Pocket Naturalist – Offline AI field guide for walks

Description and use

Pocket Naturalist is an offline plant‑identification guide that runs locally on a laptop and phone. Adding a 107‑line Indian field guide CSV improved accuracy from 4/15 to 10/15 and replaced fabricated facts with actionable "look‑closer" tips.

Problem

Users need an offline plant identification guide that works without internet, provides reliable results, and encourages real‑world observation.

Outcome

Adding a region‑specific field guide CSV and prompt rules increased correct plant identifications from 4/15 to 10/15 and eliminated fabricated facts, while keeping the system fully offline.

Workflow

• 1. Start a walk – the phone receives a first quest via offline TTS.
• 2. Snap a photo or add from gallery; the phone connects to the laptop over a hotspot.
• 3. The laptop runs server.py, which sends the image to Ollama running gemma4:12b (vision).
• 4. The model outputs a fixed‑JSON response: features seen, top three candidates, and a "look‑closer" clue if unsure.
• 5. The app reads the answer aloud, then returns the phone to the pocket.
• 6. At walk end, the app compiles a journal from the collected data and user corrections.

Evidence

Stock Gemma got 4 of 15 right.

Source

After the fix: 4 → 10 correct out of 15 photos where I know the right answer.

Source

The laptop is nothing special: an RTX 3050 with 6 GB of GPU memory and 16 GB of RAM.

Source