CPC G06F 40/30 (2020.01) [G06F 18/21 (2023.01); G06F 18/22 (2023.01); G06V 10/761 (2022.01); G06V 30/248 (2022.01); G06V 30/10 (2022.01)] | 20 Claims |
1. A computer-implemented method comprising:
accessing, by a server system, image data comprising a plurality of images and a geographic location where each of the plurality of images was captured;
analyzing the image data for each of the plurality of images using a trained machine learning model configured to determine how likely an image comprises a logo associated with a place, to generate a logo detection score;
determining whether the logo detection score for each of the plurality of images is greater than a predetermined threshold;
generating a name similarity score for one or more images of the plurality of images based on a computed similarity between text extracted from the one or more images and a place name associated with the geographic location where the one or more images were captured;
storing an image as place data associated with a place based on determining that logo detection score associated with the image is higher than the predetermined threshold and based on the name similarity score;
receiving, by the server system, a request for navigation instructions from a computing device;
determining, from the stored images, that there is an image of a destination location for the request for navigation instructions; and
providing the image of the destination location to the computing device to display the image to a driver of a vehicle for navigation.
|