KR20160127369A

KR20160127369A - System and method for searching image

Info

Publication number: KR20160127369A
Application number: KR1020150058655A
Authority: KR
Inventors: 정윤재
Original assignee: 삼성에스디에스 주식회사
Priority date: 2015-04-27
Filing date: 2015-04-27
Publication date: 2016-11-04

Abstract

An image retrieval system and method are provided. According to an embodiment of the present invention, there is provided an image retrieval system including: a depth image obtaining unit that obtains a two-dimensional depth image representing a contour of the three-dimensional image from a target file including a three-dimensional image; An index generator for extracting a feature value from the 2D depth image and generating an index value for the 3D image from the feature value; And an image retrieving unit for retrieving an index value having the highest similarity to the generated index value among the stored index values and retrieving a three-dimensional image corresponding to the index value extracted from the stored three-dimensional images.

Description

[0001] SYSTEM AND METHOD FOR SEARCHING IMAGE [0002]

Embodiments of the present invention relate to a technique capable of retrieving a three-dimensional image at high speed.

In recent years, 3D printing technology is gradually being commercialized. Accordingly, efforts are being made to search a large-capacity three-dimensional image file at high speed in order to prevent unauthorized copying, alteration and abuse of a three-dimensional image file in advance.

However, since the conventional three-dimensional image retrieval technology computes a three-dimensional image file in a three-dimensional coordinate system, the complexity of the computation becomes three-quadrants of the data amount, There is a problem that image retrieval speed is remarkably slow. In order to solve these problems, a retrieval method of inputting words (keywords), sentences, categories or the like describing the appearance of a three-dimensional image or using metadata of a three-dimensional image file has been suggested as an alternative. However, There was a very low problem. In addition, a compound technique for simultaneously processing words (keywords), sentences, categories, and metadata describing the outline of a three-dimensional image together with external data of a three-dimensional image has been proposed. However, In the data age, it is difficult to efficiently retrieve large amounts of data.

Korean Patent Laid-Open Publication No. 10-2014-0004240 (Apr. 1, 2014)

Embodiments of the present invention are intended to provide a means for efficiently searching a large-capacity three-dimensional image file.

According to an exemplary embodiment of the present invention, there is provided an image processing apparatus including: a depth image obtaining unit obtaining a two-dimensional depth image representing a contour of the three-dimensional image from a target file including a three-dimensional image; An index generator for extracting a feature value from the 2D depth image and generating an index value for the 3D image from the feature value; And an image retrieval unit for extracting an index value having the highest similarity to the generated index value among the stored index values and retrieving a three-dimensional image corresponding to the index value extracted from the stored three- / RTI >

The depth image obtaining unit may obtain a plurality of the two-dimensional depth images by mapping the pixels of the three-dimensional image to the two-dimensional plane in multiple directions based on the set axis.

The image search system may further include a fingerprint image obtaining unit for normalizing the two-dimensional depth image to obtain a two-dimensional fingerprint image, and the index generating unit may extract the feature value from the two-dimensional fingerprint image.

The fingerprint image obtaining unit may obtain the two-dimensional fingerprint image by latticing the depth image into a plurality of cells and normalizing the number of pixels in the cell and the thickness of the outline of the depth image.

The index generator may calculate the feature value by multiplying the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum have.

Wherein the fingerprint image obtaining unit obtains a plurality of the two-dimensional fingerprint images for the plurality of depth images, and obtains a two-dimensional fingerprint image having the largest feature value among the plurality of obtained two- Can be selected.

The index generator may select variance values of the normalized number of pixels included in each cell of the representative two-dimensional fingerprint image as an index value for the three-dimensional image.

The image searching unit may calculate a difference between the stored index value and the generated index value and extract an index value having the highest similarity to the generated index value among the stored index values.

According to another exemplary embodiment of the present invention, there is provided a depth image obtaining unit, comprising: obtaining a two-dimensional depth image representing a contour of the three-dimensional image from a target file including a three-dimensional image; Extracting a feature value from the 2D depth image; Generating an index value for the three-dimensional image from the feature value; Extracting an index value having the highest degree of similarity with the generated index value among the stored index values in the image searching unit; And retrieving, in the image retrieving unit, a three-dimensional image corresponding to the index value extracted from the stored three-dimensional image.

The acquiring of the two-dimensional depth image may acquire a plurality of the two-dimensional depth images by mapping the pixels of the three-dimensional image to the two-dimensional plane in multiple directions based on the set axis.

Wherein the image retrieval method further comprises the step of obtaining a two-dimensional fingerprint image by normalizing the two-dimensional depth image in a fingerprint image obtaining unit after obtaining the two-dimensional depth image, The feature value may be extracted from the two-dimensional fingerprint image.

The step of acquiring the two-dimensional fingerprint image may include gridding the depth image into a plurality of cells; And normalizing the thickness of the contour of the depth image with the number of pixels in the cell.

Wherein the extracting of the feature value comprises multiplying the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum, The value can be calculated.

Wherein acquiring the two-dimensional fingerprint image comprises: obtaining a plurality of the two-dimensional fingerprint images for the plurality of depth images; And selecting a two-dimensional fingerprint image having the largest feature value among the acquired plurality of two-dimensional fingerprint images as a representative two-dimensional fingerprint image.

The step of generating an index value for the three-dimensional image may include, as index values for the three-dimensional image, variance values of the number of normalized pixels contained in each cell of the representative two-dimensional fingerprint image.

The step of extracting the index value having the highest degree of similarity may include calculating a difference between the stored index value and the generated index value and extracting an index value having the highest degree of similarity with the generated index value .

According to another exemplary embodiment of the present invention, there is provided an image processing method comprising the steps of: obtaining, in a depth image acquiring unit, a two-dimensional depth image representing a contour of a three-dimensional image from a three-dimensional image; Extracting a feature value from the 2D depth image; Generating an index value for the three-dimensional image from the feature value; Extracting an index value having the highest degree of similarity with the generated index value among the stored index values in the image searching unit; And retrieving, in the image retrieving unit, a three-dimensional image corresponding to the index value extracted from the stored three-dimensional image.

According to embodiments of the present invention, a three-dimensional image is converted into a one-dimensional index value, and a stored three-dimensional image is retrieved using the converted one-dimensional index value, so that the complexity of an operation required for image retrieval is significantly . As a result, the overall image search speed can be improved and the image search time can be shortened. In addition, since the index value is generated based on the outline of the three-dimensional image, the accuracy of the image search is high.

1 is a block diagram showing a detailed configuration of an image retrieval system according to an embodiment of the present invention;
2 is a view for explaining a process of acquiring a 2D depth image by a depth image acquiring unit according to an embodiment of the present invention;
3 is a view for explaining a process of acquiring a two-dimensional fingerprint image according to an embodiment of the present invention;
FIG. 4 is a view for explaining a process of extracting a feature value by an index generating unit according to an embodiment of the present invention.
5 is a view for explaining a process of measuring the similarity between an index value stored in an image search unit and an index value generated in an index generator according to an embodiment of the present invention;
6 is a flowchart illustrating an image search method according to an embodiment of the present invention.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to provide a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely an example and the present invention is not limited thereto.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. The following terms are defined in consideration of the functions of the present invention, and may be changed according to the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification. The terms used in the detailed description are intended only to describe embodiments of the invention and should in no way be limiting. Unless specifically stated otherwise, the singular form of a term includes plural forms of meaning. In this description, the expressions "comprising" or "comprising" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, Should not be construed to preclude the presence or possibility of other features, numbers, steps, operations, elements, portions or combinations thereof.

1 is a block diagram showing a detailed configuration of an image retrieval system 100 according to an embodiment of the present invention. 1, an image retrieval system 100 according to an embodiment of the present invention includes a depth image acquisition unit 102, a fingerprint image acquisition unit 104, an index generation unit 106, an image search unit 108 and a database 110.

The depth image acquiring unit 102 acquires a depth image representing a contour of a three-dimensional image from a target file including a three-dimensional image. Here, the three-dimensional image means a figure, a figure, a still image, etc. having a three-dimensional shape. Also, a target file containing a three-dimensional image can be, for example, a * .stl file used in a 3D printer, a * .gcode file or a CAD file (e.g., * .dwg, * .dxf, etc.) have. The target file may have coordinate values (i.e., point clouds) of the x-axis, y-axis, and z-axis for the three-dimensional image.

The depth image obtaining unit 102 may obtain a two-dimensional depth image from the three-dimensional image included in the target file. The depth image refers to a two-dimensional shaded image taken around a plurality of principal axes in a Cartesian coordinate system, and can represent the contour of a three-dimensional image. The depth image obtaining unit 102 may obtain a plurality of two-dimensional depth images by mapping the pixels of the three-dimensional image included in the object file to the two-dimensional plane in multiple directions based on the set axis. For example, the depth image obtaining unit 102 maps a pixel of a three-dimensional image included in a target file into a two-dimensional plane while rotating at an equal angle (for example, 30 degrees or 60 degrees) The same process can be repeated for the axis and the z-axis to acquire a plurality of depth images.

The fingerprint image obtaining unit 104 normalizes the depth image obtained by the depth image obtaining unit 102 to obtain a two-dimensional fingerprint image. To this end, the fingerprint image acquisition unit 104 may adjust the depth image to a predetermined size and gratify it into a plurality of cells. For example, the fingerprint image obtaining unit 104 may adjust the depth image to a size of 5 cm x 5 cm and gratify it into 16 cells. In addition, the fingerprint image obtaining unit 104 may normalize the number of pixels of each cell and the thickness of the contour of the depth image. For example, when the number of pixels in a cell is between 1 and 20, the fingerprint image obtaining unit 104 adjusts the number of pixels in the cell to be 15 while maintaining the contour of the depth image, Is between 21 and 40, the number of pixels in the cell can be adjusted to 35 while maintaining the outline of the depth image. Further, the fingerprint image obtaining unit 104 may convert the thickness of all the contours in the depth image into 1 mm. Accordingly, the image searching unit 108, which will be described later, can easily search a three-dimensional image similar to the three-dimensional image included in the target file regardless of the overall size and resolution of the three-dimensional image.

The index generation unit 106 extracts a feature value from the two-dimensional fingerprint image (or the two-dimensional depth image acquired by the depth image acquisition unit 102) acquired by the fingerprint image acquisition unit 104, An index value (or matrix) for the three-dimensional image included in the target file is generated. As described above, the depth image acquiring unit 102 can acquire a plurality of two-dimensional depth images by mapping the pixels of the three-dimensional image in multiple directions in a two-dimensional plane on the basis of the set axis, and the fingerprint image obtaining unit 104 Can normalize a plurality of two-dimensional depth images to obtain a plurality of two-dimensional fingerprint images. At this time, since the degree to which the three-dimensional image can be identified differs depending on the angle at which the three-dimensional image is viewed, the index generation unit 106 extracts feature values for each of the plurality of two-dimensional fingerprint images, The image obtaining unit 104 can select a two-dimensional fingerprint image having the largest feature value among the plurality of two-dimensional fingerprint images as the representative two-dimensional fingerprint image. The index generation unit 106 may generate an index value for the three-dimensional image included in the target file from the feature values of the representative two-dimensional fingerprint image. The feature value and the index value are identification values indicating the external features of the three-dimensional image, and may be a letter, a number, or a combination thereof. A method of extracting a feature value by the index generation unit 106 and a method of generating an index value will be described later in detail with reference to FIG.

The image retrieval unit 108 extracts an index value having the highest similarity to the index value generated by the index generation unit 106 among the index values stored in the database 110, which will be described later. For example, the image searching unit 108 may calculate the difference between the index value stored in the database 110 and the index value generated in the index generating unit 106 to determine the degree of similarity. The image searching unit 108 may determine that the index value having the smallest difference from the index value generated by the index generating unit 106 among the index values stored in the database 110 is the index value having the highest similarity.

Also, the image search unit 108 can search a three-dimensional image corresponding to the index value having the highest similarity among the three-dimensional images stored in the database 110. The index generation unit 106 may generate an index value by repeating the above-described process for each of the three-dimensional images stored in the database 110. The index generation unit 106 matches the generated index value with the corresponding three- Lt; / RTI > The index value stored in the database 110 may be used by the image retrieval unit 108 to retrieve a three-dimensional image.

The database 110 stores a three-dimensional image file and index values corresponding to the three-dimensional image file. The depth image acquiring unit 102, the fingerprint image acquiring unit 104 and the index generating unit 106 may repeat the above-described processes for each of the three-dimensional images stored in the database 110. [ Accordingly, the index generating unit 106 may generate an index value for each of the three-dimensional images and store the index value in the database 110. The index value stored in the database 110 may be used by the image retrieval unit 108 to retrieve a three-dimensional image.

In one embodiment, the depth image acquisition unit 102, the fingerprint image acquisition unit 104, the index generation unit 106, the image retrieval unit 108, and the database 110 may include one or more processors and computer readable Lt; RTI ID = 0.0 > a < / RTI > capable recording medium. The computer readable recording medium may be internal or external to the processor, and may be coupled to the processor by any of a variety of well known means. A processor in the computing device may cause each computing device to operate in accordance with the exemplary embodiment described herein. For example, a processor may execute instructions stored on a computer-readable recording medium, and instructions stored on the computer readable recording medium may cause a computing device to perform operations in accordance with the exemplary embodiments described herein For example.

2 is a view for explaining a process of acquiring a 2D depth image by the depth image acquiring unit 102 according to an embodiment of the present invention. As described above, the depth image obtaining unit 102 can obtain a plurality of two-dimensional depth images by mapping the pixels of the three-dimensional image to the two-dimensional plane in multiple directions based on the set axis. For example, as shown in FIG. 2, the depth image obtaining unit 102 may obtain four two-dimensional depth images of a three-dimensional image while rotating the image by 90 degrees while holding the y-axis as a main axis. Here, 90 degrees is only one example, and the depth image obtaining unit 102 may obtain a plurality of two-dimensional depth images while rotating by 30 degrees or 60 degrees. The depth image obtaining unit 102 may obtain a plurality of depth images by repeating the same process for the x-axis and the z-axis. Through this process, the depth image obtaining unit 102 can reduce the dimension of the image from three dimensions to two dimensions.

FIG. 3 is a view for explaining a process of acquiring a two-dimensional fingerprint image by the fingerprint image obtaining unit 104 according to an embodiment of the present invention. As described above, the fingerprint image obtaining unit 104 may normalize the depth image obtained by the depth image obtaining unit 102 to obtain a two-dimensional fingerprint image. For example, the fingerprint image obtaining unit 104 may adjust the depth image to a size of 5 cm x 5 cm and gratify it into 16 cells. In addition, the fingerprint image obtaining unit 104 may normalize the number of pixels of each cell and the thickness of the contour of the depth image. For example, the fingerprint image obtaining unit 104 may calculate the number of pixels in the cell, adjust the number of pixels in the cell, and convert the thickness of all the contours in the depth image into the set size. Accordingly, the image searching unit 108 can easily search a three-dimensional image similar to the three-dimensional image included in the target file regardless of the overall size and resolution of the three-dimensional image.

4 is a diagram for explaining a process of extracting a feature value by the index generation unit 106 according to an embodiment of the present invention. As described above, the index generation unit 106 can extract the feature value from the two-dimensional fingerprint image (or the two-dimensional depth image acquired by the depth image acquisition unit 102) acquired by the fingerprint image acquisition unit 104 have. For example, the index generator 106 multiplies the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum, Can be calculated. Referring to FIG. 4, the sum of the normalized number of pixels included in the two-dimensional fingerprint image is 60, the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum is 4.2, Can be 4.2 X 60 = 252.

As described above, the fingerprint image acquisition unit 104 may acquire a plurality of two-dimensional fingerprint images for a plurality of depth images, and the index generation unit 106 may acquire feature values for each of the plurality of two-dimensional fingerprint images Can be calculated. Accordingly, the fingerprint image obtaining unit 104 can select the two-dimensional fingerprint image having the largest feature value among the plurality of acquired two-dimensional fingerprint images as the representative two-dimensional fingerprint image. Here, it is assumed that the two-dimensional fingerprint image having the largest feature value best represents the external feature of the three-dimensional image. The degree to which a three-dimensional image can be identified varies depending on the angle at which the three-dimensional image is viewed. The larger the complexity of the contour of the three-dimensional image or the greater the difference in the concentration of the contour line for each cell, have. On the other hand, here, the index generation unit 106 calculates the feature value from the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two- However, this is merely an example, and the method of calculating feature values is not limited thereto. The feature value acquisition method of the index generation unit 106 may adopt a method other than the above-described method only if the condition that the feature value has a larger value as the outline feature of the three-dimensional image is better represented. For example, the index generating unit 106 may extract a feature value from a two-dimensional fingerprint image using a Scale Invariant Feature Transform (SIFT) algorithm, a SURF (Speed Up Robust Features) algorithm, or the like.

The index generation unit 106 may generate an index value for the three-dimensional image from the feature values for the representative two-dimensional fingerprint image. For example, the index generator 106 may select the variance values of the normalized number of pixels included in each cell of the representative two-dimensional fingerprint image as an index value for the three-dimensional image. That is, in FIG. 4, the indexes for the three-dimensional images (5, 4, 4, 5, 2, 3, 3, 2/1, 7, 7, 1/2, 6, Lt; / RTI >

5 is a diagram for explaining a process of measuring the similarity between the index value stored in the database 110 and the index value generated in the index generation unit 106 according to an embodiment of the present invention. to be. As described above, the image retrieval unit 108 can extract an index value having the highest similarity with the index value generated by the index generation unit 106, among the index values stored in the database 110. For example, the image searching unit 108 may calculate the difference between the index value stored in the database 110 and the index value generated in the index generating unit 106 to determine the degree of similarity. FIG. 5A shows the index value generated by the index generating unit 106, and FIG. 5B shows the index value stored in the database 110. FIG. The image searching unit 108 may calculate the difference between the index value generated in the index generating unit 106 and the index value stored in the database 110 for each cell as shown in Equation 1 below, The index value having the smallest difference from the index value generated by the index generator 106 among the stored index values can be determined as the index value having the highest similarity.

Here, d is the difference between the index value Qi stored in the database 110 and the index value Si generated by the index generator 106, m is the number of rows of cells in the index value Qi, Si, n denotes the number of columns of cells in the index value (Qi, Si).

6 is a flowchart illustrating an image search method according to an embodiment of the present invention. The method shown in Fig. 6 can be performed, for example, by the image retrieval system 100 described above. In the illustrated flow chart, the method is described as being divided into a plurality of steps, but at least some of the steps may be performed in reverse order, combined with other steps, performed together, omitted, divided into detailed steps, One or more steps may be added and performed.

In step S602, the depth image obtaining unit 102 obtains a two-dimensional depth image representing the outline of the three-dimensional image from the target file including the three-dimensional image. The depth image obtaining unit 102 may obtain a plurality of two-dimensional depth images by mapping the pixels of the three-dimensional image included in the object file in a two-dimensional plane in multiple directions on the basis of the set axis.

In step S604, the fingerprint image obtaining unit 104 normalizes the two-dimensional depth image to obtain a two-dimensional fingerprint image. For example, the fingerprint image obtaining unit 104 may obtain a two-dimensional fingerprint image by grating the depth image into a plurality of cells and normalizing the number of pixels in the cell and the thickness of the outline of the depth image.

In step S606, the index generation unit 106 extracts a feature value from the 2D depth image. For example, the index generator 106 multiplies the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum, Can be calculated.

In step S608, the fingerprint image obtaining unit 104 selects the two-dimensional fingerprint image having the largest feature value extracted in step S606 among the plurality of two-dimensional fingerprint images as the representative two-dimensional fingerprint image. Here, it is assumed that the two-dimensional fingerprint image having the largest feature value best represents the external feature of the three-dimensional image.

In step S610, the index generation unit 106 generates an index value for the three-dimensional image from the feature value. For example, the index generator 106 may select the variance values of the normalized number of pixels included in each cell of the representative two-dimensional fingerprint image as an index value for the three-dimensional image.

In step S612, the image retrieval unit 108 extracts the index value having the highest similarity with the index value generated in the index generation unit 106 among the index values stored in the database 110, Dimensional image corresponding to the extracted index value is searched for. For example, the image searching unit 108 calculates the difference between the index value stored in the database 110 and the index value generated in the index generating unit 106, extracts the index value having the highest similarity, Dimensional image corresponding to the index value extracted from the three-dimensional image stored in the storage unit 110. [

On the other hand, an embodiment of the present invention may include a program for performing the methods described herein on a computer, and a computer-readable recording medium including the program. The computer-readable recording medium may include a program command, a local data file, a local data structure, or the like, alone or in combination. The media may be those specially designed and constructed for the present invention, or may be those that are commonly used in the field of computer software. Examples of computer-readable media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, and specifically configured to store and execute program instructions such as ROM, RAM, flash memory, Hardware devices. Examples of such programs may include machine language code such as those produced by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, I will understand. Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be determined by equivalents to the appended claims, as well as the appended claims.

100: Image Search System
102: Depth image generation unit
104: fingerprint image generating unit
106: index generation unit
108: Image search unit
110: Database

Claims

A depth image obtaining unit obtaining a two-dimensional depth image representing a contour of the three-dimensional image from a target file including a three-dimensional image;
An index generator for extracting a feature value from the 2D depth image and generating an index value for the 3D image from the feature value; And
And an image retrieval unit for retrieving an index value having the highest similarity to the generated index value among the stored index values and searching for a three-dimensional image corresponding to the index value extracted from the stored three-dimensional images.

The method according to claim 1,
Wherein the depth image obtaining unit obtains a plurality of the two-dimensional depth images by mapping pixels of the three-dimensional image to a two-dimensional plane in multiple directions based on the set axis.

The method of claim 2,
Further comprising a fingerprint image acquiring unit for acquiring a two-dimensional fingerprint image by normalizing the two-dimensional depth image,
Wherein the index generating unit extracts the feature value from the two-dimensional fingerprint image.

The method of claim 3,
Wherein the fingerprint image obtaining unit obtains the two-dimensional fingerprint image by latticing the depth image into a plurality of cells, and normalizing the number of pixels in the cell and the thickness of the contour of the depth image.

The method of claim 4,
Wherein the index generator calculates the feature value by multiplying the sum of the normalized number of pixels included in the two-dimensional fingerprint image by the variance of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum , Image retrieval system.

The method of claim 5,
Wherein the fingerprint image obtaining unit obtains a plurality of the two-dimensional fingerprint images for the plurality of depth images, and obtains a two-dimensional fingerprint image having the largest feature value among the plurality of obtained two- Image search system to select.

The method of claim 6,
Wherein the index generating unit selects the variance values of the normalized number of pixels included in each cell of the representative two-dimensional fingerprint image as an index value for the three-dimensional image.

The method according to claim 1,
Wherein the image searching unit calculates a difference between the stored index value and the generated index value and extracts an index value having the highest degree of similarity with the generated index value among the stored index values.

In the depth image acquiring unit, acquiring a depth image representing a contour of the three-dimensional image from a target file including a three-dimensional image;
Extracting a feature value from the 2D depth image;
Generating an index value for the three-dimensional image from the feature value;
Extracting an index value having the highest degree of similarity with the generated index value among the stored index values in the image searching unit; And
And searching the image searching unit for a three-dimensional image corresponding to the index value extracted from the stored three-dimensional image.

The method of claim 9,
Wherein the acquiring of the two-dimensional depth image acquires a plurality of the two-dimensional depth images by mapping the pixels of the three-dimensional image to the two-dimensional plane in multiple directions based on the set axis.

The method of claim 10,
After obtaining the two-dimensional depth image,
In the fingerprint image acquisition unit, further comprising the step of normalizing the two-dimensional depth image to obtain a two-dimensional fingerprint image,
Wherein the extracting of the feature value extracts the feature value from the two-dimensional fingerprint image.

The method of claim 11,
Wherein acquiring the two-dimensional fingerprint image comprises:
Grating the depth image into a plurality of cells; And
Normalizing the number of pixels in the cell and the thickness of the contour of the depth image.

The method of claim 12,
Wherein the extracting of the feature value comprises multiplying the sum of the normalized number of pixels included in the two-dimensional fingerprint image and the variance value of the number of normalized pixels included in each cell of the two-dimensional fingerprint image with respect to the sum, A method of image retrieval that computes a value.

14. The method of claim 13,
Wherein acquiring the two-dimensional fingerprint image comprises:
Obtaining a plurality of the two-dimensional fingerprint images for the plurality of depth images; And
Selecting a representative two-dimensional fingerprint image as a two-dimensional fingerprint image having the largest feature value among the acquired plurality of two-dimensional fingerprint images.

15. The method of claim 14,
Wherein the step of generating an index value for the three-dimensional image comprises selecting the variance values of the normalized number of pixels included in each cell of the representative two-dimensional fingerprint image as an index value for the three-dimensional image.

The method of claim 9,
The step of extracting the index value having the highest degree of similarity may include calculating a difference between the stored index value and the generated index value and extracting an index value having the highest degree of similarity with the generated index value among the stored index values , Image retrieval method.

Combined with hardware
In the depth image acquiring section, acquiring a depth image representing a contour of the three-dimensional image from the three-dimensional image;
Extracting a feature value from the 2D depth image;
Generating an index value for the three-dimensional image from the feature value;
Extracting an index value having the highest degree of similarity with the generated index value among the stored index values in the image searching unit; And
The image searching unit searches for a three-dimensional image corresponding to the index value extracted from the stored three-dimensional images
The computer program being stored on a recording medium.