This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Lucky Prospector
Find four-leaf clovers with on-device AI
Only about 1 clover in 5,000 has four leaves. Point your phone at a clover patch and Lucky Prospector highlights the likely four-leaf ones in the live camera view. The AI runs entirely on the phone, so it works offline and the camera image never leaves the device. Finds go into a private notebook, no account needed, with an optional shared map. Free, no ads, open source (GPL-3.0).
Hi Product Hunt! 👋 I'm Daniele, a developer from Italy.
I've never been good at spotting four-leaf clovers, so I trained a small object detector to do it for me. I fine-tuned YOLOX-Tiny on three CC BY clover datasets using my gaming GPU, quantized it to about 6 MB and run it on the phone with LiteRT, tiling the live camera frame so small leaves are not lost.
The hardest part was not the four-leaf clovers but everything that looks like them: wood sorrel, overlapping leaves, tiny clovers seen from standing height.
I'd love feedback on detection quality where you live, and ideas for what to add next. 🍀
About Lucky Prospector on Product Hunt
“Find four-leaf clovers with on-device AI”
Lucky Prospector was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #459 on the daily leaderboard. Only about 1 clover in 5,000 has four leaves. Point your phone at a clover patch and Lucky Prospector highlights the likely four-leaf ones in the live camera view. The AI runs entirely on the phone, so it works offline and the camera image never leaves the device. Finds go into a private notebook, no account needed, with an optional shared map. Free, no ads, open source (GPL-3.0).
On the analytics side, Lucky Prospector competes within Android, Open Source, Artificial Intelligence and GitHub — topics that collectively have 652.4k followers on Product Hunt. The dashboard above tracks how Lucky Prospector performed against the three products that launched closest to it on the same day.
Who hunted Lucky Prospector?
Lucky Prospector was hunted by Daniele Bulgarelli. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Lucky Prospector including community comment highlights and product details, visit the product overview.
Hi Product Hunt! 👋 I'm Daniele, a developer from Italy.
I've never been good at spotting four-leaf clovers, so I trained a small object detector to do it for me. I fine-tuned YOLOX-Tiny on three CC BY clover datasets using my gaming GPU, quantized it to about 6 MB and run it on the phone with LiteRT, tiling the live camera frame so small leaves are not lost.
The hardest part was not the four-leaf clovers but everything that looks like them: wood sorrel, overlapping leaves, tiny clovers seen from standing height.
Everything stays on the device unless you choose to share a find, and the whole project is open source (GPL-3.0): https://github.com/EmergentOrEmergency/lucky-prospector-app
I'd love feedback on detection quality where you live, and ideas for what to add next. 🍀