Similar image retrieving apparatus, three-dimensional image database apparatus and method for constructing three-dimensional image database

• US 6,804,683 B1
• Filed: 11/20/2000
• Issued: 10/12/2004
• Est. Priority Date: 11/25/1999
• Status: Expired due to Fees

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Corporation
• Inventors: Kosaka, Akio, Shibasaki, Takao, Matsuzaki, Hiroshi
• Primary Examiner(s): Robinson, Greta
• Assistant Examiner(s): LEWIS, CHERYL RENEA
• Application Number:
  US09/716,692
• Time in Patent Office: 1,422 Days
• Field of Search: 707/1, 707/3, 707/100, 707/6, 707/7, 707/103.R, 707/104.1, 382/173, 382/174, 382/190, 382/189, 382/164, 382/165, 382/180, 345/419, 345/418
• US Class Current: 1/1
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: Y10S 707/99931 Database or file accessing
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A similar image retrieving means has a region of interest setting portion, a feature quantity calculation portion, a similarity calculation portion and an image selection portion. A part of the three-dimensional image of the retrieval object is set as a region of interest. The feature quantity calculation portion calculates the quantity of the region of interest. The similarity calculation portion calculates the similarity between the retrieval object and the three-dimensional image data stored in advance by comparing the feature quantity of the region of interest of the retrieval object which quantity is calculated with the feature quantity calculation means with the three-dimensional image data where the region of interest is set which is stored in advance in the image database, and the feature quantity of this region of interest is calculated. The image selection portion selects similar images in an order of decreasing similarity from the image database.

Claims

1. A similar image retrieving apparatus comprising:

a region of Interest setting portion for setting a portion of a three-dimensional image of retrieved object including a landmark as a region of interest;

a feature quantity calculation portion for calculating a feature quantity including positions of the landmark and of the region of interest set by the region of interest setting portion as parameters;

a similarity calculation portion for calculating a similarity between the retrieved object and three-dimensional image data stored in the image database in advance by comparing the feature quantity of the region of interest of the retrieved object which quantity is calculated with the feature quantity calculation portion with the three-dimensional image data where a region of interest stored in the image database is set in advance and the feature quantity of this region of interest is calculated; and

an image selection portion for selecting similar images in an order of decreasing similarity from the image database on the basis of the similarity calculated with the similarity calculation portion.

2. The similar image retrieving apparatus according to claim 1, wherein the similarity calculation portion calculates the similarity of the image with respect to only the image with which a key word agrees out of the key words selected from a set of key words prepared in advance and images to which key words are added in advance which images are stored in the image database.

3. The similar image retrieving apparatus according to claim 1, wherein the feature quantity calculation portion calculates the feature quantity by setting in advance the three-dimensional standard model which is compared in the image retrieval and using a position posture relationships between the standard model and the retrieved object image data.

4. An image retrieving apparatus comprising:

image database in which object three-dimensional images are stored; and

an image retrieving engine for retrieving images by using similarity of images;

the image retrieving engine comprising,

three-dimensional region of Interest setting means for cutting out the three-dimensional region of interest from the three-dimensional images where the object including a landmark input from the three-dimensional input device or from the image database is photographed,

feature quantity calculation means for calculating the feature quantity of the three-dimensional region of interest set, including the positions of the three-dimensional region of interest and the landmark as parameters,

similarity calculation and image selection means for calculating similarity between the three-dimensional region of interest and a constituent element of a three-dimensional image group stored in advance in the image database, a three-dimensional region of interest being set and the feature quantity being calculated by using the feature quantity thereof and selecting similar images from the image database in an order of decreasing similarity on the basis of the similarity, and

an image display means for retrieving the three-dimensional image selected with the similarity calculation and image selection means from the image database and displaying the image.

5. The image retrieving apparatus according to claim 4, wherein the image similarity calculation portion calculates the similarity only in the image with which the key word added to the image in advance agrees.

6. The apparatus for retrieving images according claim 4, wherein the feature quantity calculation portion calculates the feature quantity by using the position posture relationships with the standard object model.

7. A three-dimensional image database apparatus for retrieving an image similar to an input three-dimensional image, the apparatus comprising:

an image input portion for inputting three-dimensional image data;

a region of Interest setting portion for setting a region of interest on the basis of the designated condition with respect to the three-dimensional image data input with the image input portion;

a three-dimensional reconstruction portion for reconstructing three-dimensional image data by normalizing and visualizing this region of interest of the three-dimensional image data set with the region of Interest setting portion; and

a three-dimensional data accumulation portion for accumulating the three-dimensional image data of the region of interest normalized by the three-dimensional reconstruction portion in correspondence to the three-dimensional image data input in the image input portion.

8. The three-dimensional image database apparatus according to claim 7, wherein three-dimensional database apparatus has a features calculation portion for calculating feature quantity of the image data with respect to the region of interest of the three-dimensional image data set by the region of Interest setting means, and

the three-dimensional image data accumulation portion accumulates the feature quantity of the image data calculated with the feature quantity calculation portion in correspondence to the three-dimensional image data input with the image input portion.

9. A method for constructing image database for retrieving an image similar to the input three-dimensional image data, the method comprising the steps of:

inputting three-dimensional image data;

setting a region of interest on the basis of the designated condition with respect to the input three-dimensional image data;

reconstructing the three-dimensional image data by normalizing and visualizing the region of interest of the set three-dimensional data; and

accumulating the reconstructed three-dimensional image data of the normalized region of interest by allowing the image data to correspond to the input three-dimensional image data.

10. A method for constructing image database for retrieving an image similar to the input three-dimensional image, the method comprising:

inputting three-dimensional image data;

setting the region of interest on the basis of the designated condition with respect to the input three-dimensional image data;

reconstructing the three-dimensional image data by normalizing and visualizing the region of interest of the set three-dimensional data;

calculating the feature quantity of the normalized region of interest of the three-dimensional image; and

accumulating the three-dimensional image of the normalized region of interest and the feature quantity of the normalized region of interest by allowing the image and the feature quantity to correspond to the input three-dimensional image.

11. An image database apparatus for retrieving an image similar to the input three-dimensional image;

an image input portion for inputting the three-dimensional images;

a region of Interest setting portion for setting the region of interest for on the basis of the designation condition with respect to the three-dimensional images input with the image input portion;

a three-dimensional reconstruction portion for reconstructing the region of interest of the three-dimensional image by normalizing and visualizing the region of interest;

a three-dimensional image data accumulation portion for accumulating the three-dimensional image of a region of interest normalized by the three-dimensional reconstruction portion by allowing the image to correspond to the three-dimensional image input in the image input portion;

a retrieval condition input portion for inputting a condition for retrieving the three-dimensional image accumulated in the three-dimensional image data accumulation portion;

a similar image extraction portion for extracting similar images from the image accumulated in the three-dimensional data accumulation means on the basis of the retrieval condition input with the retrieval condition input portion; and

a similar image accumulation portion for accumulating a similar image extracted by the similar image extraction portion by allowing the similar image to correspond to the three-dimensional image input with the image input portion and the retrieval condition input with the retrieval condition input portion.

12. The database apparatus according to claim 11, wherein the extracted similar images, the input three-dimensional images and the retrieval conditions are displayed in correspondence to each other.

13. A method for constructing image database for retrieving an image similar to the input three-dimensional images, the method comprising the steps of:

inputting a three-dimensional image;

setting a region of interest on the basis of the designation condition with respect to the input three-dimensional image;

reconstructing the region of interest of the input three-dimensional image by normalizing and visualizing the region of interest;

accumulating the reconstructed three-dimensional image of a normalized region of interest by allowing the image to correspond to the input three-dimensional image;

inputting a retrieval condition for retrieving accumulated three-dimensional images;

extracting a similar images from the accumulated three-dimensional image on the basis of the retrieval condition; and

accumulating the extracted similar image by allowing the image to correspond to the input three-dimensional images and the retrieval condition.

14. The method for constructing images similar to the input three-dimensional images according to claim 13, further comprising the step of displaying the extracted similar images, the input three-dimensional images and the retrieval condition in correspondence to each other.

15. A similar image retrieving apparatus comprising:

region of Interest setting means for setting a part of the three-dimensional image of the retrieval object including a landmark as the region of interest;

feature quantity calculation portion for calculating the feature quantity of including portions of the landmark and the region of interest set with the region of interest setting means as parameters;

similarity calculation means for calculating similarity with the retrieval object and the three-dimensional data stored in advance in the image database by comparing the feature quantity of the region of interest of the retrieval object calculated with the feature quantity calculation means with the three-dimensional image data in which the region of interest is set which is stored in the image database in advance and the feature quantity of this region of interest is calculated;

image selection means for selecting similar images from the image database in the order of decreasing similarity on the basis of similarity calculated with the similarity calculation means.

16. The image retrieving means comprising:

image database in which the three-dimensional image of an object is stored;

an engine for retrieving images by using similarity of the images, the engine comprising;

three-dimensional region of Interest setting means for cutting out the three-dimensional region of interest from the three-dimensional images where the object including a landmark input from the three-dimensional input device or from the image database is photographed,

feature quantity calculation means for calculating the feature quantity of the three-dimensional region of interest set with the three-dimensional region of Interest setting means, including the positions of the three-dimensional region of interest and the landmark as parameters,

similarity calculation and image selection means for calculating similarity between the three-dimensional region of interest and a constituent element of a three-dimensional image group stored in advance in the image database, a three-dimensional region of interest being set and the feature quantity being calculated by using the feature quantity thereof and selecting similar images from the image database in an order of decreasing similarity on the basis of the similarity, and

an image display means for retrieving the three-dimensional image selected with the similarity calculation and image selection means from the image database and displaying the image.

17. A three-dimensional image database apparatus for retrieving images similar to the input three-dimensional images, the apparatus comprising:

image input means for inputting three-dimensional image data;

region of Interest setting means for setting the region of interest on the basis of the designated condition with respect to the three-dimensional image data input with the image input means;

three-dimensional reconstruction means for reconstructing three-dimensional image data by normalizing and visualizing this region of interest of the three-dimensional image data set with the region of Interest setting means; and

three-dimensional image data accumulating means for accumulating the three-dimensional image data of the region of interest normalized by the three-dimensional reconstruction means in correspondence to the three-dimensional image data input in the image input means.

18. An image database apparatus for retrieving images similar to the input images comprising:

image input means for inputting the three-dimensional images;

region of interest setting means for setting the region of interest on the basis of the designated condition with respect to the three-dimensional image input with the image input means;

three-dimensional reconstruction means for reconstructing the region of interest of three-dimensional image by normalizing and visualizing this region of interest of the three-dimensional image;

three-dimensional image data accumulating means for accumulating the three-dimensional image of a region of interest normalized by the three-dimensional reconstruction means by allowing the data correspond to the three-dimensional image data input in the image input means;

retrieval condition input means for inputting a condition for retrieval with respect to the three-dimensional image accumulated in the three-dimensional image data accumulation means;

similar image extraction means for extracting similar images from the images accumulated in the three-dimensional image accumulation means on the basis of the retrieval condition input with the retrieval condition input means; and

similar image accumulation means for accumulating similar images extracted with the similar image extraction means in correspondence to the three-dimensional image input with the image input means and the retrieval condition input with the retrieval condition input means.