An optical character detection accessor. This accessor takes an input image and attempts to recognize text in the image. It considers the whole image, so it works best if the image is pre-cropped to the portion containing only text.
This accessor uses Tesseract.js, an open source optical character recognition tool, available under the Apache 2.0 license. http://tesseract.projectnaptha.com/
- Version:
- $$Id$$
- Source:
Inputs:
| Name | Type | Description |
|---|---|---|
input |
An image | |
(JSON) |
options A JSON object of options. See: https://github.com/naptha/tesseract.js/blob/master/docs/tesseract_parameters.md |
Outputs:
| Name | Type | Description |
|---|---|---|
text |
String | A string of any text recognized in the image. |