Retrieve details from an image
Retrieve details from an image.
Application
- Intelligent Document Processing
Inputs (what you have)
| Name | Description | Data Type | Required? | Example |
|---|---|---|---|---|
| Image | Image to retrieve details from. The supported file formats are: .pdf (1st page only), .gif, .tiff, .tif, .jpg, .jpeg, .png, .bmp, .webp. | File | Yes | |
| Schema for extraction | Array of field definitions for extraction | List of objects | Yes |
Schema for extraction - Details
| Name | Description | Data Type | Required? | Example |
|---|---|---|---|---|
| Name | Field key used in the schema for the extracted value | Text(Short) | Yes | full_name |
| Description | Human-readable explanation of what should be extracted for this field | Text(Long) | No | The full name on the drivers license |
| Value type | Data type expected for the value returned by this schema field | Pre-defined choice | Yes | String |
| Occurrence type | Whether this field is required and whether it allows single or multiple values | Pre-defined choice | Yes | Required once |
Outputs (what you get)
| Name | Description | Data Type | Required? | Example |
|---|---|---|---|---|
| All image text | All of the text that was read from the image | Text (Long) | Yes | |
| Image width | The width of the provided image in pixels | Number with decimals | Yes | |
| Image height | The height of the provided image in pixels | Number with decimals | Yes | |
| Schema to extract JSON | A JSON Object that contains all details extracted from the image in the format of the provided schema to extract | Text (Long) | No | |
| Image text orientation degrees | Specific estimated orientation of image based on the angle of the text vs. upright. | Number with decimals | No | |
| Bounding box of all text | Bounding box from the image that contains the pixel-based coordinates from the upper left-most text to the bottom right most text. In the format [x1, y1, x2, y2] in pixels | Text (Short) | No | |
| Bounding box of schema to extract values | Bounding box from the image that contains the pixel-based coordinates from the upper left-most text identified in your schema to extract to the bottom right most text identified in your schema to extract. In the format [x1, y1, x2, y2] in pixels | Text (Short) | No |
Outcomes
| Name | Description |
|---|---|
| Success | This status is selected if the job has successfully completed. |
Requirements
- N/A