AIToday
Image GenerationZenn AI/MLPublished: Nov 20, 2026, 16:00 JST

YomiToku tops home-PC receipt OCR test at 93% accuracy

Send on LINE
YomiToku tops home-PC receipt OCR test at 93% accuracy

3 Key Points

  1. What happened

    Across 15 setups on 11 real Japanese receipts, YomiToku's two-pass read hit 93% exact product names and 100% of amounts at roughly 1.8 seconds per receipt; NDLOCR-Lite and PP-OCRv6 led the commercial-friendly options.

  2. Why it matters

    The most accurate option on printed receipts carries a non-commercial license, so anyone planning to embed it in a paid product or workflow must choose a less accurate engine instead.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Context & Analysis

The test grew out of a personal expense-tracking app: the author wanted store names, dates, items and amounts filled in automatically from photos of receipts, and chose to process images locally rather than send them to an outside service, since receipts carry store, item and even staff names. The machine used is deliberately modest — a Beelink SER10 MAX mini PC with an AMD Ryzen AI 9 HX 470 and integrated Radeon 890M graphics, run through Proxmox with 8 CPU threads and 16GB of memory and no NVIDIA GPU, a setup that departs from the NVIDIA-centric assumptions of most OCR write-ups.

The results split along the nature of the document. Japanese-specialized and conventional engines, which detect where text sits and then read line by line, returned coordinates and confidence scores and almost never invented characters; that let the author re-read only low-confidence lines with a heavier model, which proved both more accurate and much faster than running the heavy model alone. The image-capable VLMs could keep up on short receipts but broke down on the long, curved 450×600-pixel Life supermarket receipt that held 21 of the 43 items, with PaddleOCR-VL looping on "* 198" and DeepSeek-OCR 2 generating inflated amounts up to "49,080". On the two handwritten receipts the ranking roughly reversed, with Qwen3-VL 4B, GLM-OCR and HunyuanOCR taking the top spots while YomiToku fell to the middle.

The author is explicit that this is a small sample — 11 receipts, with half the items concentrated on one — and that a single item can flip the ranking, so the numbers are best read as a tendency. The practical takeaway offered is procedural rather than a single winner: because handwritten receipts have no item column, arithmetic checks cannot catch a misread amount, so reading with two engines and accepting a result automatically only when they agree, with a human reviewing any mismatch, appears the safer path.

FAQ
Which OCR should I use for printed Japanese receipts if I need commercial use?
The benchmark points to NDLOCR-Lite or PP-OCRv6. NDLOCR-Lite ran in under one second on CPU and read product names well, while PP-OCRv6 captured every printed amount.
How did image-capable AI models (VLMs) do on printed receipts?
They lagged on long receipts, sometimes repeating the same characters until the output limit. On handwritten receipts, though, VLMs such as Qwen3-VL 4B and GLM-OCR moved to the top.
What hardware did the test run on?
A Beelink SER10 MAX mini PC with an AMD Ryzen AI 9 HX 470 CPU and integrated Radeon 890M GPU, running containers on Proxmox with 8 CPU threads and 16GB of memory, and no NVIDIA GPU.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleApple hiring engineers to build autonomous AI agents, Bloomberg finds