Image processing device, image processing method, and program

• US 8,363,910 B2
• Filed: 03/05/2008
• Issued: 01/29/2013
• Est. Priority Date: 03/08/2007
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Asukai, Masamichi, Tsuruta, Masaaki, Ozaki, Nozomu, Ito, Taiji, Sugino, Akinobu, Sekizawa, Hidehiko, Sano, Akane, Sako, Yoichiro
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US12/074,667
• Publication Number:
  US 20080273798A1
• Time in Patent Office: 1,791 Days
• Field of Search: 382/115, 382/118, 382/181, 382/190, 382/195, 382/199, 382/203, 382/209, 382/216, 382/217, 382224-228
• US Class Current: 382/118
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

There is provided an image processing device that includes a facial image extraction portion, a positivity computation portion, and a selected image update portion. The facial image extraction portion specifies a facial region of an imaged subject within at least one sequentially input selection-eligible image and extracts from the selection-eligible image a facial image that corresponds to the facial region. The positivity computation portion computes for the selection-eligible image, using the corresponding facial image, a positivity of the imaged subject toward a person who acquired the selection-eligible image. The selected image update portion compares the selection-eligible image for which the positivity was computed in the positivity computation portion to a selection candidate image that has the greatest positivity among selection-eligible images for the same imaged subject for which the positivities have already been computed, and makes the image with the greater positivity the new selection candidate image.

Claims

1. An image processing device comprising:

a facial image extraction portion configured to specify a facial region of an imaged subject within at least one sequentially input selection-eligible image and to extract from a selection-eligible image in the at least one sequentially input selection-eligible image a facial image that corresponds to the facial region;

an eligibility determination portion configured to determine whether the imaged subject is eligible for image selection;

a positivity computation portion configured to compute for the selection-eligible image, using the facial image and information indicating at least one of a date and time of acquisition of the selection-eligible image and a location of the acquisition of the selection-eligible image, a positivity of the imaged subject toward a person who acquired the at least one selection-eligible image if the eligibility determination portion determines that the imaged subject is eligible for image selection; and

a selected image update portion configured to compare the selection-eligible image for which the positivity was computed in the positivity computation portion to a selection candidate image that has a greatest positivity among all the selection-eligible images for the same imaged subject for which the positivities have already been computed, and to make the image with a greater positivity a new selection candidate image.

2. The image processing device according to claim 1, further comprising:

an image selection portion configured to select, as a selected image for the imaged subject, the selection candidate image for the imaged subject that was updated in the selected image update portion.

3. The image processing device according to claim 1,

wherein the positivity is computed based at least in part on a feature selected from the group consisting of a size of the facial image, a color saturation of the facial image, and a spatial frequency of the facial image.

4. The image processing device according to claim 3, wherein

a corresponding sound is input for the selection-eligible image, and

the positivity is computed based at least in part on an intonation of the sound and/or a volume of the sound.

5. The image processing device according to claim 1, wherein

the eligibility determination portion is configured to make the eligibility determination using selection-ineligible information that specifies the imaged subject is not eligible for the selected image selection.

6. The image processing device according to claim 1, further comprising:

a first positivity editing portion configured to increase and decrease the positivity that the positivity computation portion computed for the selection-eligible image based on input from a user of the image processing device.

7. The image processing device according to claim 1, further comprising:

a second positivity editing portion configured to increase and decrease the positivity that was computed for the selection candidate image for the imaged subject based on input from a user of the image processing device.

8. The image processing device according to claim 1, further comprising:

an image acquisition portion configured to acquire and input n real time the at least one selection-eligible image.

9. The image processing device according to claim 1, further comprising:

a storage portion configured to store the at least one selection-eligible image.

10. The image processing device according to claim 1,

wherein the at least one selection-eligible image is input from an external device.

15. The image processing apparatus of claim 1, wherein the facial image extraction portion is further configured to append index information to the extracted facial image, wherein the index information correlates the extracted facial image to the selection-eligible image from which the extracted facial image was extracted.

11. An image processing method, comprising the steps of:

specifying a facial region of an imaged subject within at least one sequentially input selection-eligible image and extracting, with a processor, from a selection-eligible image in the at least one sequentially input selection-eligible image a facial image that corresponds to the facial region;

determining whether the imaged subject is eligible for image selection;

if it is determined that the imaged subject is eligible for image selection, computing for the selection-eligible image, using the facial image and information indicating at least one of a date and time of acquisition of the selection-eligible image and a location of the acquisition of the selection-eligible image, a positivity of the imaged subject toward a person who acquired the at least one selection-eligible image; and

comparing the selection-eligible image for which the positivity was computed in the computing step to a selection candidate image that has a greatest positivity among all the selection-eligible images for the imaged subject for which the positivities have been computed, and making the image with a greater positivity a new selection candidate image.

12. The image processing method according to claim 11, further comprising the step of:

selecting, as a selected image for the imaged subject, the selection candidate image for the imaged subject that is updated when the image with the greater positivity is made the new selection candidate image.

16. The image processing method of claim 11, wherein specifying the facial region further comprises appending index information to the extracted facial image, wherein the index information correlates the extracted facial image to the selection-eligible image from which the extracted facial image was extracted.

13. A memory device storing instructions that command a computer to execute a method comprising:

specifying a facial region of an imaged subject within at least one sequentially input selection-eligible image and extracts from a selection-eligible image in the at least one sequentially input selection-eligible image a facial image that corresponds to the facial region;

determining whether the imaged subject is eligible for image selection;

if it is determined that the imaged subject is eligible for image selection, computing for the selection-eligible image, using the facial image and information indicating at least one of a date and time of acquisition of the selection-eligible image and a location of the acquisition of the selection eligible image, a positivity of the imaged subject toward a person who acquired the at least one selection-eligible image; and

comparing the selection-eligible image for which the positivity was computed in the computing portion to a selection candidate image that has a greatest positivity among all the selection-eligible images for the imaged subject for which the positivities have already been computed, and makes a image with the greater positivity a new selection candidate image.

14. The memory device according to claim 13, wherein the method further comprises:

selecting, as a selected image for the imaged subject, the selection candidate image for the imaged subject that is updated when the image with the greater positivity is made the new selection candidate image.

17. The memory device of claim 13, wherein specifying the facial region further comprises appending index information to the extracted facial image, wherein the index information correlates the extracted facial image to the selection-eligible image from which the extracted facial image was extracted.