Reference documentation and code samples for the Google Cloud Vision Ai V1 Client class ImageSegmentationPredictionResult.
Prediction output format for Image Segmentation.
Generated from protobuf message google.cloud.visionai.v1.ImageSegmentationPredictionResult
Namespace
Google \ Cloud \ VisionAI \ V1Methods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ category_mask |
string
A PNG image where each pixel in the mask represents the category in which the pixel in the original image was predicted to belong to. The size of this image will be the same as the original image. The mapping between the AnntoationSpec and the color can be found in model's metadata. The model will choose the most likely category and if none of the categories reach the confidence threshold, the pixel will be marked as background. |
↳ confidence_mask |
string
A one channel image which is encoded as an 8bit lossless PNG. The size of the image will be the same as the original image. For a specific pixel, darker color means less confidence in correctness of the cateogry in the categoryMask for the corresponding pixel. Black means no confidence and white means complete confidence. |
getCategoryMask
A PNG image where each pixel in the mask represents the category in which the pixel in the original image was predicted to belong to. The size of this image will be the same as the original image. The mapping between the AnntoationSpec and the color can be found in model's metadata. The model will choose the most likely category and if none of the categories reach the confidence threshold, the pixel will be marked as background.
| Returns | |
|---|---|
| Type | Description |
string |
|
setCategoryMask
A PNG image where each pixel in the mask represents the category in which the pixel in the original image was predicted to belong to. The size of this image will be the same as the original image. The mapping between the AnntoationSpec and the color can be found in model's metadata. The model will choose the most likely category and if none of the categories reach the confidence threshold, the pixel will be marked as background.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getConfidenceMask
A one channel image which is encoded as an 8bit lossless PNG. The size of the image will be the same as the original image. For a specific pixel, darker color means less confidence in correctness of the cateogry in the categoryMask for the corresponding pixel. Black means no confidence and white means complete confidence.
| Returns | |
|---|---|
| Type | Description |
string |
|
setConfidenceMask
A one channel image which is encoded as an 8bit lossless PNG. The size of the image will be the same as the original image. For a specific pixel, darker color means less confidence in correctness of the cateogry in the categoryMask for the corresponding pixel. Black means no confidence and white means complete confidence.
| Parameter | |
|---|---|
| Name | Description |
var |
string
|
| Returns | |
|---|---|
| Type | Description |
$this |
|