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.
|