INFORMATION OUTPUT METHOD AND INFORMATION PROCESSING DEVICE

• US 20170124422A1
• Filed: 10/26/2016
• Published: 05/04/2017
• Est. Priority Date: 10/29/2015
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: TADA, Takatoshi
• Granted Patent: US 10,592,724 B2
• Time in Patent Office: Days
• CPC Class Codes: G06T 15/20 Perspective computation
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06V 10/243 by compensating for image skew or non-uniform image deformations
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 20/64 Three-dimensional objects

Abstract

A method for outputting information corresponding to an object includes identifying a shape of the object, receiving an image of a label corresponding to the object, generating a three-dimensional model of the object to which the image of the label is virtually attached based on the identified shape of the object and the image of the label, generating a plurality of pieces of two-dimensional image data corresponding to the three-dimensional model of the object, the plurality of pieces of two-dimensional image data being generated by changing a virtual capturing position for capturing the three-dimensional model of the object, comparing input image data to the plurality of pieces of two-dimensional image data and outputting the information corresponding to the object based on a positive comparison between the input image data and at least one of the plurality of pieces of two-dimensional image data.

Claims

1. A method for outputting information corresponding to an object, the method comprising:

identifying a shape of the object;

receiving an image of a label corresponding to the object;

generating a three-dimensional model of the object to which the image of the label is virtually attached based on the identified shape of the object and the image of the label;

generating, by circuitry, a plurality of pieces of two-dimensional image data corresponding to the three-dimensional model of the object, the plurality of pieces of two-dimensional image data being generated by changing a virtual capturing position for capturing the three-dimensional model of the object;

comparing input image data to the plurality of pieces of two-dimensional image data; and

outputting the information corresponding to the object based on a positive comparison between the input image data and at least one of the plurality of pieces of two-dimensional image data.

2. The method of claim 1, wherein the plurality of pieces of two-dimensional image data are generated by changing an illumination condition for capturing the three-dimensional model of the object.

3. The method of claim 2, wherein the changing of the illumination condition includes changing at least one of a position of light sources, a number of the light sources, and a brightness of light output from the light sources.

4. The method of claim 1, wherein the plurality of pieces of two-dimensional image data are generated by changing a first angle and a second angle of the virtual capturing position for capturing the three-dimensional model of the object.

5. The method of claim 4, wherein

a first virtual line passes through a center of the three-dimensional model of the object along a length of the three-dimensional model of the object, a second virtual line is perpendicular to the first virtual line and passes through a center of the virtually attached image of the label, a third virtual line is perpendicular to both the first virtual line and the second virtual line, and a point of intersection of the first virtual line, the second virtual line, and the third virtual line is an origin point,

the first angle corresponds to an angle formed at the origin point between a fourth virtual line corresponding to a line of view from a virtual capturing device and the second virtual line, the fourth virtual line corresponding to a virtual line formed on a plane formed by the first virtual line and the second virtual line, and

the second angle corresponds to an angle formed at the origin point between a fifth virtual line corresponding to the line of view from the virtual capturing device and the second virtual line, the fifth virtual line corresponding to a virtual line formed on a plane formed by the second virtual line and the third virtual line.

6. The method of claim 5, wherein when the first angle is increased, a change in the second angle is decreased for capturing the three-dimensional model of the object to generate the plurality of pieces of two-dimensional image data.

7. The method of claim 5, wherein when the first angle is decreased, a change in the second angle is increased for capturing the three-dimensional model of the object to generate the plurality of pieces of two-dimensional image data.

8. The method of claim 4, further comprising:

generating a greater number of pieces of two-dimensional image data when the first angle is increased compared to when the first angle is decreased.

9. The method of claim 1, wherein the plurality of pieces of two-dimensional image data are generated by changing the virtual capturing position for capturing the three-dimensional model of the object by a predetermined distance.

10. The method of claim 1, wherein

the shape of the object is curved, and

the image of the label is virtually attached to a curved portion of the object.

11. The method of claim 1, further comprising:

assigning a corresponding reference image number to each of the plurality of pieces of two-dimensional image data; and

storing the plurality of pieces of two-dimensional image data in a memory by associating the plurality of pieces of two-dimensional image data with the corresponding reference image number.

12. The method of claim 1, further comprising:

generating a corresponding evaluation value for each of the plurality of pieces of two-dimensional image data based on a comparison between the input image data and the plurality of pieces of two-dimensional image data.

13. The method of claim 12, further comprising:

assigning a corresponding weight to the corresponding evaluation value to generate a corresponding score for each of the plurality of pieces of two-dimensional image data based on a corresponding angle of the virtual capturing position for capturing the three-dimensional model of the object.

14. The method of claim 13, further comprising:

determining the positive comparison between the input image data and the at least one of the plurality of pieces of two-dimensional image data based on the corresponding score generated for each of the plurality of pieces of two-dimensional image data.

15. The method of claim 13, further comprising:

determining the positive comparison between the input image data and the at least one of the plurality of pieces of two-dimensional image data when the corresponding score exceeds a predetermined threshold.

16. The method of claim 1, further comprising:

reading a label area corresponding to the object based on a received object code; and

identifying a reference point on the object to virtually attach the image of the label based on the read label area.

17. The method of claim 1, further comprising:

registering the information corresponding to the object, a label image number of the image of the label, and a corresponding object code in a memory.

18. The method of claim 1, further comprising:

outputting information indicating that the object is not identified in the input image data when there is no positive comparison between the input image data and the plurality of pieces of two-dimensional image data.

19. An apparatus for generating a plurality of pieces of two-dimensional data, the apparatus comprising:

circuitry configured to;

identify a shape of an object,

receive an image of a label corresponding to the object,

generate a three-dimensional model of the object to which the image of the label is virtually attached based on the identified shape of the object and the image of the label,

generate the plurality of pieces of two-dimensional image data corresponding to the three-dimensional model of the object, the plurality of pieces of two-dimensional image data being generated by changing a virtual capturing position for capturing the three-dimensional model of the object, and

store the plurality of pieces of two-dimensional image data into a memory.

20. A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a computer, cause a computer to execute a process for generating a plurality of pieces of two-dimensional data, the process comprising:

identifying a shape of an object;

receiving an image of a label corresponding to the object;

generating a three-dimensional model of the object to which the image of the label is virtually attached based on the identified shape of the object and the image of the label;

generating the plurality of pieces of two-dimensional image data corresponding to the three-dimensional model of the object, the plurality of pieces of two-dimensional image data being generated by changing a virtual capturing position for capturing the three-dimensional model of the object; and

storing the plurality of pieces of two-dimensional image data into a memory.