Configure Image Properties Detection
Image properties detection is a type of image detection that detects the key properties/attributes of the image such as colors. For example, dominant colors were detected from the image below with detailed properties about the percentage of image pixels with each particular color, the palette number and the RGB composition. The properties are the foundation of computer vision models for various ML tasks.
This block will summarize the color breakdown of the image into the desired number of dominant colors as specified by the Result Limit setting (default is 10), then calculate score and pixel fraction, and break down the RGB components of the color category. This may be helpful in identifying under or over exposed images or outliers in data.
This block uses the Detect Image Properties Google Cloud Vision API. Responses are returned in Plainsight format. See the docs for more information:
To add an image properties detection block to your pipeline:
- 1.Navigate to the "Pipeline Blocks" tab.
- 2.Under the Prediction section, click on the Image Properties box to configure this processing block. You may need to click "Show All" or use the search box to find the block.
- 3.Enter the desired Result Limit between 1-50. This will limit the number of results returned per image for this block.
- 4.Click "Add to Pipeline" to add the block to your pipeline. This will bring you back to the "Pipeline Blocks" tab. From there you can add additional blocks and drag and drop to rearrange around other blocks as needed.
Image file size should not exceed 20 MB.
{
"type": "select",
"children": {
"red": {
"type": "regression",
"children": {},
"data": 154.0
},
"blue": {
"type": "regression",
"children": {},
"data": 3.0
},
"green": {
"type": "regression",
"children": {},
"data": 36.0
},
"pixel_fraction": {
"type": "regression",
"children": {},
"data": 0.01719697006046772
}
},
"data": {
"selected": "dominant_color"
},
"score": 0.2203129380941391
}
Last modified 5mo ago