KR20080100371A - Video image information processing device, judging method and computer program - Google Patents

Abstract

In a video image information processing device, a video input unit (10) inputs a video image information, a marker detecting unit (21) detects a marker (100) from a video image of the input video image information, a position and posture detecting unit (22) detects a position of the marker (100) of the video image and judges differences between extracted marks in a plurality of video images, respectively. In that case, the position and posture detecting unit (22) is provided with judging conditions based on the position of each marker (100) as at least selectively applied judging conditions.

Description

IMAGE IMAGE INFORMATION PROCESSING DEVICE, JUDGING METHOD AND COMPUTER PROGRAM

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image information processing apparatus, a judging method, and a computer program for judging the difference between the plurality of images and the same mark in each image.

BACKGROUND ART A bar code reader is generally well known as an information presenting device for specifying predetermined related information about an object and / or a predetermined mark (marker) in the real world. Among them, there is an apparatus for specifying information by using spatial information of an object and / or a predetermined marker.

As such an apparatus, for example, US Pat. No. 6,389,182 discloses the following technique. That is, the two-dimensional code printed on the business card is read by the camera, and the ID is analyzed by a program in the computer. Then, the face picture of the person corresponding to this ID is displayed on the display on the computer as if it is next to the two-dimensional code on the business card.

However, in the technique as disclosed in the above-mentioned US Pat. No. 6,389,182, if a cover (marker) of the same design exists in a plurality of images, it is recognized as the same marker. This is due to the problem that each marker cannot be distinguished.

<Start of invention>

This invention is made | formed in view of the above point, and an object of this invention is to provide the image information processing apparatus, the determination method, and the computer program which can determine the difference and the same of the mark which exists in each image among a some image.

An aspect of the image information processing apparatus of the present invention includes image information input means for inputting image information, extraction means for extracting a cover in an image of image information input by the image information input means, and the extraction means. A position detecting means for detecting a position in the image of the cover sheet extracted in step S, and means for determining a difference between the cover sheets extracted from the plurality of images, respectively, and which are at least selectively applied to the position detecting means. And judging means having judging conditions based on the positions of the respective markers detected by the mark.

In addition, one aspect of the method for determining whether the indicia present in each image is different among the plurality of images of the present invention is a step of inputting a plurality of images and a step of flowing out the indicia in each of the input images. And a step of detecting a position on the image of the extracted marker and at least optionally a determination condition based on the detected position of the marker, wherein the image markers extracted from the plurality of input images are different from each other. Characterized in that it comprises a step of determining.

In addition, one aspect of the computer program of the present invention is a computer program for determining, by a computer, that a cover page existing in each image is different among a plurality of images. In the image, a cover sheet is extracted, a position on the image of the extracted cover sheet is detected, and at least selectively applied to a determination condition based on the detected position of the cover sheet, each extracted from the plurality of input images. It is characterized by determining that they are different from each other and the same.

1 is a diagram illustrating a configuration of an image information processing apparatus according to an embodiment of the present invention.

2 is a diagram for explaining an example of a marker that is a marker.

3 is a diagram illustrating a flowchart for explaining the operation of the image information processing apparatus.

FIG. 4 is a flowchart for explaining details of marker identification processing in FIG. 3. FIG.

Fig. 5 is a diagram showing first and second images for explaining the case where the markers picked up by the image input unit increase from one to two.

Fig. 6 is a diagram showing first and second images for explaining the case where the markers picked up by the image input unit are reduced from two to one.

The figure which shows the 1st screen in the case of applying to a nervous breakdown game as an example in the case of using a plurality of same markers.

8 is a diagram illustrating a second screen in a case where a nervous breakdown game is applied as an example of using a plurality of the same markers.

FIG. 9 is a diagram showing a third screen in the case where a plurality of the same markers are used, when applied to a nervous breakdown game. FIG.

Fig. 10 is a diagram showing a fourth screen in the case where a plurality of identical markers are used as an example of a nervous breakdown game.

The figure which shows the 5th screen at the time of applying to the nervous breakdown game in the case of using multiple same markers.

FIG. 12 is a diagram illustrating a sixth screen in the case where a plurality of identical markers are used as an example of a nervous breakdown game.

13 is a diagram illustrating a first configuration example of the configuration of a marker.

14 is a diagram illustrating a second configuration example of the configuration of the marker.

15 is a diagram illustrating a third configuration example of the configuration of the marker.

16 is a diagram illustrating a fourth structural example of the configuration of the marker.

<Best Mode for Carrying Out the Invention>

EMBODIMENT OF THE INVENTION Hereinafter, the best form for implementing this invention is demonstrated with reference to drawings.

An image information processing apparatus according to an embodiment of the present invention has a configuration as shown in FIG. 1, including an image input unit 10 which is a camera, a control unit 20 constituted by a personal computer, and a display unit such as a liquid crystal display ( 30). In addition, of course, you may comprise as a portable apparatus which integrated these image input parts 10, the control part 20, and the display part 30. As shown in FIG. It is also possible to form part of the function of the control unit 20 on a server that can be accessed through a network.

The image input unit 10 functions as image information input means. The image input unit 10 captures a marker 100 which is a mark having a predetermined pattern. And the said image input part 10 inputs into the control part 20 the image information obtained by this imaging | photography. Here, the marker 100 is, for example, as shown in Figure 2, the frame portion 101 of a predetermined shape (square in this embodiment) and the characters recorded inside the frame portion 101 It consists of a symbol or chair 102 including.

The controller 20 includes a marker detector 21, a position and attitude detector 22, a marker information storage 23, a related information generator 24, a related information storage 25, and a superimposed image generator ( 26). Here, the marker detection unit 21 functions as extraction means. The marker detection unit 21 detects the marker 100 as the front cover by detecting the frame 101 from within the image of the image information input by the image input unit 10. The marker detector 21 then supplies the detection result to the position and attitude detector 22 as marker information. The position and attitude detector 22 functions as position detection means, determination means, and similarity evaluation means. The position and posture detection section 22 identifies the corresponding marker from the information stored in the marker information storage section 23 using the marker information from the marker detection section 21. As a result, the position and attitude detector 22 detects the position and attitude of the camera (image input unit 10). The position and attitude detector 22 then supplies the result of the detection to the related information generator 24. The marker information storage unit 23 stores information about the marker 100, such as a template image of the marker 100, position and posture information on which the marker 100 is disposed. The related information generation unit 24 extracts preset information from the related information storage unit 25 according to the position and attitude of the image input unit 10 detected by the position and posture detection unit 22 to obtain related information. Create Then, the related information generating unit 24 supplies the generated related information to the superimposed image generating unit 26. The related information storage unit 25 stores related information such as position and attitude information, shape information, and attribute information of the model disposed on the model space. The superimposed image generating unit 26 superimposes the image information from the image input unit 10 and the related information generated by the related information generating unit 24. The superimposed image generation unit 26 supplies the superimposed image generated by the superimposition to the display unit 30.

In addition, the display unit 30 displays the superposed image generated by the superposed image generating unit 26.

The operation of the image information processing apparatus having the above configuration will be described in detail with reference to the flowchart of FIG. 3.

First, the image input unit 10 captures an image and inputs the obtained image information into the marker detection unit 21 as first image information (step S10). The marker detection unit 21 detects the marker 100 included in the image of the input first image information (step S12). This first detects the marker candidate by detecting the frame portion 101 of the marker 100. Since detection of this frame part 101 is a well-known image processing method, the detailed description is abbreviate | omitted. At this time, the marker candidates to be detected are not limited to one. Next, the coordinates in the four corners of the image of the frame portion 101 of each marker candidate to be detected are detected, and the interior of each frame portion 101 is extracted to perform affine transformation, respectively. And pattern matching with each image after affine conversion, and the template image of the marker previously registered in the marker information storage part 23 (for example, the symbol of "50", etc., or the image of the marker which has the design 102). Do each of them. As a result, if there is no image matching the template image of the marker, the marker 100 is not detected (step S14), and the process returns to the image input step of step S10.

On the other hand, if there is an image that matches the template image of the marker, the marker detection unit 21 assumes that the marker 100 has been detected (step S14). In this case, the position and attitude detection unit 22 obtains the center coordinates of the frame unit 101 from the coordinates of the four corners of the frame unit 101 of the marker detected by the marker detection unit 21, respectively. Let it be the positional information of 100 (step S16). Then, an ID is assigned to each detected marker (step S18). The ID and position information of each marker are also stored in an internal memory (not shown) (step S20).

Thereafter, the image input unit 10 captures an image and inputs the obtained image information into the marker detection unit 21 as the second image information (step S22). The marker detection unit 21 detects the marker 100 included in the image of the input second image information in the same manner as in the step S12 (step S24). Here, if the marker 100 is not detected (step S26), it returns to the image input step of the said step S22.

On the other hand, when the marker 100 is detected (step S26), the position and attitude | position detection part 22 detects the positional information of each marker 100 similarly to the said step S16 (step S28). Then, the position and attitude detection unit 22 executes marker identification processing (step S30).

As shown in FIG. 4, the marker identification processing of step S30 first compares the image similarity of each marker detected from the first image and each marker detected from the second image (step S301). This compares the similarity degree of each marker, without distinguishing between the marker of a 1st image, and the marker of a 2nd image. If the same (similar) marker is not present (step S302), all the IDs of the markers detected and stored from the first image are cleared (step S303). Then, IDs are newly assigned to all the markers detected from the second image (step S304), and the marker identification processing ends.

In contrast, if the same (similar) markers exist (step S302), the same (similar) markers are associated with each other (step S305). This association can be performed in three types: (1) associating only the marker of the first image, (2) associating only the marker of the second image, and (3) associating including the markers of both images. Do. Next, in the associated markers, the markers detected from the second image are associated with the markers detected from the first image in the order in which the distances are close to each other (step S306). This is done for each association, but of course, it is associated only in the case of the association in which the markers of both images of (3) are included. If the numbers of the markers of the first image and the markers of the second image are different from each other, "rest" occurs in many of them. In the case of associating only the marker of the first image of (1) and only the marker of the second image of (2), all the markers are "rest."

Next, in each associated marker, the ID of the marker detected from the first image is posted to the ID of the marker detected from the second image with respect to the correspondence (step S307). This is done for each association, and the "rest" that is not associated in step S307 becomes out of the target of electricity.

Then, except for the above-described ID, all the IDs of the markers detected from the first image are cleared (step S308). That is, the marker only for the first image that is not present in the second image clears all the IDs. Furthermore, IDs are newly assigned to all the markers detected from the second image except for the above-mentioned IDs (step S09). That is, a marker newly generated in the second image assigns a new ID. And this marker identification process is complete | finished.

Here, the operation until this marker identification process is demonstrated using a specific example.

First, the case where the markers imaged by the image input unit 10 increases from one to two will be described with reference to FIG. 5. Here, the marker 100C is the same marker as the marker 100A, and the marker 100B is assumed to be a newly shown marker. In addition, these markers 100A, 100B, and 100C are markers of the same design (symbols and designs 102 are the same).

That is, one process (marker 100A) is detected in the 1st image 41 by the process of said step S10 thru | or step S20. This marker is a marker having a symbol of "50" or a design 102 (for example, in coordinates with (0, 0) on the upper left of the image), its center coordinate is (80, 80), and ID is "1." Is remembered. In addition, by the process of said step S22-step S28, two markers are detected in the 2nd image 42. FIG. Here, one marker 10OB has a symbol of "50" and a design 102, the center coordinate is a marker of (10, 10), and the other marker 100C has the same symbol of "50". With the design 102, the center coordinates are detected to be markers of (90, 90).

In such a case, first, in the identification processing, the current second image (for the marker 100A whose ID detected in the first image 41 by the processing of the steps S301, S305, S306 is "1") The marker 100B detected in 42) and the marker closest to each other within the marker 100C are found. Here, since the center coordinate of the marker 100A of ID "1" is (80, 80), the marker of the marker 100C whose center coordinate is (90, 90) is the marker whose center coordinate is (10, 10) ( The distance is closer than that of 100B). Therefore, the ID of the marker 100C of the center coordinates 90 and 90 is set to "1" by the process of the said step S306, S307. In addition, since the number of markers detected in the first image 41 is one, it is determined that the marker B of the remaining center coordinates 10 and 10 is a marker newly detected in the current second image 42, By the process of the said step S309, "2" is set as ID.

As mentioned above, the marker 100A which has the symbol of "50" detected by the center coordinates 80 and 80 in the 1st image 41, and the design 102 is center coordinates (at the present 2nd image 42). It becomes possible to recognize that it is the marker 100C which has the symbol of "50" and the design 102 which were detected by 90,90. In addition, the marker 100B having the same symbol and designation 102 as "50" detected by the center coordinates 10 and 10 from the current second image 42 can be recognized as a new detection marker. do.

Next, the case where the marker image | photographed by the image input part 10 reduces from two to one is demonstrated with FIG. Here, it is assumed that the marker 100F is the same marker as the marker 100E, and the marker 100D is a marker which becomes invisible.

That is, by the process of said step S10-step S20, two markers are detected in the 1st image 51. FIG. One marker 100D has a symbol of 50 and a design 102, and is stored as a marker having a center coordinate of (10, 10) and an ID of "1". The other marker 100E similarly has a symbol or design 102 of "50" and is stored as a marker whose center coordinates are (90, 90) and ID is "2". In addition, one process (marker 100F) is detected in the 2nd image 52 by the process of the said step S22-step S28. The marker has a symbol of "50" or a design 102 and is detected to be a marker whose center coordinates are (80, 80).

In such a case, first, in the identification processing, the following processing is performed in the above steps S301, S305, and S306. That is, first, the distance from the marker 100F detected by the current second image 52 is obtained for the marker 100D whose ID detected by the first image 51 is "1". Next, with respect to the marker 100E whose lD detected by the first image 51 is "2", the distance from the marker 100F detected by the current 2nd image 52 is calculated | required. And since the marker 100F is the center coordinates 80 and 80, since the marker 100E of the center coordinates 90 and 90 is closest to each other, the markers 100F of the marker 100F are processed by the processing of steps S306 and S307. Set the ID to "2".

In addition, since the number of markers detected by the first image 51 is two, the marker 100D of the remaining center coordinates 10 and 10 is a marker which cannot be detected by the next second image 52. It judges and clears ID "1" by the process of said step S308.

By the above, the marker 100E which has the symbol of "50" and the design 102 which were detected by the center coordinates 90 and 90 in the previous 1st image 51 is centered in the next 2nd image 52. FIG. It becomes possible to recognize that it is the marker 100F which has the symbol of "50" detected by the coordinates 80 and 80, and the design 102. FIG. In addition, the marker 100D having the symbol of "50" and the design 102 detected by the center coordinates 10, 10 in the first image 51 can be recognized as a marker that cannot be detected. .

When the position and attitude detection unit 22 performs the above-described marker identification processing and assigns an ID to each marker in the second image, the ID of each marker and the position information of each marker detected in the step S28. Is stored in an internal memory (not shown) (step S32).

Then, the positional and posture detection section 22 and the marker information storage section 23 obtain spatial positional information (position and posture information on which the marker is placed) of each marker identified. Then, the position and attitude of the camera (image input unit 10) are detected from the positions of the four corners of the frame portion 101 of the marker in the image (step S34). In addition, a method of obtaining a camera position and posture from a marker is, for example, “A High Accurasy Realtime 3D Measuring Method of Marker for VR Interface by Monocular Vision” (3D Image Conference '96 Proceeding pp. 167-172, Akira Takahashi , Ikuo Ishii, Hideo Makino, Makoto Nakashizuka, 1996), and the detailed description thereof is omitted.

The related information generator 24 extracts predetermined information from the related information storage unit 25 according to the position and attitude of the camera (image input unit 10) detected by the position and posture detection unit 22. The relevant information is generated (step S36). The superposed image generating unit 26 superimposes the image from the image input unit 10 and the related information generated by the related information generating unit 24 and displays the superposed image on the display unit 30 (step S38). .

As described above, even when a plurality of markers 100 having the same design (having the same sign or design 102) are photographed at the same time, the respective markers 100 can be distinguished. In addition, it is possible to determine that the markers 100 present in each image are different from each other and are the same.

[Application Example]

Here, as an example of the case where a plurality of markers 100 having the same symbol (or the same symbol or design 102) are used, a case where the present embodiment is applied to a nervous breakdown game will be described.

When this first breakdown game first handed over the first card, and then turned over the second card, if the first and the second were the same card, the character displayed as the related information of the first card is the second. Let's move to the position of the card.

That is, FIG. 7: is a figure which shows the screen 31 of the display part 30 at the time of image | photographing the state which turned over the card 200 which printed the marker 100. FIG. In this case, although there are four cards 200 in the screen 31, since the marker 100 is not recognized, nothing is displayed.

FIG. 8 shows the screen 32 when photographing a state in which one card 200 is turned upside down. In the screen 32 at this time, one marker 100 having the symbol &quot; 50 &quot; and the design 102 printed on the flipped card 200 is detected. Thereby, the character 60 (in this case, "car"), which is the symbol of "50" and the related information corresponding to the design 102, is in a position and posture according to the position and posture of the inverted card 200. Is displayed.

FIG. 9 is a diagram showing a screen 33 when photographing a state in which one card 200 is turned upside down. In this screen 33, two markers 100 having the same symbol and designation 102 of "50" are detected. Therefore, two identical characters 60 (in this case, "car") corresponding to the symbol "50" and the design 102 are displayed in accordance with the position and attitude of each card 200.

In addition, of course, because it is a nervous breakdown game, it is often taken to photograph a state in which a card having another symbol or design 102 is turned upside down as the second sheet. In that case, the symbol of the marker printed on the second card and the character corresponding to the design 102 are displayed according to the posture up to the position of the second card.

Then, as shown in Fig. 9, when the symbol of the marker and the chairman 102 coincide, the matching of the picture is successful. Therefore, in such a case, the display is changed from the screen 33 of FIG. 9 to the screens 34 to 36 as shown in FIGS. That is, the screen 34 of FIG. 10 shows the symbol and design 102 of "50" detected on the second sheet from the position of the marker 100 having the symbol of "50" detected on the first sheet and the design 102. The character 60 (in this case, the "car") is moving toward the marker 100 having the dot). The screen 35 of FIG. 11 completes the movement of the character 60 ("car" in this case), and changes the display to one large character 61. In the screen 36 of FIG. 12, instead of the character 61, a character 62 indicating success is displayed.

In this way, even if a plurality of markers of the same design are used, the respective markers can be distinguished, and therefore, the markers can be used for various purposes, for example, in applications to nervous breakdown games.

As mentioned above, although this invention was demonstrated based on one Example, this invention is not limited to an Example mentioned above, Of course, various deformation | transformation and application are possible within the scope of the summary of this invention.

For example, in the above embodiment, the case where the respective configurations of the control unit 20 are implemented as hardware has been described. However, the same function may be realized by using a computer program and executing it on a computer. For example, each configuration of the control unit 20 may be in the form of a computer program, and the computer program may be stored in advance in a program memory included in the computer. For example, each configuration of the control unit 20 is in the form of a computer program, the computer program is provided by a recording medium such as a CD-ROM, and the computer is read from the recording medium. It may be stored in the program memory. In addition, what is recorded in an external recording medium via a network such as the Internet or a LAN may be downloaded and stored in a program memory.

In the above embodiment, only the case where two images of the first image and the second image are used has been described, but three or more images may be used, and motion prediction may be applied.

In addition, in the above-described embodiment, as shown in FIG. 2, the marker 100 includes a symbol part 101 having a predetermined shape, and a symbol or design including characters written in the interior of the mold part 101. 102). However, the configuration of the marker 100 is not limited to this configuration. For example, various configurations are considered, including four structural examples described below.

<First Configuration Example>

For example, as shown in FIG. 13, the marker 100 may be configured to surround the design 102 with a circular, polygonal, or free-form frame 101 (in the example shown in FIG. 13). Frame 101 is circular).

<2nd structural example>

In addition, as shown, for example in FIG. 14, the marker 100 may be made into the structure which becomes the part of the design 102 inside the frame part 101 itself.

<3rd structural example>

For example, as shown in FIG. 15, the marker 100 may be made into a structure which can be distinguished from other markers only by the design 102, without providing a frame part itself.

Fourth Configuration Example

As shown in Fig. 16, for example, the marker 100 is provided with a symbolic symbol 102A (a heart-shaped mark in this example) around the design 102 (a person's face in this example). Of course, it is good also as a structure.

In addition, in the case where the marker 100 is configured as shown in Figs. 13 to 15, in order to specify the marker 100, the method of pattern matching by the processing in the steps S12 and S14 must be performed. You do not have to use. That is, for example, from the image information obtained from the image input unit 10, a point (hereinafter referred to as a 'feature point') having an image feature is extracted, and the marker information stored in advance in the marker information storage unit 23 is extracted. By evaluating the similarity with each feature point in the template image, it becomes possible to specify the marker 100 included in the image information.

When the matching method by the characteristic point is employ | adopted as mentioned above for the specification of the marker 100, even if the marker 100 overlaps each other or the image information which a part of the marker 100 is missing, the marker 100 is carried out. It becomes possible to specify. That is, in order to specify the marker 100, it is practically effective to employ the matching method by the feature point as mentioned above.

In addition, the matching method by the feature point mentioned above may be applied to calculation of the positional information of the marker 100 by the position and attitude | position detection part 22 (step S16). That is, the position and attitude | position detection part 22 may calculate | require not the position information of the marker 100 from the coordinate of the four corners of the frame part 101 of the said marker 100, but may obtain as follows. That is, based on the center of gravity of the pixel of the marker 100 occupying the image information, the center of gravity of the feature point of the marker 100, or the plurality of points that are widest among the feature points of the marker 100, Of course, the position information may be calculated. Here, the "a plurality of points which are the widest among the feature points of the marker 100" may be three points or four points, for example, and a number of points more than that may be sufficient as it. In addition, of course, the number of the corresponding points may be changed dynamically so as to include all the feature points of the marker 100.

In addition, the position information of each marker 100 obtained by the position and posture detection unit 22 may have not only a position in the image information of each marker 100 but also information on the direction at that position. Of course. Here, the information of the said direction is the said image information, for example, when the image direction at the time of registration of the template image of the marker 100 in the marker information storage part 23 is made into the reference direction (reference axis). Information indicating how much the specific direction of the marker 100 is rotated from the reference axis in the image. In addition, this rotation is not limited to two-dimensional rotation. That is, for example, the three-dimensional posture of the marker may be calculated from the trapezoidal distortion of the marker 100. And this calculation is possible by a well-known technique. The information of the direction which the marker 100 obtained by such calculation can be said to be attitude information in three-dimensional space. In addition, the trapezoidal distortion of the marker 100 can be obtained not only from the rectangular frame as shown in FIG. 2, but also by considering the relative positions of the feature points by the matching method using the feature points described above. .

Claims (7)

Image information input means (10) for inputting image information, Extraction means 21 for extracting the front cover 100 in the image of the image information input by the image information input means 10; Position detecting means 22 for detecting a position in the image of the front cover 100 extracted by the extracting means 21; Determination based on the position of each indicia detected by the position detecting means 22 as a determination condition to be applied at least selectively, as a means for determining the difference between the indicia extracted from a plurality of images, respectively. Determination means 22 with conditions An image information processing device comprising: The method of claim 1, Further comprising similarity evaluating means 22 for evaluating the similarity between the labels 100 extracted by the extracting means 21, The judging means 22 determines the position of the respective marks detected by the position detecting means 22 when it is impossible to determine the difference between the marks 100 by the evaluation result of the similarity evaluating means 22 alone. An image information processing device characterized by performing this determination based on the information. The method of claim 1, The determination means 22 indicates that the distance between the respective indicia 100 derived from the positional information of the respective indicia 100 detected by the position detection means 22 is the same between the nearest indicia 100. The image information processing device characterized by the above-mentioned. Steps S10 and S22 for inputting a plurality of images, Steps S12 and S24 for extracting the front cover 100 in each of the input images, Detecting the positions on the image of the extracted front cover 100 (S16, S28), Step S30 of determining, by applying at least a selection condition based on the detected position of the indicia 100, the difference between two and the same image indicia extracted from the input plurality of images; A determination method for determining whether or not the same as that of the front cover (100) existing in each image among a plurality of images. The method of claim 4, wherein Further comprising the step (S301) of evaluating the similarity between the extracted cover 100, Step S30 for determining the difference between the image indicia is equal to the detection of the position when the determination of the difference between the image indicia is not possible only with the evaluation result of the similarity. The determination method is performed based on the positional information of the respective indicia. The method of claim 4, wherein In step S30 of determining whether the image markers are different from each other and the same, the distance between the respective markers derived from the position information of the respective markers 100 detected by the steps S16 and S28 of detecting the position is the most. A determination method characterized by determining that adjacent signs are the same. A computer program for determining, by a computer, a differentness and the sameness of the front cover 100 existing in each image among a plurality of images, On your computer, Input a plurality of images (S10, S22), In each of the input images, the front cover 100 is extracted (S12, S24), Detecting the position on the image of the extracted cover 100 (S14, S26), Applying a determination condition based on at least the position of the detected cover page 100 at least selectively, it is determined to be different and equal between the image cover pages respectively extracted from the plurality of input images (S30). Computer program, characterized in that.

Images