System and method for using an image to obtain search results

A tangible, non-transitory, computer-readable medium storing computer program instructions that when executed by one or more processors effectuate operations comprising:

• obtaining, with a computer system, a first training set to train a computer vision model, the first training set comprising a first plurality of images of a first object;
• obtaining, with the computer system, a second training set to train the computer vision model, the second training set comprising a second plurality of image of a second object;
• training, with the computer system, the computer vision model to detect the first or second object in a query image based on the first training set and the second training set, wherein training the computer vision model comprises:
• associating with each of the first plurality of images an orientation information that functions to define a location relative to the first object from which each of the first plurality of images was captured and a visual complexity value;
• and
• associating with each of the second plurality of images an orientation information that functions to define a location relative to the second object from which each of the second plurality of images was captured and a visual complexity value;
• receiving, with the computer system, the query image as captured by an imaging device;
• and
• using the training and an orientation information that functions to define a location relative to a query object from which the query image was captured by the imaging device and a visual complexity value of the query object to determine, by the computer system, whether the query object corresponds to the first object, the query object corresponds to the second object, or if additional information is required from a user to assist in making an object recognition determination.