VNTranslator
Become a PatronJoin Our Discord
  • Overview
  • GETTING STARTED
    • Getting Started
    • System Requirements
    • Download & Installation
    • Interface Basics
  • Features
    • Launcher
    • Modules
    • Translation
      • Translation Settings
      • Translation Glossary
      • Extra Options
        • Pre-translation
        • Post-translation
        • Variables
      • Transcheck
      • Advanced Settings
      • Translation Editor
      • Export Translation
      • Import Translation
    • MT Engines
      • MT Settings
      • DeepL API
      • OpenAI Translate (Legacy)
    • Extra Window
    • Hyper Overlay
    • Extensions
      • JParser
      • Jisho
      • Fast OCR
    • Hotkeys
  • User Guide
    • Clipboard
    • OCR
      • Features
        • OCR Screen
        • OCR Master
        • Pre-processing
        • OCR Engines
          • Tesseract OCR
          • Windows OCR
          • Google Cloud Vision
          • Azure Cloud Vision
          • Google Lens
          • Custom - Command Line
          • Custom - HTTP POST
        • Post-processing
      • OCR Engine Installer
      • Understanding OCR and Improving Accuracy
      • OCR Engines Comparison
    • OCR GX 🎮
    • AutoTrans
      • Translation Modes
      • Font Replacement
      • Feature Settings
        • Translation
        • Mods
      • Extract & Translate
      • Steam Connect
      • RTL
      • FAQ
        • How Can I Improve Game Speed in AutoTrans?
        • How to Change Font Type in RenPy?
        • How to Change Font Size in Unity?
    • RenPy Games
    • Tyrano Builder
    • TextractorCLI
  • ADVANCED
    • LLMs
      • System Prompt
      • OpenAI API
      • GeminiAI API
    • Custom MT
      • Schema
      • Form Builder
      • Request & Response
      • Components
      • webLLM
      • MT Kit
      • V1 & V2 (Archive)
    • OCR Server Kit
      • EasyOCR
      • SuryaOCR
    • API Gateway
      • Translate
      • Translation Memory 🚧
    • RegExp
      • Matching
      • Replacement
  • Help
    • FAQ
    • Troubleshooting
      • Launcher
        • VNTranslator appears as a black box
      • Network Connection
      • Machine Translation (MT)
        • Web Scraping Timeout
        • API Error Codes
        • Clear Cookies & Site Data
      • OCR
      • AutoTrans
      • TextractorCLI
    • Glossary
    • Archives
      • Comparison of OCR Version 1.0 and 2.0
      • Workflow Explanation for OCR
      • OCR 1.0 (Archive)
        • Tesseract OCR
        • Screen Capture
        • Post-Capture Actions
    • Credits
Powered by GitBook
On this page
  • Download & Install Tesseract
  • Trained Data Files (Languages)
  • Page Segmentation Modes
  • Troubleshooting
  1. User Guide
  2. OCR
  3. Features
  4. OCR Engines

Tesseract OCR

PreviousOCR EnginesNextWindows OCR

Last updated 7 months ago

Download & Install Tesseract

  • Visit the

  • Select the tesseract-ocr-w64-setup-v5.3.x.exe (64 bit) file to download the Tesseract executable installer

  • Once downloaded, open the executable file and follow the installation prompts

Make sure you have installed the tesseract-64bit in C:\Program Files\Tesseract-OCR

Trained Data Files (Languages)

You can download the .traineddata file for the language you need and place it in Tesseract OCR installation directory C:\Program Files\Tesseract-OCR\tessdata\[here] (this should be the same as where the tessdata directory is installed)

Page Segmentation Modes

The PSM allows you to select a segmentation method dependent on your particular image and the environment in which it was captured

Page segmentation modes

1

Orientation and script detection (OSD) only.

2

Automatic page segmentation with OSD.

3

Automatic page segmentation, but no OSD, or OCR. (not implemented)

4

Fully automatic page segmentation, but no OSD. (Default)

5

Assume a single column of text of variable sizes.

6

Assume a single uniform block of vertically aligned text.

7

Assume a single uniform block of text.

8

Treat the image as a single text line.

9

Treat the image as a single word.

10

Treat the image as a single word in a circle.

11

Treat the image as a single character.

12

Sparse text. Find as much text as possible in no particular order.

13

Sparse text with OSD.

14

Raw line. Treat the image as a single text line, bypassing hacks that are Tesseract-specific.

The number one reason I see budding OCR practitioners fail to obtain the correct OCR result is that they are using the incorrect page segmentation mode. To quote the Tesseract documentation, by default, Tesseract expects a page of text when it segments an input image (Improving the quality of the output).

That “page of text” assumption is so incredibly important. If you’re OCR’ing a scanned chapter from a book, the default Tesseract PSM may work well for you. But if you’re trying to OCR only a single line, a single word, or maybe even a single character, then this default mode will result in either an empty string or nonsensical results.

Troubleshooting

tessdata Speed : Faster than tessdata-best Accuracy : Slightly less accurate than tessdata-best

tessdata-best (Recommended for video games) Speed : Slowest Accuracy : Most accurate

tessdata-fast Speed : Fastest Accuracy : Least accurate

Read More

https://github.com/tesseract-ocr/tessdata
https://github.com/tesseract-ocr/tessdata_best
https://github.com/tesseract-ocr/tessdata_fast
https://pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/
https://docs.vntranslator.com/help/troubleshooting/ocr
Tesseract at UB Mannheim