Information processing apparatus and information processing method

Patent metadata

Field	Value
Publication number	US-10891765-B2
Application number	US-201716081235-A
Country	US
Kind code	B2
Filing date	Jan 20, 2017
Priority date	Apr 11, 2016
Publication date	Jan 12, 2021
Grant date	Jan 12, 2021

Abstract

There is provided an information processing apparatus and an information processing method, the information processing apparatus including: a display size decision unit configured to decide a display size of data that is based on learning of a label corresponding to a class, on the basis of a distance between a position of the data arranged on the basis of a likelihood vector obtained by recognition of the data, and a position of a class to which the data belongs; and a communication control unit configured to cause the display size to be transmitted.

First claim

The invention claimed is:

1. An information processing apparatus comprising:
a display size decision unit configured to decide a display size of each piece of a plurality of pieces of image data that is based on learning of a label corresponding to a class into which a selected piece among the plurality of pieces of image data is classified, wherein the display size of each respective piece of the image data is decided according to a respective likelihood vector obtained by recognition of the image data, the respective likelihood vector indicating a distance between a position of the respective piece of the image data arranged based on the recognition of the image data and a position of the class into which the selected piece of the image data is classified; and
a communication control unit configured to cause the decided display size of each piece of the image data to be transmitted,
wherein the display size decision unit and the communication control unit are each implemented via at least one processor.

2. The information processing apparatus according to claim 1 , wherein the display size decision unit decides the display size such that the display size becomes larger as the distance between the respective piece of image data and the position of the class into which the selected piece of image data is classified becomes larger.

3. The information processing apparatus according to claim 1 , wherein the display size decision unit decides the display size further on a basis of a radius of a circle indicating a range of the class.

4. The information processing apparatus according to claim 3 , wherein the display size decision unit decides the display size such that the display size becomes larger as a ratio of the distance with respect to the radius becomes larger.

5. The information processing apparatus according to claim 3 , wherein the display size decision unit decides the display size such that the display size becomes larger in a case where a ratio of the distance with respect to the radius is larger than a predetermined threshold value.

6. The information processing apparatus according to claim 1 , further comprising:
an arrangement control unit configured to arrange the image data,
wherein the arrangement control unit arranges the image data by generating a graph using the class and the image data as vertexes, and
wherein the arrangement control unit is implemented via at least one processor.

7. The information processing apparatus according to claim 6 , wherein the arrangement control unit generates the graph on a basis of a mechanical model.

8. The information processing apparatus according to claim 7 , wherein the arrangement control unit allocates force that is based on the likelihood vector, to a side between the class and the image data.

9. The information processing apparatus according to claim 8 , wherein the arrangement control unit allocates the force such that the force to be allocated to the side between the class and the image data becomes larger as a likelihood related to the class in the likelihood vector becomes larger.

10. The information processing apparatus according to claim 6 , wherein the arrangement control unit allocates, to a side between classes, force that is based on a similarity degree between the classes.

11. The information processing apparatus according to claim 10 , wherein the arrangement control unit allocates the force such that the force to be allocated to the side between the classes becomes larger as the similarity degree between the classes becomes larger.

12. The information processing apparatus according to claim 1 , further comprising:
a display control unit configured to cause the image data to be displayed in the display size,
wherein the display control unit is implemented via at least one processor.

13. The information processing apparatus according to claim 1 , wherein the selected piece of the image data is enlarged upon selection until the label is affixed to the selected piece of the image data.

14. An information processing apparatus comprising:
a receiving unit configured to receive a display size of each piece of a plurality of pieces of image data that is based on learning of a label corresponding to a class into which a selected piece among the plurality of pieces of image data is classified, wherein the display size of each respective piece of the image data is decided according to a respective likelihood vector obtained by recognition of the image data, the respective likelihood vector indicating a distance between a position of the respective piece of the image data arranged based on the recognition of the image data and a position of the class into which the selected piece of the image data is classified; and
a processing unit configured to perform processing on a basis of the decided display size of the image data,
wherein the receiving unit and the processing unit are each implemented via at least one processor.

15. An information processing method comprising:
deciding, by a processor, a display size of each piece of a plurality of pieces of image data that is based on learning of a label corresponding to a class into which a selected piece among the plurality of pieces of image data is classified, wherein the display size of each respective piece of the image data is decided according to a respective likelihood vector obtained by recognition of the image data, the respective likelihood vector indicating a distance between a position of the respective piece of the image data arranged based on the recognition of the image data and a position of the class into which the selected piece of the image data is classified; and
causing the decided display size of the image data to be transmitted.

16. An information processing apparatus comprising:
an input unit configured to receive a change of a display target; and
a display size decision unit configured to decide, in response to the change of the display target, a display size of each piece of a plurality of pieces of image data that is based on learning of a label corresponding to a class into which the display target is classified, wherein the display size of each respective piece of the image data is decided according to a respective likelihood vector obtained by recognition of the image data, the respective likelihood vector indicating a distance between a position of the respective piece of the image data arranged based on the recognition of the image data, and a position of a class into which the respective piece of the image data is classified based on the learning of the label corresponding to the class into which the display target is classified,
wherein the input unit and the display size decision unit are each implemented via at least one processor.

17. An information processing method comprising:
receiving a change of a display target; and
deciding, by a processor, in response to the change of the display target, a display size of each piece of a plurality of pieces of image data that is based on learning of a label corresponding to a class into which the display target is classified, wherein the display size of each respective piece of the image data is decided according to a respective likelihood vector obtained by recognition of the image data, the respective likelihood vector indicating a distance between a position of the respective piece of the image data arranged based on the recognition of the image data and a position of a class into which the respective piece of the image data is classified based on the learning of the label correspondi

Assignees

• Sony Corp

Inventors

• OOBUCHI Yukio
• Ide Naoki
• Fukui Akira
• Kobayashi Yoshiyuki
• Takamatsu Shingo

Classifications

• G06F16/5866 Primary

  using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title

• G06T11/26

  Drawing of charts or graphs · CPC title

• G06F18/2431

  Multiple classes · CPC title

• G06F18/2411

  based on the proximity to a decision surface, e.g. support vector machines · CPC title

• G06N99/00

  Subject matter not provided for in other groups of this subclass · CPC title