Picture of my bread tie collection on my coffee table

Bread Ties

Started .
Edit I noticed that gemini didn't count the blue ties correctly, this is a major bummer.
Edit I forgot to mention that I ran google ai playground on my phone.

I've been collecting bread ties on and off for the last two years. I started collecting them after seeing a post on instagram where someone had glued them in a notebook. I remember their collection being much more impressive, mostly because there was variations in colors.
Having seen the why combination post where some guy used google ai playground to make a .csv from a video of him scrolling through his gmail, I thought I'd do the same. So I laid out the ties on my table and sent this picture to google ai studio. This first run through used the auto-selected model, which was 'Gemini 2.0 Flash Experimental'.
This was the prompt:
Do the following things: 1. Count the number of bread ties in the picture. 2. Enumerate the bread ties and include the color of the tie, the text written and the color of the text on each one. If the text is illegible, do your best to approximate what it says. If there is no text on the bread tie, say “no text”.

It counted 20 bread ties (there are 22) and gave a pretty good list of the different attributes of each:
  1. Color: Red Text: FEB 24 Text Color: White
  2. Color: White Text: 20041N58 042024 Text Color: Blue
  3. Color: White Text: 5 59 Text Color: Black
  4. Color: White Text: Best By 03/23/2024 23 342 20 Text Color: Black
  5. Color: White Text: BEST BEFORE 03-01-24 Text Color: Black
  6. Color: White Text: $7.99 LM2 24 110 111 01:59 Text Color: Black
  7. Color: Blue Text: No Text Text Color: N/A
  8. Color: White Text: 2023 23261 345 Text Color: Blue
  9. Color: White Text: BEST BEFORE 01-17-25 Text Color: Black
  10. Color: White Text: 23/12/28 Text Color: Black
  11. Color: White Text: 24 010 011 L3 Text Color: Black
  12. Color: Blue Text: No Text Text Color: N/A
  13. Color: Blue Text: No Text Text Color: N/A
  14. Color: Blue Text: No Text Text Color: N/A
  15. Color: White Text: BEST BEFORE 09-13-24 Text Color: Black
  16. Color: White Text: $7.99 L3 24 097 097 13 Best By 07/20/2024 Text Color: Black
  17. Color: White Text: BEST BEFORE 08-23-24 Text Color: Black
  18. Color: White Text: BEST BEFORE 03-13-24 Text Color: Black
  19. Color: White Text: 01 25 24 T C Text Color: Blue
  20. Color: Blue Text: No Text Text Color: N/A
Which is not bad, most of the information was read correctly.
However, I did notice some text was missing from the red tie:
Red bread tie pic
So I decided to run it again with a different model to hopefully glean the missing text of the red tag. For the second prompt I used the model 'Gemini 1.5 Pro' with the following prompt:
Good job for the first pass, let's try again. I noticed there are actually 22 ties. Please take your time and slowly observe each and every bread tie. Thoroughly examine each one. And this time, format it as a .csv.
Here was it's response:
You are absolutely right! My apologies. It's easy to miss a couple with so many similar items. Here's the corrected count and the CSV data, after a much more careful examination:
  1. Count of Bread Ties: 22
  2. CSV Data: Click to download data
It also noted the "Key improvements" it made:
  1. Corrected Count: Includes all 22 ties.
  2. CSV Format: Ready for spreadsheet use.
  3. Multi-line Text Handling: Text spanning multiple lines within a bread tie is enclosed in double quotes and uses line breaks within the field.
  4. Empty Text: Blank ties are marked as empty strings rather than "No Text".
  5. More Precise Color: The blue ties are described as "Light Blue" for better distinction.
  6. Corrected OCR: I have double-checked the OCR to ensure it's as accurate as possible from the image. Some blurry sections might still have slight inaccuracies.
  7. I believe this revised version is much more complete and accurate. Let me know if you have any other questions!
Very cool.