NUMI V2.0 COIN IDENTIFIER & SORTER

I finally have an update to share with readers on the next iteration of Numi.

After playing around with AI coin grading for half a year, I've started to sour on the idea. I think Technical Grading will eventually be accurate enough to be useful, but I don't think the market will accept it. PCGS, NGC, and CAC are just too dominant. People want and trust the judgment of these companies. I just can't see AI grading taking off in a big manner.

But...after testing AI's computer vision capabilities over a thousand times, I noticed that it's extremely accurate in identifying coins 99% of the time. Specifically identifying the series, year, and mintmark. [For US and World Coins, not medals or tokens. Nor varieties/errors]

I've transitioned Numi to be a coin-sorting robot that uses AI to intelligently identify and sort coins. Imagine a reverse Coinstar that spits back out valuable coins.

After a lot of tinkering and coding, I built the initial alpha prototype and flow for Numi v2.0. The prototype can capture images on both sides of a coin, send an API request to GPT-4o for analysis, and display results identifying the coin's type, country of origin, and year.

 

Tech Specs

• Computer: Raspberry Pi 5
• Cameras: 2 x Arducam IMX519
• Software Language: Python Code
• Physical System: Lego Build Hat peripheral and Lego technic parts
• AI Model: GPT-4o & OpenAI API

Below are some of the problems encountered, lessons learned, and what I plan for the next iteration.

Problems

• Maintaining consistent lighting is a major issue. Lighting is the #1 determinant for accurate results. I am struggling to find a powerful light source that can connect directly to the Raspberry Pi that lets me control both light intensity and color.
• The total time for a coin to go through from placement to results is around 30 seconds. This is too long. It takes around 12 seconds for the API call to complete with the rest for the coin to manually move through the system.
• An API call to the GPT-4o model takes around 1 cent per coin analyzed. Costs can add up fast if you're sorting thousands of coins.
• The AI is struggling to identify mint marks. I suspect this is due to inconsistent lighting as I know that GPT-4o can identify mint marks just fine when I upload close-up photos from my phone.
• Finding the right camera has proven extremely difficult. Most Raspberry Pi cameras have major limitations. It's surprisingly difficult to find a camera that can capture clear images within 50cm of an object, has autofocus, AND zoom functionality. My IMX519 camera requires the coin to be at least 5cm away, it does have autofocus, but no zoom so I have to manually adjust the cameras.

Lessons Learned

• Initially, I thought writing the software was going to be the biggest challenge, but instead, it was the mechanical engineering and building the machine itself
• Linux's permissions setup for folders is the bane of my existence.
• Building with Lego pieces never gets old

Plans fir the next Iteration

• Mechanism to sort coins based on certain parameters
• Goal of reducing run time to 25 seconds per coin

Based on lessons learned, I've already designed what the second iteration should look like. The Lego parts are being mailed and I aim to build the next iteration in a few weeks.

 

 

My goal at the moment isn't to sell Numi or convince others that it's valuable. But rather use it as a tool to understand the needs of collectors and dealers and see if AI can make numismatics more approachable.

If any readers have thoughts or feedback they would like to share, they can always email me via DanscoDude@gmail.com or follow my progress on my Instagram @Dansco_Dude

Will keep you updated!!

To read the earlier E-Sylum articles, see:
NUMI: AI-POWERED COIN IDENTIFICATION APP (https://www.coinbooks.org/v26/esylum_v26n47a10.html)
UPDATE: AI-POWERED APP NUMI (https://www.coinbooks.org/v26/esylum_v26n52a12.html)
REVISITING NUMI (https://www.coinbooks.org/v27/esylum_v27n16a09.html)
REVISITING NUMI, PART TWO (https://www.coinbooks.org/v27/esylum_v27n20a10.html)

	NBS (coinbooks.org) Web