I hope they succeed and grow their service. Unfortunately I don’t have any 2000-present cards so I’ll be on the sideline watching.

[brianp-beme]

Originally Posted by robw1959

Since companies are always trying to draw commercial attention to themselves, maybe a good variation on that phrase could be the slogan, "TAG . . . We're IT!"

Or if Ricky Henderson were to become a spokesperson, it could instead be:

TAG...Ricky be IT!


Brian

[cubman1941]

I have some modern cards which are not worth a lot but I did an email sign up to get information from TAG but have received nothing. I figured if the price was right I might get one or two graded just to check them out.