Identifying object representations in image data

• US 10,445,608 B2
• Filed: 10/25/2017
• Issued: 10/15/2019
• Est. Priority Date: 10/25/2017
• Status: Active Grant

• Current Assignee: Motorola Mobility LLC (Lenovo Group Ltd.)
• Original Assignee: Motorola Mobility LLC (Lenovo Group Ltd.)
• Inventors: Kim, Mina, Desai, Rahul B., Prabhu, Rohan S., Foy, Kevin O.
• Primary Examiner(s): Niu, Feng
• Application Number:
  US15/792,975
• Publication Number:
  US 20190122063A1
• Time in Patent Office: 720 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/17 using hand-held instruments
• CPC Class Codes: G06V 10/22 by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
• CPC Class Codes: G06V 20/20 in augmented reality scenes

Abstract

A method, a device, and a computer program product for identifying objects in image data. The device is enabled to, in response to determining that an object type of a first set of object types is represented in the image data, indicate that the object type is represented in captured image data. The device is further enabled to, in response to determining that no object type of the first set of object types is represented in the image data, determine whether the image data comprises an object characteristic of a specific one of a second set of object types. The device is further enabled to, in response to determining that the image data comprises an object characteristic of the specific one of the second set of object types, indicate that the image data comprises an object characteristic of the specific one of the second set of object types.

Claims

1. A method comprising:

capturing image data using an image sensor of a first device;

determining, by the first device, whether the image data comprises a representation of a first type of object;

in response to determining that the image data does not comprise a representation of the first type of object;

determining that the image data comprises a characteristic of a different type of object based, at least in part, on a focus distance associated with the image data; and

in response to determining that the image data comprises the characteristic of the different type of object, indicating, to a user, that the image data comprises a characteristic of the different type of object.

2. The method of claim 1, further comprising:

in response to determining that the image data does not comprise a representation of the first type of object, determining, by the first device, whether the image data comprises a representation of a second type of object;

wherein said determining that the image data comprises a characteristic of the different type of object is further in response to determining that the image data does no comprise a representation of the second type of object.

3. The method of claim 2, wherein said determining whether the image data comprises the representation of the first type of object comprises determining whether the image data comprises a representation of a barcode and wherein said determining whether the image data comprises the representation of the second type of object comprises determining whether the image data comprises a representation of a face.

4. The method of claim 1, wherein said determining that the image data comprises the characteristic of the different type of object comprises:

determining that the focus distance is less than a threshold; and

in response to said determining that the focus distance is less than the threshold, indicating, in image analysis metadata, that the image data comprises a representation of a third type of object.

5. The method of claim 1, wherein said determining that the image data comprises the characteristic of the different type of object further comprises:

determining that the focus distance is greater than or equal to a threshold; and

in response to determining that the focus distance is greater than or equal to the threshold, indicating, in image analysis metadata, that the image data comprises a representation of a fourth type of object.

6. The method of claim 1, further comprising:

receiving an indication to send a search and analysis request to a second device; and

in response to receiving the indication to send the search and analysis request to the second device, sending the image data and image analysis metadata to the second device, wherein the image analysis metadata comprises a parameter for identifying object metadata associated with the different type of object.

7. The method of claim 6, further comprising:

receiving, from the second device, the object metadata; and

displaying the object metadata on the display of the first device.

8. The method of claim 1, further comprising:

in response to determining that the image data comprises the representation of the first type of object;

identifying text represented in the image data; and

in response to identifying that text is represented in the image data, storing, in image analysis metadata, the text represented in the image data.

9. A device comprising:

an image sensor; and

one or more processors that execute program code, wherein execution of the program code enables the device to;

capture image data using the image sensor;

for each of a first set of object types;

determine whether a selected object type of the first set of object types is represented in the image data; and

in response to a determination that the selected object type of the first set of object types is represented in the image data, indicate that the selected object type of the first set of object types is represented in the image data; and

in response to a determination that no object type of the first set of object types is represented in the image data;

determine whether the image data comprises an object characteristic of a specific one of a second set of object types based, at least in part, on a first criterion; and

in response to a determination that the image data comprises an object characteristic of the specific one of the second set of object types, indicate that the image data comprises an object characteristic of the specific one of the second set of object types.

10. The device of claim 9, wherein the device is further enabled to:

receive an indication that an object represented in the image data should be identified, wherein the type of the object is the specific one of the second set of object types;

in response to receiving an indication that an object represented in the image data should be identified, send the image data and image analysis metadata to a server, wherein the image analysis metadata provides an indication of the specific one of the second set of object types; and

receive, from the server, object metadata associated with the image data, wherein the object metadata is based, at least in part, on the image analysis metadata.

11. The device of claim 9, wherein to determine whether the image data comprises an object characteristic of the specific one of the second set of object types the device:

determines whether a focus distance associated with the image data is less than a first value; and

in response to a determination that the focus distance is less than the first value, indicates, in image analysis metadata, that the image data comprises an object characteristic of the specific one of the second set of object types.

12. The device of claim 11, wherein the device is further enabled to:

in response to a determination that the focus distance is not less than the first value;

determine that the focus distance is greater than or equal to a second value, wherein the second value is greater than or equal to the first value; and

in response to a determination that the focus distance is greater than or equal to the second value, indicate, in the image analysis metadata, that the image data comprises an object characteristic of a different one of the second set of object types.

13. The device of claim 9, wherein said determination whether a selected object type of the first set of object types is represented in the image data is based, at least in part, on an object identification technique associated with the selected object type of the first set of object types.

14. The device of claim 13, wherein the object types of the first set of object types are iterated over in an order based, at least in part, on a criterion.

15. The device of claim 14, wherein the criterion comprises a performance metric associated with each object identification technique corresponding to each respective object type of the first set of object types.

16. The device of claim 9, wherein the device is further enabled to:

in response to a determination that no object type of the first set of object types is represented in the image data;

identify the object characteristic of the specific one of the second set of object types based, at least in part, on an edge detection technique or a depth detection technique.

17. A computer program product comprising:

a computer readable storage device with program code stored thereon which, when executed by one or more processors of a device, enables the device to;

capture image data using an image sensor of the device;

determine, by the device, whether the image data comprises a representation of a first type of object;

in response to a determination that the image data does not comprise a representation of the first type of object;

determine that the image data comprises a characteristic of a second type of object based, at least in part, on a focus distance associated with the image data; and

in response to a determination that the image data comprises the characteristic of the second type of object, indicating that the image data comprises a characteristic of the second type of object.

18. The computer program product of claim 17, wherein the program code further comprises program code to:

receive an indication to send a search and analysis request to a search and analysis system;

in response to receiving the indication to send the search and analysis request to the search and analysis system, send the image data and image analysis metadata to the search and analysis system, wherein the image analysis metadata comprises a parameter for providing object metadata associated with the second type of object; and

receiving, from the search and analysis system, the object metadata.

19. The computer program product of claim 17, wherein the program code which enables the device to capture image data using the image sensor of the device comprises program which enables the device to capture image data using the image sensor of the device in response to a determination that a setting associated with the device has remained within a particular range for a predetermined period of time.