Back to results
US 8,798,375 B1Granted
Object recognition in images
AssigneeGoogle Inc.
InventorsEdward Y. Chang, Zhiyu Wang, Dingyin Xia
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for labeling images. In one aspect, a method includes automatically identifying an object in an image using a deep model-based and data-driven hybrid architecture.
Claims20
A method implemented by data processing apparatus, the method comprising:
- dividing, by the data processing apparatus, an image into a plurality of first sub-images;
- comparing, by the data processing apparatus, each first sub-image, using values representing one or more data feature dimensions in the first sub-image, with a plurality of second sub-images in a sub-image library to determine which second sub-images are within a threshold of similarity to the first sub-image, each of the second sub-images having values representing a plurality of model feature dimensions;
- creating, by the data processing apparatus, a first image vector space, each data point in the first image vector space representing a number of first sub-images that are within the threshold of similarity to a second sub-image;
- combining, by the data processing apparatus, the first image vector space and a second image vector space and mapping the combination to an object vector space in a plurality of object vector spaces, each object vector space being labeled;
- and
- associating the image with the label of the mapped object vector space.
3 more elements
A system, comprising:
- a data processing apparatus;
- and
- a non-transitory computer storage medium in data communication with the data processing apparatus and storing instructions that when executed by the data processing apparatus cause the data processing apparatus to perform operations comprising:
- dividing an image into a plurality of first sub-images;
- comparing each first sub-image, using values representing one or more data feature dimensions in the first sub-image, with a plurality of second sub-images in a sub-image library to determine which second sub-images are within a threshold of similarity to the first sub-image, each of the second sub-images having values representing a plurality of model feature dimensions;
- creating a first image vector space, each data point in the first image vector space representing a number of first sub-images that are within the threshold of similarity to a second sub-image;
- combining the first image vector space and a second image vector space and mapping the combination to an object vector space in a plurality of object vector spaces, each object vector space being labeled;
- and
- associating the image with the label of the mapped object vector space.
6 more elements
A non-transitory computer storage medium in data communication with the data processing apparatus and storing instructions that when executed by the data processing apparatus cause the data processing apparatus to perform operations comprising:
- dividing an image into a plurality of first sub-images;
- comparing each first sub-image, using values representing one or more data feature dimensions in the first sub-image, with a plurality of second sub-images in a sub-image library to determine which second sub-images are within a threshold of similarity to the first sub-image, each of the second sub-images having values representing a plurality of model feature dimensions;
- creating a first image vector space, each data point in the first image vector space representing a number of first sub-images that are within the threshold of similarity to a second sub-image;
- combining the first image vector space and a second image vector space and mapping the combination to an object vector space in a plurality of object vector spaces, each object vector space being labeled;
- and
- associating the image with the label of the mapped object vector space.
3 more elements
Dependencies are inferred from the claim text.