International Business Machines Corporation
ADJUSTING IMAGE CAPTURE PARAMETERS VIA MACHINE LEARNING

Abstract:

Techniques are described with respect to adjusting image capture parameters. An associated method includes constructing an image capture learning model based upon data collection. The method further includes receiving, via at least one lens of an image capture device, at least one captured image from a client and parsing the at least one captured image to identify a plurality of discrete objects. The method further includes assigning a relevancy score to each of the plurality of discrete objects in the at least one captured image based upon analysis of a plurality of contextual inputs in view of the image capture learning model and determining at least one captured image modification option. Each of the at least one captured image modification option includes at least one photographic adjustment to the plurality of discrete objects in the at least one captured image based upon assigned relevancy score.