Skip to main content

Visual Text Recognition

The Visual Text Recognition block is used to recognize text in an image. The block must accept an image as input and output the text that is recognized in the image. Result is return as primitive type visionObservation.

The configuration for this block is as follows:

Languages​

The language(s) that the block will recognize.

Result Confirmer​

turning this option on will show a confirmation dialog before the result is sent to the next block. This is useful when you want to make sure the result is correct before sending it to the next block.

Confidence Threshold​

This block will return a list of possible results, with a confidence score for each result. This option allows you to specify the minimum confidence score for a result to be considered valid. For example, if you set this option to 0.5, then only results with a confidence score of 0.5 or higher will be considered valid.