Machine learning based system and method for controlling residual artifacts in media contents to optimize user experience in real-time screen-to-camera communication environment

A machine learning based system for controlling one or more residual artifacts in the one or more media contents to optimize user experience in real-time screen-to-camera communication environment, the machine learning based system comprising:

• one or more hardware processors;
• and
• a memory coupled to the one or more hardware processors, wherein the memory comprises a plurality of subsystems in form of programmable instructions executable by the one or more hardware processors, wherein the plurality of subsystems comprises:
• a color space values conversion subsystem configured to convert one or more Red Green Blue (RGB) values of one or more pixels associated with one or more frames of the one or more media contents to one or more values of one or more orthogonal color space values for the one or more pixels associated with the one or more frames of the one or more media contents;
• an intensity segmenting subsystem configured to segment one or more intensities of the one or more frames associated with the one or more media contents, into at least one of:
• bright region, dark region, and middle region, wherein each region of at least one of:
• the bright region, the dark region, and the middle region, is divided into one or more sub-regions to provide control on modifications to one or more pixel values;
• a symbol generation subsystem configured to generate one or more symbols comprising one or more optimized-frequency regions being detectable and classifiable using a machine learning model;
• a border setting subsystem configured to set a width border of one or more boundaries to pre-determined pixel values along four sides of the one or more frames for encoding one or more data associated with automatic content recognition;
• a boundaries dividing subsystem configured to divide the one or more boundaries into one or more boxes comprising one or more pre-determined sizes, to embed one or more information associated with the one or more symbols;
• a value assigning subsystem configured to assign a bit value of one to the one or more boxes comprising one or more first pre-determined sizes, and a bit value of zero to the one or more boxes comprising one or more second pre-determined sizes, wherein the one or more pixels in the one or more boxes comprising the one or more first pre-determined sizes are flickered;
• a box assembling subsystem configured to assemble one or more boxes comprising at least one of:
• the one or more first pre-determined sizes and the one or more second pre-determined sizes, within an interior of the one or more frames;
• a bit generation subsystem configured to generate one or more bits of the one or more information based on the one or more frames with one or more pre-determined sizes, with the one or more boxes comprising the one or more pre-determined sizes with a pre-determined number of the one or more pixels in the one or more boundaries;
• a redundancy optimizing subsystem configured to optimize redundancy based on a pre-determined number of bits of the one or more information;
• and
• a residual artifact controlling subsystem configured to control the one or more residual artifacts of an encoding process in the one or more media contents by reducing modulation depth based on the optimized redundancy.

A non-transitory computer-readable storage medium having instructions stored therein that when executed by one or more hardware processors, cause the one or more hardware processors to execute operations of:

• converting one or more Red Green Blue (RGB) values of one or more pixels associated with one or more frames of the one or more media contents to one or more values of one or more orthogonal color space values for the one or more pixels associated with the one or more frames of the one or more media contents;
• segmenting one or more intensities of the one or more frames associated with the one or more media contents, into at least one of:
• bright region, dark region, and middle region, wherein each region of at least one of:
• the bright region, the dark region, and the middle region, is divided into one or more sub-regions to provide control on modifications to one or more pixel values;
• generating one or more symbols comprising one or more optimized-frequency regions being detectable and classifiable using a machine learning model;
• setting a width border of one or more boundaries to pre-determined pixel values along four sides of the one or more frames for encoding one or more data associated with automatic content recognition;
• dividing the one or more boundaries into one or more boxes comprising one or more pre-determined sizes, to embed one or more information associated with the one or more symbols;
• assigning a bit value of one to the one or more boxes comprising one or more first pre-determined sizes, and a bit value of zero to the one or more boxes comprising one or more second pre-determined sizes, wherein the one or more pixels in the one or more boxes comprising the one or more first pre-determined sizes are flickered;
• assembling one or more boxes comprising at least one of:
• the one or more first pre-determined sizes and the one or more second pre-determined sizes, within an interior of the one or more frames;
• generating one or more bits of the one or more information based on the one or more frames with one or more pre-determined sizes, with the one or more boxes comprising the one or more pre-determined sizes with a pre-determined number of the one or more pixels in the one or more boundaries;
• optimizing redundancy based on a pre-determined number of bits of the one or more information;
• and
• controlling the one or more residual artifacts of an encoding process in the one or more media contents by reducing modulation depth based on the optimized redundancy.