Using machine learning to define user controls for photo adjustments

A tangible machine-readable medium in communication with at least one processor, the tangible machine-readable medium storing instructions which, when executed by the at least one processor of a machine, cause the machine to perform operations comprising:

• receiving a new image to be adjusted;
• applying a weight to each reference image of a reference dataset based on a comparison of content of the new image to reference images of a reference dataset;
• generating a plurality of basis styles by applying weighted averages of adjustment parameters corresponding to the weighted reference images to the new image, each of the plurality of basis styles comprising a version of the new image with an adjustment of at least one image control based on the weighted averages of the adjustment parameters of the reference dataset;
• and
• providing the plurality of basis styles on a user interface of a display device.

A system comprising:

• a hardware processor of a machine;
• an image input module to receive a new image to be adjusted;
• a prediction module to
• apply a weight to each reference image of a reference dataset based on a comparison of content of the new image to reference images of a reference dataset, and
• generate, using the hardware processor, a plurality of basis styles by applying weighted averages of adjustment parameters corresponding to the weighted reference images to the new image, each of the plurality of basis styles comprising a version of the new image with an adjustment of at least one image control based on the weighted averages of the adjustment parameters of the reference dataset;
• and
• a user interface module to provide the plurality of basis styles on a user interface of a display device.