Hierarchical deep convolutional neural network for image classification
US-10387773-B2 · Aug 20, 2019 · US
US10885394B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10885394-B2 |
| Application number | US-201916367367-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 28, 2019 |
| Priority date | Jan 19, 2015 |
| Publication date | Jan 5, 2021 |
| Grant date | Jan 5, 2021 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.
Opening claim text (preview).
What is claimed is: 1. A method comprising: accessing an image; identifying, using one or more hardware processors, an object in the image, the identified object being associated with a coarse category; based on the coarse category, analyzing the image to identify a fine category; and causing presentation of information related to the identified fine category. 2. The method of claim 1 , further comprising: determining a bounding box that encompasses the object in the image. 3. The method of claim 1 , further comprising: performing a search for the information related to the identified fine category. 4. The method of claim 1 , wherein the fine category is a sub-category of the coarse category. 5. The method of claim 1 , wherein the fine category is identifiable by a name. 6. The method of claim 1 , further comprising: rotating at least a portion of the image based on orientation. 7. The method of claim 1 , wherein the fine category is identified from a set of available fine categories for the coarse category. 8. A system comprising: one or more hardware processors; and a storage medium storing instructions that; when executed by the one or more hardware processors, causes the one or more hardware processors to perform operations comprising: accessing an image; identifying an object in the image, the identified object being associated with a coarse category; based on the coarse category, analyzing the image to identify a fine category; and causing presentation of information related to the identified fine category. 9. The system of claim 8 , wherein the operations further comprise: determining a bounding box that encompasses the object in the image. 10. The system of claim 8 , wherein the operations further comprise: performing a search for the information related to the identified fine category. 11. The system of claim 8 , wherein the fine category is a sub-category of the coarse category. 12. The system of claim 8 , wherein the fine category is identifiable by a name. 13. The system of claim 8 , wherein the operations further comprise: rotating at least a portion of the image based on orientation. 14. The system of claim 8 , wherein the fine category is identified from a set of available fine categories for the coarse category. 15. A machine-readable storage device storing instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising: accessing an image; identifying an object in the image, the identified object being associated with a coarse category; based on the coarse category, analyzing the image to identify a fine category; and causing presentation of information related to the identified fine category. 16. The machine-readable storage device of claim 15 , wherein the operations further comprise: determining a bounding box that encompasses the object in the image. 17. The machine-readable storage device of claim 15 , wherein the operations further comprise: performing a search for the information related to the identified fine category. 18. The machine-readable storage device of claim 15 , wherein the fine category is a sub-category of the coarse category. 19. The machine-readable storage device of claim 15 , wherein the fine category is identifiable by a name. 20. The machine-readable storage device of claim 15 , wherein the operations further comprise: rotating at least a portion of the image based on orientation.
Obtaining sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title
Distances to closest patterns, e.g. nearest neighbour classification · CPC title
by locating a pattern; Special marks for positioning · CPC title
by using evolutionary computational techniques, e.g. genetic algorithms · CPC title
based on the proximity to a decision surface, e.g. support vector machines · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.