Channel Statistics

The channelstats function is similar to the imagestats function except that it only calculates the normal statistics for each pixel value on a per channel basis.

  • Pixel Statistics (Per Channel)

  • mean pixel value (float16)

  • pixel value standard deviation (float16)

  • pixel value variance (float16)

  • pixel value skew (float16)

  • pixel value kurtosis (float16)

  • entropy of the image (float16)

  • pixel percentiles (min, max, 25th, 50th, and 75th percentile values) (float16)

  • histogram of pixel values (uint32)

Tutorials

To see how the channelstats function can be used while doing exploratory data analysis, check out the EDA Part 1 tutorial.

Exploratory Data Analysis Part 1

How To Guides

There is a how-to guide that applies to the channelstats function.

DataEval API

dataeval.metrics.channelstats(images: Iterable[_SupportsArray[dtype[Any]] | _NestedSequence[_SupportsArray[dtype[Any]]] | bool | int | float | complex | str | bytes | _NestedSequence[bool | int | float | complex | str | bytes]], flags=ImageStat.ALL_PIXELSTATS) → StatsOutput

Calculates pixel statistics for each image per channel

Parameters:

  • images (Iterable[ArrayLike]) – Images to run statistical tests on

  • flags (ImageStat, default ImageStat.ALL_PIXELSTATS) – Statistic(s) to calculate for each image per channel Only flags in the ImageStat.ALL_PIXELSTATS category are supported

Return type:

Dict[str, Any]