How Japanese OCR works
Drop a photo of a Japanese document, a book or manga page, a menu, a sign or a screenshot, and the text is recognised and saved as Unicode Japanese for Word, Google Docs, LINE or a translator. Choose Japanese for text written across the page, and Japanese (vertical) for tategaki, text written in columns from top to bottom and right to left, as in most novels and newspapers.
Japanese mixes three scripts in one sentence: kanji, of which about 2,000 are in everyday use, and the two kana syllabaries, hiragana and katakana, with 46 basic characters each. Some kana are near twins of each other or of kanji, such as ロ (katakana ro) and 口 (the kanji for mouth), or ニ and 二, and the small kana ャ, ュ, ョ and ッ differ from the full-size ones only in size. Tesseract's Japanese models recognise each character as a whole and output standard Unicode, including full-width punctuation.
Furigana, the small reading aids printed beside kanji, confuse OCR: they can appear in the output mixed into the line, so crop them out or delete them from the result. Tesseract tends to put spaces between Japanese characters; they are removed here, while spaces around English words are kept. Manga lettering and hand-drawn sound effects are much harder than typeset text.
The Japanese model, about 2.0 MB, downloads from the jsDelivr CDN the first time you press the button and is cached, along with the OCR engine of about 4 MB, so later images start straight away. The image itself is read inside this tab and never uploaded. The result is a UTF-8 text file named after the image. For an editable Word document instead, use Image to Word and choose Japanese.
Japanese OCR options explained
| Language | Japanese, already selected; Japanese (vertical) is in the same menu. |
|---|---|
| Script | Kanji, hiragana and katakana, horizontal or vertical (tategaki). |
| Model size | About 2.0 MB, downloaded once and cached. |
| Output | Plain UTF-8 text, one file per image. |
| Layout | Not kept; the words come out in reading order. |
When to use it
Use Japanese OCR to translate a menu, label, sign or product box by pasting its text into a translator, to look up kanji you cannot type, to copy text from a screenshot of a game or web page, or to search scanned documents.
Crop to one block of text at a time, and choose the vertical model for columns. For manga, crop each speech bubble on its own.
About the OCR engine
Text recognition uses Tesseract, the open-source OCR engine first developed at HP, then for many years at Google, and now maintained by its open-source community. Its current generation reads whole lines of text with a neural network (an LSTM) rather than matching letters one at a time, which is what lets it handle joined scripts such as Arabic and Devanagari. Tesseract.js compiles it to WebAssembly so it runs in this tab. Each language has its own trained model, downloaded from the jsDelivr CDN only when that language is chosen and then cached, so reading English never downloads Hindi, and the other way round. The models used here are the integer versions of Tesseract's most accurate models, which keep nearly all of their accuracy at a fraction of the size. Tesseract is built for printed text: it reads books, letters, forms, signs and screenshots well, handwriting poorly, and it keeps the words of a page in reading order but not its layout.
Japanese OCR troubleshooting
Vertical text comes out jumbled
Choose Japanese (vertical) for text in columns.
Small kana are read as full-size
Use a larger image; size is the only difference between ッ and ツ.
Extra characters appear in the line
They are probably furigana. Crop them out, or delete them from the result.
How to use Japanese OCR, step by step
- Press "Choose images" or drag files onto the box.
- Set the options if you need to; the defaults suit most uses.
- Press "Extract text". The work happens on your device.
- Save the result with its download button.
Is it safe to do this online?
With most online tools, "online" means your file is uploaded to a company's server, processed there and kept for a while before it is deleted. Here it is not. The page downloads the tool's code to your browser, and your file is read and processed inside the tab on your own device. It is never sent to TapToConvert or anyone else.
You can check this yourself: once the page and its engine have loaded, turn off Wi-Fi and the tool still works. That also means there is no queue, no daily limit and no file size cap set by a server; the only limit is the memory your browser gives a single tab.
Japanese OCR FAQ
Does it read vertical Japanese?
Yes. Choose Japanese (vertical).
Can it read manga?
Typeset speech bubbles read reasonably well when cropped one at a time; hand-drawn lettering does not.
Can it read handwriting?
Not reliably; it is trained on printed text.
Can I get a Word document?
Yes. Use Image to Word and choose Japanese.
Is it free?
Yes. No sign-up, no watermark and no limit on use. TapToConvert is supported by advertising.
Are my files uploaded?
No. Everything happens inside your browser tab, on your own device.