OCR stands for "Optical Character Recognition”. OCR software is used to convert a document or an image into accessible, machine-readable text data. The OCR Analyze step is used to do this within Synatic by providing readily available models that can be analyzed and converted.
NB: To train a document or for any enquiries, please send an email to support@synatic.com
Illustrated in the below image is a flow where the Byte Group step is used to convert the document from bytes to base64 string. An OCR Analyze step is used to analyze a provided document. The Buffer is used to store the data from the file.
The image below shows the Byte Group step configuration. The Input Mode is set to Byte and the Output Mode is set as a Base64 string. The To Field is "data" in this example.
Adding an OCR Analyze step
To add an OCR Analyze step in a flow, follow the below instructions:
1. Click on the highlighted icon as shown in the below image.
2. The below page will appear. Select or search for OCR as shown in the image below. Click on the OCR Analyze destination step to add the step.
Configuring an OCR Analyze step
Illustrated in the below image is the configuration that is available in the OCR step.
OCR Model – The prebuilt model to process. Click the dropdown arrow on the far right of the field to select an option. This field is required for the step to work. The following model options are available:
From Field – Retrieve the value from a field on the record.
Is Base64 checkbox – Specify if the retrieved value from a field on the record is Base64 encoded.
Using an OCR Analyze step
The image below shows a receipt used as an example.
To use an OCR Analyze step, follow the instructions below:
1. Click on the play icon on the Calculator step after the OCR Analyze destination step as highlighted in the image below:
2. A Test pop up page will appear. Click the highlighted area in the image below to upload the file.
3. Click the Test button as shown in the image below.
The image below shows the output from the OCR Analyze destination step.
In addition, there is a confidence field which confirms that the value is accurate. It is a value ranging from zero to 1 and represents a percentage. In this case, the confidence is at 1 meaning the percentage is 100%.