Information processor, information processing method, and program

• US 9,589,341 B2
• Filed: 07/21/2015
• Issued: 03/07/2017
• Est. Priority Date: 09/05/2011
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Sato, Tatsuhito, Gotoh, Tomohiko, Mochizuki, Daisuke, Mochizuki, Shunsuke, Sun, Yun, Okamura, Yuki, Yaeda, Takeshi
• Primary Examiner(s): AHMED, SAMIR ANWAR
• Application Number:
  US14/804,923
• Publication Number:
  US 20150324971A1
• Time in Patent Office: 595 Days
• Field of Search: 382/159, 382/195, 700/47, 700/48
• US Class Current: 1/1
• CPC Class Codes: G06F 18/2411 based on the proximity to a decision surface, e.g. support vector machines
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 2207/10004 Still image; Photographic image
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis

Abstract

An information processor includes a detection unit detecting a photographic subject region of an image, a characteristic amount generation unit generating a characteristic amount including at least positional information of the photographic subject region for each of the detected photographic subject region, a combined characteristic amount generation unit generating a combined characteristic amount corresponding to the image by combining the characteristic amount generated for each of the photographic subject region, and an identification unit identifying a label corresponding to a combination of a photographic subject appearing in the image based on the generated combined characteristic amount.

Claims

1. An information processor, comprising:

circuitry configured to;

detect a plurality of individual regions of an image, wherein each of the plurality of individual regions supports one of a plurality of subjects of the image;

generate a respective characteristic amount for each of the plurality of individual regions detected, wherein the characteristic amount is generated based on one or more of positional information of a respective individual region and an area of the respective individual region;

generate a combined characteristic amount that corresponds to the image, wherein the combined characteristic amount is generated based on a combination of the characteristic amounts for at least two individual regions having largest areas among areas of the plurality of individual regions; and

determine a label that corresponds to a combination of the subjects supported by the at least two individual regions, appearing in the image, based on the generated combined characteristic amount,

wherein the image is a cooked food image having a cooked food as the subject supported by each of the plurality of detected individual regions, and the circuitry is further configured to detect individual plates in the cooked food image as the individual regions.

2. The information processor according to claim 1, wherein the circuitry is further configured to carry out machine learning based on the label and the combined characteristic amount corresponding to the image for learning as inputs.

3. The information processor according to claim 1, wherein the circuitry is further configured to generate the characteristic amount based on a combination of at least the positional information of the individual regions and an identification result of the subject for each of the plurality of detected individual regions.

4. The information processor according to claim 1, wherein the circuitry is further configured to generate the characteristic amount based on a combination of the at least positional information of the individual regions and an image characteristic of the subject supported by each of the plurality of detected individual regions.

5. The information processor according to claim 1, wherein the circuitry is further configured to detect a shape of the plurality of individual regions and the positional information is detected as being center coordinates for each of the plurality of individual regions.

6. An image processing method, comprising:

detecting at least a relative area and positional information for each of a plurality of individual regions of an image, each of the plurality of individual regions appearing in the image as individually supporting one of a plurality of subjects;

generating a respective characteristic amount for each of the plurality of detected individual regions, wherein the characteristic amount is generated based on one or more of the positional information of a respective individual region and the relative area of the respective individual region;

generating a combined characteristic amount corresponding to the image, wherein the combined characteristic amount is generated by combining the characteristic amount generated for at least two individual regions having largest relative areas among relative areas of the plurality of individual regions; and

determining a label corresponding to a combination of the subjects supported by the at least two individual regions, appearing in the image, based on the generated combined characteristic amount,

wherein the image is a cooked food image having a cooked food as the subject supported by each of the plurality of detected individual regions, and the individual plates in the cooked food image is detected as the individual regions.

7. The method according to claim 6, wherein generating the characteristic amount includes combining at least the positional information of the individual regions and an identification result of the subject for each of the detected individual regions.

8. The method according to claim 6, wherein generating the characteristic amount includes combining at least the positional information of the individual regions and an image characteristic of the subject supported by each of the plurality of individual detected regions.

9. The method according to claim 6, further comprising detecting a shape for the plurality of individual regions and wherein the positional information is detected as being center coordinates for each of the plurality of individual regions.

10. A non-transitory computer-readable medium having a set of computer-executable instructions embodied thereon that, when executed, cause a computer to perform operations, comprising:

detecting at least a relative area and positional information for each of a plurality of individual regions of an image, each of the plurality of individual regions appearing in the image as individually supporting one of a plurality of subjects;

generating a respective characteristic amount for each of the plurality of detected individual regions, wherein the characteristic amount is generated based on one or more of the positional information of a respective individual region and the relative area of the respective individual region;

generating a combined characteristic amount corresponding to the image, wherein the combined characteristic amount is generated by combining the characteristic amount generated for at least two subjects supported by the individual regions having largest relative areas among relative areas of the plurality of individual regions; and

determining a label corresponding to a combination of the subjects supported by the at least two individual regions appearing in the image based on the generated combined characteristic amount,

wherein the image is a cooked food image having a cooked food as the subject supported by each of the plurality of detected individual regions, and the individual plates in the cooked food image is detected as the individual regions.