Category weight setting apparatus and method, image weight setting apparatus and method, category abnormality setting apparatus and method, and programs therefor

• US 20070208717A1
• Filed: 02/28/2007
• Published: 09/06/2007
• Est. Priority Date: 03/01/2006
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Matsui, Yuko
• Granted Patent: US 8,116,573 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G11B 27/3027 used signal is digitally coded
• CPC Class Codes: G11B 27/32 on separate auxiliary tracks of the same or an auxiliary record carrier
• CPC Class Codes: H04N 5/781 on disks or drums
• CPC Class Codes: H04N 5/907 using static stores, e.g. storage tubes or semiconductor memories H04N5/91 takes precedence
• CPC Class Codes: H04N 9/8047 using transform coding
• CPC Class Codes: H04N 9/8205 involving the multiplexing of an additional signal and the colour video signal

Abstract

When images are classified into categories, which of the categories has important images can be understood easily without a burned on a user. For this purpose, a category weight calculation unit statistically calculates a weight of each of the categories obtained by classification of the images, based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein.

Claims

1. A category weight setting apparatus comprising category weight calculation means for statistically calculating a weight of each category obtained by classification of a plurality of images, based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein.

2. The category weight setting apparatus according to claim 1,

the category weight calculation means calculating at least two of the characteristic quantities comprising the number of images therein found by considering similar images therein, the total photography time thereof, the rate of similar images therein, the rate of human images therein, and the average number of human faces therein,

the category weight calculation means statistically calculating an individual weight or individual weights corresponding to the characteristic quantity or quantities based on the characteristic quantity or quantities, and

the category weight calculation means calculating the category weight by weighting the individual weight or weights.

3. An image weight setting apparatus comprising:

category weight calculation means for statistically calculating a weight of each category obtained by classification of a plurality of images; and

image weight calculation means for statistically calculating a weight of each of the images included in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

4. The image weight setting apparatus according to claim 3, wherein the image weight calculation means calculates the weight of each of the images in the target category according to α

n×

(the weight of the category)+β

n where n refers to the number of similar images therein and α

n and β

n are statistically predetermined weight coefficients.

5. The image weight setting apparatus according to claim 3, wherein the category weight calculation means statistically calculates the weight of each of the categories based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein.

6. The image weight setting apparatus according to claim 5,

the category weight calculation means calculating at least two of the characteristic quantities comprising the number of images therein found by considering similar images therein, the total photography time thereof, the rate of similar images therein, the rate of human images therein, and the average number of human faces therein,

the category weight calculation means statistically calculating an individual weight or individual weights corresponding to the characteristic quantity or quantities based on the characteristic quantity or quantities, and

the category weight calculation means calculating the category weight by weighting the individual weight or weights.

7. An image weight setting apparatus comprising:

classification means for classifying a plurality of images into categories based on accompanying information added to the images;

category weight calculation means for statistically calculating a weight of each of the categories based on a characteristic of the images included therein; and

image weight calculation means for statistically calculating a weight of each of the images in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

8. The image weight setting apparatus according to claim 7,

the classification means classifying the images into the categories according to date of photography based on information on time and date of photography added to each of the images,

the category weight calculation means statistically calculating the weight of each of the categories based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein, and

the image weight calculation means statistically calculating the weight of each of the images in the target category based on the number of similar images therein and the weight thereof.

9. The image weight setting apparatus according to claim 8, wherein the image weight calculation means calculates the weight of each of the images in the target category according to α

n×

(the weight of the category)+β

n where n refers to the number of similar images therein and α

n and β

n are statistically predetermined weight coefficients.

10. A category weight setting method comprising the step of statistically calculating a weight of each category obtained by classification of a plurality of images, based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein.

11. An image weight setting method comprising the steps of:

statistically calculating a weight of each category obtained by classification of a plurality of images; and

statistically calculating a weight of each of the images included in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

12. An image weight setting method comprising the steps of:

classifying a plurality of images into categories based on accompanying information added to the images;

statistically calculating a weight of each of the categories based on a characteristic of the images included therein; and

statistically calculating a weight of each of the images in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

13. A program causing a computer to execute a category weight setting method comprising the procedure of statistically calculating a weight of each category obtained by classification of a plurality of images, based on at least one of characteristic quantities comprising the number of images therein found by considering similar images therein, a total photography time thereof, a rate of similar images therein, a rate of human images therein, and an average number of human faces therein.

14. A program causing a computer to execute an image weight setting method comprising the procedures of:

statistically calculating a weight of each category obtained by classification of a plurality of images; and

statistically calculating a weight of each of the images included in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

15. A program causing a computer to execute an image weight setting method comprising the procedures of:

classifying a plurality of images into categories based on accompanying information added to the images;

statistically calculating a weight of each of the categories based on a characteristic of the images included therein; and

statistically calculating a weight of each of the images in a targeted one of the categories, based on the number of similar images included therein and the weight thereof.

16. A category abnormality setting apparatus comprising category abnormality calculation means for calculating an abnormality of each category obtained by classification of a plurality of images, based on a statistical abnormality distribution in a relationship of any one of the number of images therein, the number of images therein found by considering similar images therein, the number of categories related thereto, and the number of hierarchical levels to a total photography time thereof and/or to a rate of similar images therein.

17. The category abnormality setting apparatus according to claim 16, wherein the category abnormality calculation means classifies each of the categories as a normal category or an abnormal category by comparing the abnormality thereof with a predetermined threshold value.

18. The category abnormality setting apparatus according to claim 17, wherein, in the case where the categories are in a hierarchy, the apparatus further comprises category weight calculation means for calculating a category weight of an uppermost-level category based on a characteristic thereof and for calculating a category weight of a lower-level category other than the uppermost-level category based on a characteristic thereof in the case where the uppermost-level category is the normal category or for setting a predetermined value as the category weight of the lower-level category in the case where the uppermost-level category is the abnormal category.

19. The category abnormality setting apparatus according to claim 16, further comprising:

certainty calculation means for statistically calculating a certainty of the abnormality for each of-the categories;

category weight calculation means for calculating a weight of each of the categories based on a characteristic thereof; and

output means for outputting the weight together with the certainty.

20. A category abnormality setting method comprising the step of calculating an abnormality of each category obtained by classification of a plurality of images, based on a statistical abnormality distribution in a relationship of any one of the number of images therein, the number of images therein found by considering similar images therein, the number of categories related thereto, and the number of hierarchical levels to a total photography time thereof and/or to a rate of similar images therein.

21. A program causing a computer to execute a category abnormality setting method comprising the procedure of calculating an abnormality of each category obtained by classification of a plurality of images, based on a statistical abnormality distribution in a relationship of any one of the number of images therein, the number of images therein found by considering similar images therein, the number of categories related thereto, and the number of hierarchical levels to a total photography time thereof and/or to a rate of similar images therein.