Warning, /documentation/digikam-doc/post_processing/ocrtext_converter.rst is written in an unsupported language. File is not indexed.

0001 .. meta::
0002    :description: The digiKam OCR Text Converter
0003    :keywords: digiKam, documentation, user manual, photo management, open source, free, learn, easy, ocr, text, tesseract
0005 .. metadata-placeholder
0007    :authors: - digiKam Team
0009    :license: see Credits and License page for details (https://docs.digikam.org/en/credits_license.html)
0011 .. _ocrtext_converter:
0013 OCR Text Converter
0014 ==================
0016 .. contents::
0018 The OCR text converter is a tool to parse the contents of an image and detect areas with text to convert into editable and translatable characters files.
0020 The tool can batch optical character recognition (OCR) over images, and their translations in many languages using an online translator engine. It also allows you to review the text and make corrections and offers spell checking.
0022 The tool use in background the `Tesseract <https://en.wikipedia.org/wiki/Tesseract_(software)>`_, a powerful open-source optical character recognition engine available for Linux, macOS, and Windows.
0024 To perform text conversions, select the scanned images including text to recognize and start the tool from the menu :menuselection:`Tools --> OCR Text Converter`, or use the icon **OCR Text Converter** from the **Tools** tab on the right sidebar. The following dialog must appear:
0026 .. figure:: images/ocrtext_converter_dialog.webp
0027     :alt:
0028     :align: center
0030     The digiKam OCR Text Converter Dialog
0032 On the right side, the **Text recognition** tab shows on the top of view the **Tesseract** binary program version detected on your system. If none is present, you will need to install it on your system. Below, the **Tesseract** settings can be customized to process images.
0034 The **Languages** setting specifies the language used for OCR. In the **Default** mode, when processing digital text with multiple languages, **Tesseract** can automatically recognize languages using Latin alphabets such as English or French, but it's not compatible with languages using hieroglyphs such as Chinese or Japanese. You can use the **Orientation and Script Detection** mode instead or a specific language module if available.
0036 The **Segmentation mode** settings specify the **Tesseract** page segmentation mode to use while processing images. Possible choices are listed below:
0038     - **OSD only**: Orientation and Script Detection (OSD) only.
0039     - **With OSD**: Automatic page segmentation with OSD.
0040     - **No OSD**: Automatic page segmentation, but no OSD, or OCR.
0041     - **Default**: Fully automatic page segmentation, but no OSD.
0042     - **Col of text**: Assume a single column of text of variable sizes.
0043     - **Vertically aligned**: Assume a single uniform block of vertically aligned text.
0044     - **Block**: Assume a single uniform block of text.
0045     - **Line**: Treat the image as a single text line.
0046     - **Word**: Treat the image as a single word.
0047     - **Word in circle**: Treat the image as a single word in a circle.
0048     - **Character**: Treat the image as a single character.
0049     - **Sparse text**: Sparse text. Find as much text as possible in no particular order.
0050     - **Sparse text + OSD**: Sparse text with OSD.
0051     - **Raw line**: Treat the image as a single text line, bypassing hacks that are Tesseract-specific.
0053 If you want more details about the Tesseract Segmentation Mode you can read this `online tutorial <https://pyimagesearch.com/2021/11/15/tesseract-page-segmentation-modes-psms-explained-how-to-improve-your-ocr-accuracy/>`_.
0055 The **Engine mode** setting specifies the **Tesseract** OCR internal engine to use while processing images. Possible choices are listed below:
0057     - **Legacy**: Legacy engine only (older engine not based on the neural network).
0058     - **LSTM**: Neural network LSTM (Long Short-Term Memory deep-learning) engine only.
0059     - **Legacy + LSTM**: Both legacy and LSTM engines will be used.
0060     - **Default**: Default value. Let Tesseract choose the best engine based on what is available.
0062 The **Resolution Dpi** settings specify the resolution as Dot Per Inch (DPI) for the input images.
0064 If the **Use Multi-cores** setting is enabled, files from the list will be processed in parallel with Tesseract.
0066 The **Store result in** will specify where to place the text contents recognized by Tesseract while processing images. Possible choices are listed below:
0068     - **Text file**: Store OCR result in a separate text file in the same directory as the processed image.
0069     - **Metadata**: Store OCR result in alternative-language XMP tag from image metadata.
0071 On the bottom of this view, the OCR result can be translated into different languages using one online translation engine. You can set more than one translation language to process images. Corresponding translations will be hosted in separate text files or in extra metadata entries depending on the **Store result in** setting. See :ref:`this page from the manual <spellcheck_settings>` for more details about the **Localize Settings**.
0073 The **Text Review** tab on the right side allows editing the OCR result for each image processed with Tesseract. Select one item from the list on the left side and OCR result will be displayed in a text editor. You can fix text if necessary or apply spell-checking. See :ref:`this page from the manual <localize_settings>` for more details about the **Spell-Checking Settings**.
0075 On the bottom of the dialog, the **Default** button allows resetting all settings to the default values. The **Start OCR** drop-down button allows the processing of the currently selected images from the list or all items. Finally, the **Close** button will stop all OCR processes if any and close the dialog.
0077 .. figure:: images/ocrtext_converter_review.webp
0078     :alt:
0079     :align: center
0081     The digiKam OCR Text Converter Content to Review on the Right Side with the Corresponding Image Open in Showfoto