Soda PDF allows you to adjust the OCR preferences depending on the type of document you're working with.
This article will cover the instructions for the following versions:
Soda PDF Desktop
- Click the gear icon in the top right corner to open the Options.
- Open the OCR tab.
- You can also access the OCR Options from the OCR tab.
- You can set the OCR language to scan a document in a language other than your computer's default language. Select your OCR language from the Language for Recognition drop-down menu.
- Recognition and output quality depend largely on the quality of the image being recognized. The lower the quality of your original image, the higher the recognition quality should be set.
- The Orientation and Script Detection toggle allows you to configure the following:
- The Deskew option allows the straightening of a crooked image.
- To straighten a skewed image, switch the toggle on for the Rotate Page option.
- To detect inverted text blocks, use the Detect Text Orientation option.
If the OCR module is not available for you, you can purchase it here.
Soda PDF Online
You can access Soda PDF Online here - https://tools.sodapdf.com/
- Click on the Account in the bottom left corner.
- Select App settings.
- Open the Recognize text section.
- You can set the OCR language to scan a document in a language other than your computer's default language. Select your OCR language from the Language for recognition drop-down menu.
- Recognition quality depends largely on the quality of the image being recognized. The lower the quality of your original image, the higher the recognition quality should be set. Select either Low, Medium, or High recognition quality depending on the quality required for your image.
- The Deskew option allows the straightening of a crooked image.
- To straighten a skewed image, switch the toggle on for the Rotate Page option.
- In order to detect inverted text blocks, use the Detect Text Orientation option.
- Select Embed Fonts to perform recognition of text containing fonts that are not installed on your system.
- Apply the Create Bookmarks option to a document containing bookmarks you would like to keep after recognition.
- The Recognized Text Output option provides you with the ability to choose the desired type of recognition:
- Text-Image removes text from a recognized image and replaces it with editable, visible text;
- Text Only completely removes a recognized image and keeps editable, visible text;
- Image-Text inserts editable non-visible text behind an image without modifying it.
- The compression quality you set affects the size of the output file. The higher the quality you choose, the larger the file size will be.
- In the JPEG 2000 Compression Quality option, click the switch to make the quality slider appear.
- Adjust the compression by choosing its quality level: Low, Medium, or High.