Neural network-based systems and computer-implemented methods for identifying and/or evaluating one or more food items present in a visual input

A system, comprising:

• at least one image capturing device;
• a non-transitory storage memory;
• one or more processors;
• and
• computer program code stored on the non-transitory storage memory and, when executed by the one or more processors, causes the one or more processors to:
• receiving a continuous video stream from at least one camera position over a table configured to receive a plurality of prepared pizzas;
• collecting a plurality of pizza containing video frames of a particular pizza from the video stream;
• applying a first conventional neural network (“CNN”) of a plurality of CNNs to select a set of best pizza containing video frames of the particular pizza from the plurality of pizza containing video frames;
• applying a second CNN of the plurality of CNNs to identify a best pizza containing image of the particular pizza from the set of best pizza containing video frames,
• wherein the second CNN devalues at least one set of a plurality of sets of pizza containing video frames of the particular pizza based on at least one image defects within the identified best pizza containing image of the particular pizza;
• applying the first CNN of the plurality of CNNs to localize at least one pizza portion of the particular pizza in the identified best pizza containing image;
• applying the second CNN of the plurality of CNNs to determine a type of the pizza of the particular pizza from the identified best pizza containing image;
• applying a third CNN of the plurality of CNNs to determine a map of pizza components of the particular pizza by automatically performing pizza image segmentation of the pizza portion based on at least the type of the pizza;
• and
• applying the third CNN of the plurality of CNNs to automatically score the particular pizza based on the determined map of pizza components, comprising:
• dynamically dividing the pizza portion of the identified best image into a plurality of slices;
• dynamically grading one of the plurality of slices of the particular pizza;
• automatically repeating the grading step to grade the remaining slices of the plurality of slices;
• automatically determining a final score of the particular pizza based on the grading of the plurality of slices;
• and
• automatically instructing based on the final score of the particular pizza, one of dispensing of the particular pizza to a customer or discarding the particular pizza.

A non-transitory computer-readable storage medium comprising processor-executable instructions for:

• receiving a continuous video stream from at least one camera position over a table configured to receive a plurality of prepared pizzas;
• collecting a plurality of pizza containing video frames of a particular pizza from the video stream;
• applying a first conventional neural network (“CNN”) of a plurality of CNNs to select a set of best pizza containing video frames of the particular pizza from the plurality of pizza containing video frames;
• applying a second CNN of the plurality of CNNs to identify a best pizza containing image of the particular pizza from the set of best pizza containing video frames,
• wherein the second CNN devalues at least one set of a plurality of sets of pizza containing video frames of the particular pizza based on at least one image defects within the identified best pizza containing image of the particular pizza;
• applying the first CNN of the plurality of CNNs to localize at least one pizza portion of the particular pizza in the identified best pizza containing image;
• applying the second CNN of the plurality of CNNs to determine a type of the pizza of the particular pizza from the identified best pizza containing image;
• applying a third CNN of the plurality of CNNs to determine a map of pizza components of the particular pizza by automatically performing pizza image segmentation of the pizza portion based on at least the type of the pizza;
• and
• applying the third CNN of the plurality of CNNs to automatically score the particular pizza based on the determined map of pizza components, comprising:
• dynamically dividing the pizza portion of the identified best image into a plurality of slices;
• dynamically grading one of the plurality of slices of the particular pizza;
• automatically repeating the grading step to grade the remaining slices of the plurality of slices;
• automatically determining a final score of the particular pizza based on the grading of the plurality of slices;
• and
• automatically instructing based on the final score of the particular pizza, one of dispensing of the particular pizza to a customer or discarding the particular pizza.