Component identification

A non-transitory computer-readable medium tangibly encoding a computer program operable to cause a data processing apparatus to perform operations comprising:

• obtaining a test image captured by a camera of a mobile device, the test image including a test component;
• processing the test image using a machine learning model, wherein the machine learning model has been trained by
• obtaining a three-dimensional (3D) model file representing a 3D model of a training component,
• generating a plurality of images of the training component based on the 3D model file representing the 3D model of the training component, wherein the plurality of images differ from one another in at least one of orientation, background, or texture,
• determining locations of the training component in each of the plurality of images, and
• training the machine learning model using, as training data, the plurality of images and the locations of the training component, wherein the machine learning model is trained to detect the training component in photographs captured by mobile devices;
• and
• presenting, at the mobile device, one or more candidate identities of the test component based on an output of the machine learning model, wherein presenting the one or more candidate identities comprises:
• determining a similarity between an image of a first candidate component and an image of a second candidate component, and
• determining, based on the similarity and based on the first candidate component and the second candidate component being included in separate products, to present at the mobile device a first candidate identity corresponding to the first candidate component.

A system comprising:

• one or more processors;
• and
• one or more computer-readable mediums encoding instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• obtaining a test image captured by a camera of a mobile device, the test image including a test component;
• processing the test image using a machine learning model, wherein the machine learning model has been trained by
• obtaining a three-dimensional (3D) model file representing a 3D model of a training component,
• generating a plurality of images of the training component based on the 3D model file representing the 3D model of the training component, wherein the plurality of images differ from one another in at least one of orientation, background, or texture,
• determining locations of the training component in each of the plurality of images, and
• training the machine learning model using, as training data, the plurality of images and the locations of the training component, wherein the machine learning model is trained to detect the training component in photographs captured by mobile devices;
• and
• presenting, at the mobile device, one or more candidate identities of the test component based on an output of the machine learning model, wherein presenting the one or more candidate identities comprises:
• determining a similarity between an image of a first candidate component and an image of a second candidate component, and
• determining, based on the similarity and based on the first candidate component and the second candidate component being included in separate products, to present at the mobile device a first candidate identity corresponding to the first candidate component.