Systems and Methods of Building and Using an Image Catalog

A computer system for managing an image catalog, comprising:

• one or more processors;
• memory;
• and
• one or more programs stored in the memory and configured for execution by the one or more processors, the one or more programs comprising instructions for, at the computer system:
• receiving reduced-resolution versions of one or more images stored in an image database of an external service distinct from the one or more servers, and receiving a specified subject matter for the one or more images;
• for each of the received reduced-resolution versions, creating a respective index entry in the image catalog, the respective index entry comprising one or more keywords extracted from the respective reduced-resolution version by performing semantic analysis on the respective reduced-resolution version using a convolutional neural network trained on images corresponding to the specified subject matter;
• receiving a query from a user;
• matching the query to a first index entry in the image catalog, the first index entry created for a first reduced-resolution version of a first full-resolution image stored in the image database of the external service;
• retrieving the first full-resolution image from the image database of the external service;
• and
• transmitting the first full-resolution image to the user.

A non-transitory computer readable storage medium storing one or more programs configured for execution by one or more processors of a computer system for managing an image catalog, the one or more programs comprising instructions for:

• receiving reduced-resolution versions of one or more images stored in an image database of an external service distinct from the one or more servers, and receiving a specified subject matter for the one or more images;
• for each of the received reduced-resolution versions, creating a respective index entry in the image catalog, the respective index entry comprising one or more keywords extracted from the respective reduced-resolution version by performing semantic analysis on the respective reduced-resolution version using a convolutional neural network trained on images corresponding to the specified subject matter;
• receiving a query from a user;
• matching the query to a first index entry in the image catalog, the first index entry created for a first reduced-resolution version of a first full-resolution image stored in the image database of the external service;
• retrieving the first full-resolution image from the image database of the external service;
• and
• transmitting the first full-resolution image to the user.