Image

The Image component is an operator component that allows users to manipulate image files. It can carry out the following tasks:

Concat
Crop
Resize
Draw Classification
Draw Detection
Draw Keypoint
Draw OCR
Draw Instance Segmentation
Draw Semantic Segmentation

Release Stage

Alpha

Configuration

The component definition and tasks are defined in the definition.yaml and tasks.yaml files respectively.

Supported Tasks

Concat

Concatenate images horizontally or vertically. All images must have the same width and height. If grid-width and grid-height are not provided, the images will be concatenated to a square grid.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_CONCAT`
Images (required)	`images`	array	Input images.
Grid Width	`grid-width`	integer	Grid width. If `grid-width` is provided, `grid-height` will be ignored.
Grid Height	`grid-height`	integer	Grid height. If `grid-height` is provided, `grid-width` will be ignored.
Padding	`padding`	integer	Padding between images. If `padding` is provided, it will be applied to all four sides of the image.

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Crop

Crop image to the specified size.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_CROP`
Image (required)	`image`	string	Input image.
Corner Radius	`corner-radius`	integer	Radius from the corner of the image to crop the image. If `corner-radius` is provided, `circle-radius` will be ignored. If the `corner-radius` is larger than half of min(width, height), the min(width, height) will be applied to `corner-radius` .
Circle Radius	`circle-radius`	integer	Radius from the center of the circle to crop the image. If `circle-radius` is provided, `corner-radius` will be ignored. If the `circle-radius` is larger than half of min(width, height), the min(width, height) will be applied to `circle-radius`.
Top Offset	`top-offset`	integer	Top offset of the crop.
Right Offset	`right-offset`	integer	Right offset of the crop.
Bottom Offset	`bottom-offset`	integer	Bottom offset of the crop.
Left Offset	`left-offset`	integer	Left offset of the crop.

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Resize

Resize image to the specified size.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_RESIZE`
Image (required)	`image`	string	Input image.
Ratio	`ratio`	number	Resize ratio (e.g., 0.5 for half size, 2 for double size) to resize the image. If ratio is provided, width and height will be ignored.
Width	`width`	integer	Width of the output image.
Height	`height`	integer	Height of the output image.

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw Classification

Draw classification result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_CLASSIFICATION`
Category (required)	`category`	string	The predicted category of the input.
Image (required)	`image`	string	Input image.
Show Score	`show-score`	boolean	Show model confidence score on each instance.
Score (required)	`score`	number	The confidence score of the predicted category of the input.

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw Detection

Draw detection result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_DETECTION`
Image (required)	`image`	string	Input image.
Objects (required)	`objects`	array[object]	A list of detected objects.
Show Score	`show-score`	boolean	Show model confidence score on each instance.

Input Objects in Draw Detection

Objects

A list of detected objects.

Field	Field ID	Type	Note
Bounding box	`bounding-box`	object	The detected bounding box in (left, top, width, height) format.
Category	`category`	string	The predicted category of the bounding box.
Score	`score`	number	The confidence score of the predicted category of the bounding box.

Bounding Box

The detected bounding box in (left, top, width, height) format.

Field	Field ID	Type	Note
Height	`height`	number	Bounding box height value
Left	`left`	number	Bounding box left x-axis value
Top	`top`	number	Bounding box top y-axis value
Width	`width`	number	Bounding box width value

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw Keypoint

Draw keypoint result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_KEYPOINT`
Image (required)	`image`	string	Input image.
Objects (required)	`objects`	array[object]	A list of keypoint objects, a keypoint object includes all the pre-defined keypoints of a detected object.
Show Score	`show-score`	boolean	Show model confidence score on each instance.

Input Objects in Draw Keypoint

Objects

A list of keypoint objects, a keypoint object includes all the pre-defined keypoints of a detected object.

Field	Field ID	Type	Note
Bounding Box	`bounding-box`	object	The detected bounding box in (left, top, width, height) format.
Keypoints	`keypoints`	array	A keypoint group is composed of a list of pre-defined keypoints of a detected object.
Score	`score`	number	The confidence score of the predicted object.

Keypoints

A keypoint group is composed of a list of pre-defined keypoints of a detected object.

Field	Field ID	Type	Note
Visibility Score	`v`	number	visibility score of the keypoint.
X Coordinate	`x`	number	x coordinate of the keypoint.
Y Coordinate	`y`	number	y coordinate of the keypoint.

Bounding Box

The detected bounding box in (left, top, width, height) format.

Field	Field ID	Type	Note
Height	`height`	number	Bounding box height value
Left	`left`	number	Bounding box left x-axis value
Top	`top`	number	Bounding box top y-axis value
Width	`width`	number	Bounding box width value

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw OCR

Draw OCR result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_OCR`
Image (required)	`image`	string	Input image.
Objects (required)	`objects`	array[object]	A list of detected bounding boxes.
Show Score	`show-score`	boolean	Show model confidence score on each instance.

Input Objects in Draw OCR

Objects

A list of detected bounding boxes.

Field	Field ID	Type	Note
Bounding Box	`bounding-box`	object	The detected bounding box in (left, top, width, height) format.
Score	`score`	number	The confidence score of the predicted object.
Text	`text`	string	Text string recognised per bounding box.

Bounding Box

The detected bounding box in (left, top, width, height) format.

Field	Field ID	Type	Note
Height	`height`	number	Bounding box height value
Left	`left`	number	Bounding box left x-axis value
Top	`top`	number	Bounding box top y-axis value
Width	`width`	number	Bounding box width value

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw Instance Segmentation

Draw instance segmentation result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_INSTANCE_SEGMENTATION`
Image (required)	`image`	string	Input image.
Objects (required)	`objects`	array[object]	A list of detected instance bounding boxes.
Show Score	`show-score`	boolean	Show model confidence score on each instance.

Input Objects in Draw Instance Segmentation

Objects

A list of detected instance bounding boxes.

Field	Field ID	Type	Note
Bounding Box	`bounding-box`	object	The detected bounding box in (left, top, width, height) format.
Category	`category`	string	The predicted category of the bounding box.
RLE	`rle`	string	Run Length Encoding (RLE) of instance mask within the bounding box.
Score	`score`	number	The confidence score of the predicted instance object.

Bounding Box

The detected bounding box in (left, top, width, height) format.

Field	Field ID	Type	Note
Height	`height`	number	Bounding box height value
Left	`left`	number	Bounding box left x-axis value
Top	`top`	number	Bounding box top y-axis value
Width	`width`	number	Bounding box width value

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.

Draw Semantic Segmentation

Draw semantic segmentation result on the image.

Input	Field ID	Type	Description
Task ID (required)	`task`	string	`TASK_DRAW_SEMANTIC_SEGMENTATION`
Image (required)	`image`	string	Input image.
Stuffs (required)	`stuffs`	array[object]	A list of RLE binary masks.

Input Objects in Draw Semantic Segmentation

Stuffs

A list of RLE binary masks.

Field	Field ID	Type	Note
Category	`category`	string	Category text string corresponding to each stuff mask.
RLE	`rle`	string	Run Length Encoding (RLE) of each stuff mask within the image.

Output	Field ID	Type	Description
Image	`image`	image/png	Output image.