pyflink.multimodal.operators.image_quality_score#

image_quality_score(*columns, concurrency=None)[source]#

Create an image quality scoring UDF (Laplacian + contrast + colorfulness-based).

Requires pip install numpy. This is a scalar UDF that processes one image at a time. It supports direct call syntax: image_quality_score(col("img")).

Parameters

*columns – Optional image column(s). When provided, the UDF is applied directly instead of returning a factory.
concurrency – UDF concurrency. None uses the framework default.

Returns

A UDF that returns a float quality score in [0, 1] combining sharpness, contrast, and colorfulness, or None for null inputs.

Example::

>>> # As a reusable variable
>>> quality = image_quality_score()
>>> df = df.with_column("quality", quality(col("img")))
>>>
>>> # Inline
>>> df = df.with_column("quality", image_quality_score(col("img")))