Segment Images
🤖 AI Drafted (Not reviewed)
Detect foreground document regions and emit cropped segment derivatives.
|
|
| Tool id |
segment_images |
| Category |
transform |
| Uses a language model |
no |
| Needs a generative model |
no |
| Runs over many items |
yes |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Files (files) |
files |
yes |
Image files to segment. |
Documents (documents) |
json |
no |
Document metadata for preview-editor edit-chain updates. |
What it emits
| Port |
Type |
Required |
What it is |
Segment Files (output_files) |
files |
— |
Cropped segment image files. |
Segments (segments) |
json |
— |
Detected segment bounding boxes. |
Options
| Option |
Type |
Default |
What it does |
compression_quality |
integer |
90 |
JPEG/WebP compression quality. |
max_segments |
integer |
20 |
Maximum number of regions to emit. |
method |
string |
foreground |
Segmentation method. One of: foreground, page. |
min_area |
integer |
100 |
Minimum segment area in pixels. |
output_dir |
string |
— |
Optional output directory. Defaults to a temp directory. |
output_format |
string |
png |
Derived segment image format. One of: jpg, png, tiff, webp. |
threshold |
integer |
28 |
Foreground threshold for document-region detection. |
The prompt it sends
This tool does not send a prompt — it does its work in code.