A discussion about using AI to grade comic books. 3 3

[namisgr]

On 12/25/2023 at 3:45 PM, VintageComics said:

It sounds like you're saying that it like will be economically feasible once bio-digital convergence becomes a regular thing, which is what I'd already stated. 

I said nothing of the kind, and I don't agree with the statement.  Like I wrote already, there have been over the past several years repeated demonstrations applying brain-computer interfaces and machine learning to derive algorithms and perform functions previously lost in humans through nervous system injury or disease.  People paralyzed have walked under their own power, "spoken" language via computer at a near normal rate, and achieved restored auditory and visual functions, all of which they were unable to do for up to a couple of decades prior.  To develop a computer-based method for grading comic books with the accuracy of professional human graders would be, comparatively, far easier to do than the achievements already made with defective nervous systems. After all, there already exists a systematic framework graders use on every book that takes into account the number, severity, nature, and placement of wear and defects that reduce numerical grade, that was implemented to maintain consistency over time and among different graders.

Also like I wrote already, the robotics technology for turning comic book pages and capturing their images, including the outside and inside covers at multiple angles, is pre-existing and I see no reason why it would be prohibitively expensive.  Finally, as I wrote already, the capacity to achieve economic equivalence with the current all human grading approach is, in my opinion, not as far away as you seem to believe, and might be cost effective in as little as a decade, and I wouldn't rule out even shorter. The emergent computer and robotics technologies to perform these tasks could work around the clock and on weekends, and there could be multiple setups operating at once.  The upfront financial burden of implementation resolves over time into a far, far smaller set of maintenance expenses.

Edited December 26, 2023 by namisgr

[VintageComics]

On 12/26/2023 at 12:07 PM, namisgr said:

Also like I wrote already, the robotics technology for turning comic book pages and capturing their images, including the outside and inside covers at multiple angles, is pre-existing and I see no reason why it would be anywhere near as expensive as you've suggested.  

I didn't put a cost to it. I simply said it's still not feasible and is not happening anytime soon. 

On 12/26/2023 at 12:07 PM, namisgr said:

Finally, as I wrote already, the capacity to achieve economic equivalence with the current all human grading approach is, in my opinion, not as far away as you seem to believe.

You seem to contradict yourself here, because above you say it's not as expensive as I've suggested, and here you say we're not far off from achieving "economic equivalence".

What's far off?

So the question, which has stayed consistent all along through all the various threads and discussions is, when will it be economically feasible to implement at CGC?

 

We can't even have automated cars yet (although that's coming), which doesn't take a lot of fine, motor skill work. It's all macro stuff. 

We can't have robots perform surgeries without human control and involvement, which you yourself have stated. 

We can't even have basic robots deliver Uber food orders yet. I once saw one of those robots hit a street pole at full speed.

I personally believe we'll sooner have automated cars for the public, robot surgeons without human involvement and Uber eats vehicles that don't hit poles before we have robot graders at CGC. 

I don't think we'll see it within a decade. 

Edited December 26, 2023 by VintageComics

[CAHokie]

This guy might be able to be programmed to do it. 

 

[FlyingDonut]

On 12/26/2023 at 12:28 PM, VintageComics said:

I didn't put a cost to it. I simply said it's still not feasible and is not happening anytime soon. 

You seem to contradict yourself here, because above you say it's not as expensive as I've suggested, and here you say we're not far off from achieving "economic equivalence".

What's far off?

So the question, which has stayed consistent all along through all the various threads and discussions is, when will it be economically feasible to implement at CGC?

 

We can't even have automated cars yet (although that's coming), which doesn't take a lot of fine, motor skill work. It's all macro stuff. 

We can't have robots perform surgeries without human control and involvement, which you yourself have stated. 

We can't even have basic robots deliver Uber food orders yet. I once saw one of those robots hit a street pole at full speed.

I personally believe we'll sooner have automated cars for the public, robot surgeons without human involvement and Uber eats vehicles that don't hit poles before we have robot graders at CGC. 

I don't think we'll see it within a decade. 

Roy - you keep moving the goalposts.

The three things you cite all have subjective issues. Grading is objective - or could be made to be - through AI.

When would it be economically feasible to implement? Within a year at the outside if they (1) had the hardware technology problems fixed to image pages (and that technology already exists) and (2) wanted to do so. Assuming the imaging issue - which should not be minimized - could be addressed to a satisfactory point, a grading company could increase throughput exponentially. 100% guarantee there will be AI grading of cards at a high level by the end of this year as the technology issue there doesn't exist.

[CAHokie]

I still don’t see it being that far fetched.  
 

Dental offices can now use a small camera that can take hundreds of pictures and make a perfect mold by splicing the photos together. (At least that’s how I understood it. Dentists can weigh in).  It is not an x-ray and prevents having to do that gel mold. 

I could envision cameras doing the same thing as the pages are turned. It can then be analyzed and details listed. I don’t really see it an issue of could they do it, but more of would they want to. 

[VintageComics]

On 12/26/2023 at 12:44 PM, FlyingDonut said:

Roy - you keep moving the goalposts.

Which goal posts did I move? Be more specific. 

[VintageComics]

On 12/26/2023 at 12:44 PM, CAHokie said:

I still don’t see it being that far fetched.  
 

Dental offices can now use a small camera that can take hundreds of pictures and make a perfect mold by splicing the photos together. (At least that’s how I understood it. Dentists can weigh in).  It is not an x-ray and prevents having to do that gel mold. 

I could envision cameras doing the same thing as the pages are turned. It can then be analyzed and details listed. I don’t really see it an issue of could they do it, but more of would they want to. 

One of my daughter runs a dental office. 

Again, not saying it's impossible. I'm saying it's not feasible at this point. 

How much does it cost? 

[CAHokie]

On 12/26/2023 at 1:02 PM, VintageComics said:

One of my daughter runs a dental office. 

Again, not saying it's impossible. I'm saying it's not feasible at this point. 

How much does it cost? 

Ask her.

[shadroch]

If a robot can be trained to perform brain surgery in the womb, I'm fairly confident one can learn how to turn pages. 

The problem here is pretty simple. Someone starts threads about AI without understanding what it is and doesn't want to let that get in the way. 

[FlyingDonut]

On 12/22/2023 at 9:45 PM, VintageComics said:

I personally have stated many times that AI can do aspects of grading, but grading an entire comic is not going to happen anytime soon for a zillion different reasons, but the primary one being that you need to intersect the following

i) handling the actual comic book is complex

ii) time constraints - sure, if I had an hour to feed all my info into a computer I may be able to get a reasonably accurate grade, or grade range but you need this done in seconds

iii) cost constraints - how do you build something this complex, in a space that doesn't take too much room, is cost effective and accurate

iv) you will ALWAYS need some level of human interaction throughout the grading process, whether it's from receiving packages, to unpackaging, to laying them down on an assembly line, to removing them from Mylars, to grading them (flipping through all pages) to putting them back into Mylars, etc. so where does the human stop and the AI start and visa versa?

v) you need to TEACH the AI to learn along the way (or from past experience) - that's a stall every time you find a new problem to solve, and this happens daily when grading 1000's of books a day. For example, there are things that happen in the grading process EVERY DAY when weird defects, or a crossover of defects happen that need actual human conversation to make a decision. This will stall the grading process and needs to be learned and it happens daily.

vi) you'd need to make AI changes every time a new defect or variant is discovered - new learning curve

----------------------------------------

The way I see it the variables are myriad and not easy to solve. 

Humans do this sort of learning very quickly. 

I just don't see AI grading books accurately, in a cost effective and timely manner anytime soon. 

Thoughts?

This was your original post.

i) This isn't an AI issue, this is a hardware issue. Imaging hardware at a high level already exists and if there was a desire to do so, it could easily be implemented by a grading company.
ii) This shows a fundamental lack of understanding what AI is and does. If you 'feed all my info into a computer" the AI will learn. That's the whole point of AI.
iii) Not an AI issue, a hardware issue.
iv) Not an AI issue, HR and hardware issues, both of which could be addressed by a forward-thinking grading company.
v) Again, a fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.
vi) Fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.

The variables are myriad but the only one that isn't easy to solve is the hardware issue. AI will learn all of the variable, and AI learns at an exponentially higher rate than humans.

 

[MyNameIsLegion]

On 12/26/2023 at 11:47 AM, VintageComics said:

Which goal posts did I move? Be more specific. 

Well, in Roy’s defense, he’s Canadian. They moved the goal post, the field, added players, kick the ball whenever they feel threatened. Utter CFL chaos! 

[Prince Namor]

On 12/27/2023 at 1:32 AM, FlyingDonut said:

This was your original post.

i) This isn't an AI issue, this is a hardware issue. Imaging hardware at a high level already exists and if there was a desire to do so, it could easily be implemented by a grading company.
ii) This shows a fundamental lack of understanding what AI is and does. If you 'feed all my info into a computer" the AI will learn. That's the whole point of AI.
iii) Not an AI issue, a hardware issue.
iv) Not an AI issue, HR and hardware issues, both of which could be addressed by a forward-thinking grading company.
v) Again, a fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.
vi) Fundamental lack of understanding of what AI is and does. The system learns. That's the whole point.

The variables are myriad but the only one that isn't easy to solve is the hardware issue. AI will learn all of the variable, and AI learns at an exponentially higher rate than humans.

 

This conversation began in another thread and there he said:

‘It’s Too Complex to be done’, ‘it’s just fairy tale stuff for the foreseeable future’ and ‘You might eventually be able to make it happen in the distant future with NASA type tech, but by then all human labor will have been replaced’.

[Buzzetta]

[FlyingDonut]

  

On 12/26/2023 at 1:02 PM, VintageComics said:

One of my daughter runs a dental office. 

Again, not saying it's impossible. I'm saying it's not feasible at this point. 

How much does it cost? 

You didn't ask how much it cost. You asked if it could be done in an economically feasible manner. It is completely impossible to answer either of those questions because no one knows how much it would cost to purchase the hardware required - which has nothing to do with the AI - nor does anyone know what the actual software would cost. You are arguing an angels on the head of a pin argument that cannot be answered.

Based on my understanding of the technology, the software, and the implementation of AI across multiple industries, if a grading company wanted to use AI and wanted to invest in the hardware required that company would, after about 12 months at the absolute outside, have a grading system that could do many multiples of the throughput that grading companies do now at a significant cost savings. There would also be a very added benefit of no subjectivity in grading - the AI would grade everything the same. There wouldn't be the "Golden Age" bump, for example (unless that was built into the algos by the information at the beginning). 

[Buzzetta]

On 12/26/2023 at 1:40 PM, FlyingDonut said:

There would also be a very added benefit of no subjectivity in grading - the AI would grade everything the same. There wouldn't be the "Golden Age" bump, for example (unless that was built into the algos by the information at the beginning). 

The guys that did it with cards were reporting that all resubmits were coming back the same once they felt the AI had reached a "stabile" position or for lack of a better phrase, "learned enough" to accurately do the job. 

Edited December 26, 2023 by Buzzetta

[VintageComics]

On 12/26/2023 at 1:13 PM, shadroch said:

If a robot can be trained to perform brain surgery in the womb, I'm fairly confident one can learn how to turn pages. 

Are you sure? This expert disagrees with you:

On 12/22/2023 at 7:59 PM, namisgr said:

Robotics is used in several types of surgeries.  But the robots are controlled and manipulated by the surgeon, and not working autonomously.

 

On 12/22/2023 at 8:41 PM, namisgr said:

It would need to be a much more deft robot, since the pages of aged comic books are much thinner and more fragile than those of hardback books.  

-----------------------------------------------

On 12/26/2023 at 1:13 PM, shadroch said:

The problem here is pretty simple. Someone starts threads about AI without understanding what it is and doesn't want to let that get in the way. 

It's a discussion about both capability and feasibility.

Are you sure? 

Edited December 26, 2023 by VintageComics

[VintageComics]

On 12/26/2023 at 1:40 PM, FlyingDonut said:

On 12/26/2023 at 1:02 PM, VintageComics said:

One of my daughter runs a dental office. 

Again, not saying it's impossible. I'm saying it's not feasible at this point. 

How much does it cost? 

You didn't ask how much it cost.

You're confusing the discussion with this post. 

I was asking CAHokie how much the dental work and the dental machines cost. 

On 12/26/2023 at 1:40 PM, FlyingDonut said:

You asked if it could be done in an economically feasible manner. It is completely impossible to answer either of those questions because no one knows how much it would cost to purchase the hardware required - which has nothing to do with the AI - nor does anyone know what the actual software would cost. You are arguing an angels on the head of a pin argument that cannot be answered.

They entire point of having the discussion is to discuss the various facets of the potential use of AI in grading comics. 

I'm not arguing angles on a pinhead because from my end, so far it's been a discussion about beliefs: what is possible and what isn't. I didn't state any absolutes within the context of this discussion. 

I specified a belief that it's too costly to do right now. I also stated it will likely be possible in the future but not the near future. I still stand by those beliefs unless someone shows me a better way. 

Discussions expand over time. 

To clarify for you:

Discussing whether AI can grade comic book or not and whether CGC will be able to use AI or not are two different discussions now. 

They've branched off into theory and implementation.

The AI discussion alone is software. Everyone knows that. I always knew that. 

The application of AI to grade comic books is a discussion about MULTIPLE facets of the application, including AI, robotics, cost, feasibility, practicality, efficiency and a zillion other things. Myriad. 

Which part of the discussion being address is important. 

JC25427N addressed the software problems from his experience in software.

namisgr addressed some hardware problems with his experience in the health industry. 

CAHokie addressed cost issues with his experience in the parent industry.

If you want to start a discussion about angels on a pinhead, that room is down the hall.

Edited December 26, 2023 by VintageComics

[VintageComics]

On 12/26/2023 at 1:40 PM, FlyingDonut said:

Based on my understanding of the technology, the software, and the implementation of AI across multiple industries, if a grading company wanted to use AI and wanted to invest in the hardware required that company would, after about 12 months at the absolute outside, have a grading system that could do many multiples of the throughput that grading companies do now at a significant cost savings. There would also be a very added benefit of no subjectivity in grading - the AI would grade everything the same. There wouldn't be the "Golden Age" bump, for example (unless that was built into the algos by the information at the beginning). 

Thank you for your opinion on the theory. I too would LOVE consistency in grading. 

What experience do you have in fine robotics?

What experience do you have in imaging?

How much do YOU think it would cost to implement a hardware system that could turn pages and image them to grade comic books?

Do you believe it would be cost efficient enough to implement in 12 months?

Did you want us to stop discussing these things? 

 

Edited December 26, 2023 by VintageComics

[namisgr]

Page turning device that's just a wee bit simpler than the work NASA or an endovascular or prenatal surgeon does:

And, to head off any suggestion at the pass, the idea of posting this video is not to suggest that this device could be used as part of an automated comic book grading system.  Instead, the idea is to illustrate how little sophistication and cost would be involved in developing a system sufficiently gentle, reliable, programmable, and cheap to turn pages and partner with an imaging and book positioning system to readily capture all the images required for an algorithm developed by machine learning from the output of professional CGC graders to devise an automated grading system.

Edited December 26, 2023 by namisgr

[CAHokie]

On 12/26/2023 at 2:07 PM, VintageComics said:

CAHokie addressed cost issues with his experience in the parent industry

I did? Now I’m lost…. All I said is that there are programs and equipment made to capture hundreds of images and splice them together into a final product.  In the dental example, it is capable of making a perfect mold that fit around teeth perfectly for that person. That is impressive. Scanning a comic book seems less impressive but that’s just an opinion.