HomeBlog › OCR App Test

I Tested 5 Japanese OCR Apps on Real Handwriting — Only One Survived Grandma’s Notebook

Printed kanji is easy. Handwritten kanji is where OCR apps quietly fall apart.

Published April 21, 2026 · 11 min read

Every Japanese OCR app demos itself the same way: a clean printed page from a textbook, perfect lighting, perfect angle. The result? 99% accuracy. Marketing screenshots, brochures, App Store features.

Real life isn’t a textbook page. Real life is a friend’s scribbled note, an izakaya menu in marker, your host mother’s shopping list, an old letter from your grandmother. So I built a benchmark and ran the same 100 characters through 5 popular OCR apps in April 2026. Only one stayed above 80% accuracy across all four scenarios.

The Test Setup

I assembled four document categories, 25 characters each, photographed in identical lighting on the same iPhone 15:

Apps tested:

  1. Google Lens
  2. Apple Live Text
  3. Manga OCR (free, open-source)
  4. Yomiwa
  5. Kanjijo (built-in OCR)

The Raw Numbers

AppA: PrintB: Neat HWC: Casual HWD: CursiveAverage
Google Lens100%88%56%20%66%
Apple Live Text100%72%44%16%58%
Manga OCR96%52%28%8%46%
Yomiwa100%92%68%40%75%
Kanjijo100%96%84%52%83%

Three observations jump out:

  1. Print is solved. Every modern OCR app handles printed kanji.
  2. Neat handwriting is borderline. Apple Live Text drops to 72%. Manga OCR collapses to 52% because it was trained on manga panels, not paper.
  3. Cursive destroys everything. Even the winners struggle below 55%.

Why Grandma’s Notebook Breaks OCR

Cursive (購書tai or 行書) introduces three failure modes:

The apps that survived (Yomiwa, Kanjijo) had two things in common: training data that included real handwritten samples, and candidate suggestion lists — instead of guessing one character, they offer the top 3–5 likely matches with confidence scores. That single UX choice rescued dozens of cursive characters in my test.

How to Choose an OCR App for Your Use Case

Your SituationBest ChoiceWhy
Reading menus, signs, websitesGoogle Lens / Apple Live TextFree, instant, accurate on print.
Reading manga panelsManga OCRTrained specifically on speech bubbles and SFX.
Studying from textbooks & notesKanjijoOCR + immediate flashcard add + SRS scheduling.
Reading handwritten letters / recipesYomiwa or KanjijoBoth expose candidate lists for ambiguous strokes.
Real-time conversation translationGoogle TranslateLive overlay, fastest pipeline.

The Two-App Stack I Actually Use Daily

After this test I settled on a hybrid:

  1. Google Lens for quick “what does this menu say” lookups while walking around.
  2. Kanjijo the moment I see a kanji I want to actually learn — one tap adds it to my SRS deck with reading, meaning, mnemonic and stroke order.

The difference is intent. Google translates and forgets. Kanjijo translates and remembers for me.

Try Kanjijo’s OCR Free

Scan any Japanese text or handwriting. Add to SRS in one tap. Reviews scheduled automatically.

The Bottom Line

Don’t trust marketing-page accuracy claims. Test with your documents — the messy, real, off-axis ones you’ll actually point your camera at. Most apps do 100% on a perfect page and fall apart on anything human-written.

Pick the OCR that survives your hardest input. For me that was a recipe written in 1962 by a woman who learned kanji before some of these apps’ engineers were born.