Apparatus and method for detecting an object from an image

1. An apparatus comprising:

a memory; and

a processor coupled to the memory and configured to:

acquire a first image captured by an image capturing device,

extract a first area corresponding to an object in the first image,

divide the first area into a plurality of first segments,

generate a plurality of histograms regarding the plurality of first segments respectively,

store the plurality of histograms into the memory,

acquire a second image which is captured by the image capturing device after the first image,

detect a second area corresponding to the object in the second image according to a first reference histogram from among the plurality of histograms,

determine whether a part of the object is outside of the second image based on the second area,

when it is determined that the part of the object is outside of the second image, select a second reference histogram used for a third image which is captured by the image capturing device after the second image, from among the plurality of histograms, and

when the third image is acquired, detect a third area corresponding to the object in the third image based on the second reference histogram.

2. The apparatus according to claim 1 , wherein the processor is configured to:

identify a segment corresponding to another part of the object which is included in the second image when it is determined that the part of the object is outside of the second image, and

select the second reference histogram that corresponds to the identified segment.

3. The apparatus according to claim 1 , wherein

the processor is configured to store information about a size of each of the plurality of segments into the memory,

the second reference histogram is selected based on the information about the size.

4. The apparatus according to claim 1 , wherein the processor is configured to

detect the second area when a similarity between the first reference histogram and a histogram generated based on the second image is greater than or equal to a threshold.

5. The apparatus according to claim 4 , wherein the processor is configured to

change the threshold to another threshold according to the relationship between a size of a first segment corresponding to the first reference histogram and another size of a second segment corresponding to the second reference histogram.

6. The apparatus according to claim 1 , wherein

the processor is configured to:

calculate a plurality of similarities between the first reference histogram and each of a plurality of images including the second image and an image captured before the second image is captured, and

store the plurality of similarities into the memory,

the second reference histogram is selected according to an average of the plurality of similarities.

7. The apparatus according to claim 1 , wherein the processor is configured to:

calculate a plurality of similarities between the first reference histogram and each of a plurality of images including the second image and an image captured before the second image is captured,

store the plurality of similarities into the memory,

calculate, for each of the plurality of segments in the first image, an evaluation value obtained by assigning a weight to similarity of an image or images that were obtained more recently according to trends of the plurality of similarities, and

select the second reference histogram according to the evaluation value.

8. A method executed by a computer, the method comprising:

acquiring a first image captured by an image capturing device;

extracting a first area corresponding to an object in the first image,

dividing the first area into a plurality of first segments,

generating a plurality of histograms regarding the plurality of first segments respectively,

storing the plurality of histograms into the memory,

acquiring a second image which is captured by the image capturing device after the first image,

detecting a second area corresponding to the object in the second image according to a first reference histogram from among the plurality of histograms,

determining whether a part of the object is outside of the second image based on the second area,

when it is determined that the part of the object is outside of the second image, selecting a second reference histogram used for a third image which is captured by the image capturing device after the second image, from among the plurality of histograms, and

when the third image is acquired, detecting a third area corresponding to the object in the third image based on the second reference histogram.

9. The method according to claim 8 , further comprising identifying a segment corresponding to another part of the object which is included in the second image when it is determined that the part of the object is outside of the second image, and

selecting the second reference histogram that corresponds to the identified segment.

10. The method according to claim 8 , further comprising:

storing information about a size of each of the plurality of segments into the memory,

selecting the second reference histogram based on the information about the size.

11. The method according to claim 8 , further comprising:

detecting the second area when a similarity between the first reference histogram and a histogram generated based on the second image is greater than or equal to a threshold.

12. The method according to claim 11 further comprising:

changing the threshold to another threshold according to the relationship between a size of a first segment corresponding to the first reference histogram and another size of a second segment corresponding to the second reference histogram.

13. The method according to claim 8 , further comprising:

calculating a plurality of similarities between the first reference histogram and each of a plurality of images including the second image and an image captured before the second image is captured;

storing the plurality of similarities into the memory; and

selecting the second reference histogram according to an average of the plurality of similarities.

14. The method according to claim 8 , further comprising:

calculating a plurality of similarities between the first reference histogram and each of a plurality of images including the second image and an image captured before the second image is captured;

storing the plurality of similarities into the memory;

calculating, for each of the plurality of segments in the first image, an evaluation value obtained by assigning a weight to similarity of an image or images that were obtained more recently according to trends of the plurality of similarities; and

selecting the second reference histogram according to the evaluation value.

15. A computer-readable recording medium storing a program that causes a computer to execute a process to detect a user, the process comprising:

acquiring a first image captured by an image capturing device;

extracting a first area corresponding to an object in the first image,

dividing the first area into a plurality of first segments,

generating a plurality of histograms regarding the plurality of first segments respectively,

storing the plurality of histograms into the memory,

acquiring a second image which is captured by the image capturing device after the first image,

detecting a second area corresponding to the object in the second image according to a first reference histogram from among the plurality of histograms,

determining whether a part of the object is outside of the second image based on the second area,

when it is determined that the part of the object is outside of the second image, selecting a second reference histogram used for a third image which is captured by the image capturing device after the second image, from among the plurality of histograms, and

when the third image is acquired, detecting a third area corresponding to the object in the third image based on the second reference histogram.

16. The apparatus according to claim 1 , wherein the object is a user to be authenticated.

17. The method according to claim 8 , wherein the object is a user to be authenticated.

18. The computer-readable recording medium according to claim 15 , wherein the object is a user to be authenticated.