System and method for identifying object information in image or video data

A system for identifying a product in an image and outputting an identifier of a target, comprising:

• a database server executed by one or more storage devices for storing image data comprising real-time inventory images and historical images of each product type;
• a data analytics system comprising one or more convolutional neural networks;
• and
• a standard dashboard;
• wherein the data analytics system comprises a non-transitory computer-readable medium and instructions that when executed by the non-transitory computer-readable medium cause the non-transitory computer-readable medium to perform operations comprising:
• receiving an input unlabeled image, via application programming interface from a recording device or an external database;
• generating, via an augmentation module of the data analytics system, an augmented unlabeled image;
• training an encoder neural network of the data analytics system with the augmented unlabeled image to extract features and generate an output labeled image;
• training a plurality of projection heads with the output labeled image to map features to a space where contrastive loss is applied and to perform types and sub-types level classification;
• and
• generating a descriptor of the object based on the types and sub-types level classification;
• and
• wherein the standard dashboard is configured to output the descriptor of the object.