JP2015210780A - Image processor, image processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To present an image desired by a user to the user by properly retrieving the image.SOLUTION: An image processor includes identification area extraction means for extracting an identification area in which information for identifying a specific object from an image of a retrieval object exists, specification means for specifying identification information of the object from the identification area, determination means for determining the priority of an image as a retrieval result in the case of retrieving the image including the object among a plurality of images on the basis of a positional relation in the image between a target area set to the image and the identification area, and registration means for registering the identification information and the priority in association with the image in storage means.

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program.

For general participation type marathon competitions, etc., there is a service in which photographers take photos of competition participants at shooting points and sell the pictures to participants after the competition. In such a service, it is required to promptly present the participant with a good photo that improves the willingness of the purchase of the competition participant, for example, a photo of the participant himself / herself in the center of the photo.
On the other hand, Patent Document 1 discloses a technique for searching for participants in a moving image taken of a tournament from the estimated passing time to a measurement point in a tournament and editing video for the participant. Has been. Patent Document 2 discloses a technology that uses a bib number assigned by a competitor as individual identification information.
On the other hand, Patent Document 3 discloses a method of extracting a feature amount from a part of an image area specified by position information of a focus of image data and using a term estimated based on the feature amount as metadata of the image. Is disclosed.

JP 2004-112153 A Japanese Patent No. 3069723 JP-A-10-236279

  What participants want is not a good photo of individual identification information represented by a bib number, but a good photo that focuses on the participants themselves. However, in the image search using only the bib number, images that are out of focus on the participant's face and images that the participant is visible on the edge of the photo are extracted. It is difficult to extract an image that a person actually wants to purchase.

  The present invention has been made in view of such problems, and an object of the present invention is to appropriately search for an image suitable for the user's desire and present it to the user.

  Therefore, the present invention is an image processing apparatus, wherein an identification area extracting unit that extracts information for identifying a specific object from an image to be searched exists, and identification information for the object is identified from the identification area. A specifying unit that performs a priority of the image as a search result when searching for an image including the object from a plurality of images, an attention area set for the image, and the identification area , And a registration unit for registering the identification information and the priority in a storage unit in association with the image.

  ADVANTAGE OF THE INVENTION According to this invention, the image suitable for a user's hope can be searched appropriately, and can be shown to a user.

It is a figure which shows the hardware constitutions of an image processing apparatus. It is a figure which shows the software structure of an image processing apparatus. It is a figure which shows the example of an image. It is a flowchart which shows a registration process. It is explanatory drawing of an identification area extraction process. It is a figure which shows an example of a focus point. It is explanatory drawing of a determination area | region setting process. It is explanatory drawing of the positional relationship of an object determination area | region and an attention area. It is a figure which shows an example of the metadata of a picked-up image. It is a figure which shows the processing result with respect to a picked-up image. It is a flowchart which shows an image search process. It is a figure which shows the example of a display of a search result. It is a flowchart which shows the image search process which concerns on a 1st modification. It is a figure which shows the example of a display of the search result which concerns on a 1st modification. It is explanatory drawing of the 3rd example of a change. It is a flowchart which shows the registration process which concerns on 2nd Embodiment. It is a figure which shows an example of an attention area. It is a figure which shows an attention area and a determination area. It is a flowchart which shows the registration process which concerns on 4th Embodiment. It is explanatory drawing of the coordinate system of a picked-up image. It is a figure which shows an attention area and an identification area.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(First embodiment)
FIG. 1 is a diagram illustrating an image processing apparatus 100 according to the present embodiment. The image processing apparatus 100 includes a CPU 101, a memory 102, a hard disk 103, a network I / F 104, and a display 105. The CPU 101 executes a program for performing control of a captured image and recognition processing. The memory 102 is used for work memory when executing a program, temporary storage of data, and the like. The hard disk 103 stores data such as an image obtained by shooting a program or a competition photo. The network I / F 104 performs data input / output. The display 105 reproduces and displays the captured image.
The image processing apparatus 100 may be connected to the network 106 via the network I / F 104. A plurality of hard disks 103 and displays 105 may be connected via the network 106.
Note that the functions and processing of the image processing apparatus 100 described later are realized by the CPU 101 reading out a program stored in the memory 102 or the hard disk 103 and executing the program.

FIG. 2 is a block diagram illustrating a software configuration of the image processing apparatus 100. As shown in FIG. 3, the image processing apparatus 100 registers a plurality of captured images taken at a marathon event as subjects, and is displayed on each captured image. The number number of the participant is recorded as metadata of each photographed image. Then, the image processing apparatus 100 searches for an image for each participant using the participant's number number as a search query.
The photographed image 300 shown in FIG. 3 shows five participants during the competition. As described above, images taken at a marathon competition include few images of a single participant, and there are many cases where a plurality of participants are captured, as in the case of a photographed image 300. For this reason, when searching for a bib number as a search query, an image in which the face of the desired participant is not in focus, an image in which the desired participant is visible on the edge of the image, etc. There is a possibility that an image that the searcher does not want can be obtained.

For example, when the bib number 987 is searched as a search query, the photographed image 300 shown in FIG. 3 is detected. However, although the bib number 987 is shown in the photographed image 300, the face of this participant is not shown. For this reason, the photographed image 300 is not preferable as a search result when the bib number 987 is used as a search query. On the other hand, the image processing apparatus 100 according to the present embodiment appropriately searches for an image that meets the user's desire and provides it to the user.
As a configuration for this, as illustrated in FIG. 2, the image processing apparatus 100 includes, as a software configuration, an identification region extraction unit 201, a character recognition unit 202, an attention region setting unit 203, a priority determination unit 204, A registration unit 205, a search unit 206, and a display unit 207 are included.

The identification area extraction unit 201 extracts an identification area in which information for identifying a specific object exists from a captured image to be processed input from an external device. Specifically, the identification area extraction unit 201 extracts a character area from the target image as an identification area. In the present embodiment, the race bib area indicated by the bib number is extracted as the identification area. For character region extraction processing, for example, Japanese Patent Laid-Open No. 2009-123205 can be referred to. In other words, the identification area extraction unit 201 generates an edge image from the target image, and generates a connected pixel block (hereinafter referred to as “CC”) from the edge image. Then, the identification area extraction unit 201 extracts candidate CC groups arranged in a straight line as a character area as a result of the Hough transform of the coordinate position of the candidate CC that is estimated to be a character from the feature quantity such as the size of the CC.
As another example, the identification area extraction unit 201 may read a newly registered image from the hard disk 103. Hereinafter, the captured image to be processed is referred to as a target image.

The character recognition unit 202 performs character recognition in the character area, and obtains a character string of a bib number as participant identification information. The attention area setting unit 203 sets a focus point at the time of shooting the target image as the attention area. Note that the focus point is one point. It is assumed that information indicating the focus point is input to the image processing apparatus 100 together with the captured image. Then, the attention area setting unit 203 sets the attention area based on the information indicating the focus point.
The priority determination unit 204 sets a priority as a search result when searching for a participant corresponding to the identification area of the target image based on the positional relationship between the identification area and the attention area in the target image.
The registration unit 205 uses the participant identification information and the priority as metadata of the target image, and records the target image including the metadata on the hard disk 103. Thereby, the hard disk 103 stores the target image as a registered image.
The search unit 206 searches the registered image of the hard disk 103 for the photographed image of the participant specified by the identification information using the identification information as a search query. The display unit 207 displays the search result based on the priority.

FIG. 4 is a flowchart showing registration processing by the image processing apparatus 100. In the registration process, the image processing apparatus 100 creates metadata for search for a newly registered image, and registers the captured image in the hard disk 103 together with the metadata.
In S400, the identification area extraction unit 201 extracts an identification area from the target image (identification area extraction process). FIG. 5 is an explanatory diagram of the identification area extraction process. As shown in FIG. 5, five identification areas 501 to 505 corresponding to the five participants are extracted from the captured image 300.

Next, in S401, the character recognition unit 202 performs character recognition in each identification area and obtains a bib number as identification information. Here, the process in S401 is a specification for identifying identification information from the identification area by character recognition processing. It is an example of a process. In step S <b> 402, the registration unit 205 sets identification information and an initial priority value “0” in the metadata of the target image. In the present embodiment, the priority takes two values “0” and “1”, and “1” means that the priority is higher than “0”.
Next, in S403, the attention area setting unit 203 sets the focus point of the target image as the attention area (attention area setting processing). FIG. 6 is a diagram illustrating an example of the focus points 601 to 609 set at the time of shooting. The number of focus points varies from camera to camera. Further, there are cases where only one focus point is set and multi-point focus points are set. In the present embodiment, it is assumed that one focus point is set for the target image.

Returning to FIG. 4, after the process of S403, in S404, the priority determination unit 204 sets a determination area based on the identification area (determination area setting process). FIG. 7 is an explanatory diagram of the determination area setting process. As illustrated in FIG. 7, the priority determination unit 204 sets an area that is an area above the identification area and has a width equal to the identification area as the determination areas 701 to 705 for the identification areas 501 to 505. Thus, setting the determination area above the identification area corresponds to the fact that the participant's head is above the bib number. The priority determination unit 204 determines the range in the vertical direction based on the size of the corresponding identification area.
As another example, the image processing apparatus 100 holds a template in which the size of the determination area is determined, for example, on the hard disk 103 or the like, and the priority determination unit 204 may set the determination area based on the template. Good. Thereby, the amount of calculation for setting the size of the determination region is reduced, and the processing speed can be increased.

Returning to FIG. 4, after the process of S404, in S405, the priority determination unit 204 selects one determination area from the set determination areas as a target determination area to be processed. Next, in S406, the priority determination unit 204 determines whether the target determination area includes the attention area. In the present embodiment, the priority determination unit 204 determines that the target determination area includes the attention area when a certain percentage of the total area of the attention area is included in the target determination area. As another example, the priority determination unit 204 may determine that the target determination area includes the attention area when the attention area is included in the target determination area.
If the target determination area includes the attention area (Yes in S406), the priority determination unit 204 advances the process to S407. If the target determination area does not include the attention area (No in S406), the priority determination unit 204 advances the process to S408.

In S407, the priority determination unit 204 changes the priority associated with the identification information corresponding to the target determination area to a higher value in the metadata. Specifically, the priority determination unit 204 changes the priority from “0” to “1”. Here, the processes of S406 and S407 are an example of a determination process for determining the priority based on the positional relationship between the attention area and the identification area in the target image. Thus, in the present embodiment, the priority determination unit 204 determines a higher priority when the determination region includes the attention region than when the determination region does not include the attention region.
Next, in S408, the priority determination unit 204 confirms whether or not there is an unprocessed determination area where the processes of S406 to S407 are not performed. If there is an unprocessed determination area (Yes in S408), the priority determination unit 204 advances the process to S405. In this case, the priority determination unit 204 selects one determination area from unprocessed determination areas in S405. If there is no unprocessed determination area (No in S408), the priority determination unit 204 advances the process to S409.
In step S409, the registration unit 205 registers the area ID for identifying the identification area, the bib number, and the priority in the hard disk 103 in association with the target image as metadata (registration process). This completes the registration process.

FIG. 8 is an explanatory diagram of the positional relationship between the target determination area and the attention area. In the example shown in FIG. 8A, the attention area 801 is included in the determination area 702 corresponding to the identification area 502. For this reason, “1” is set to the priority corresponding to the identification information (bib number) “123” obtained from the identification area 502, and “0” is set to the priority corresponding to other bib numbers. The
FIG. 9 is a diagram illustrating an example of metadata of the photographed image 300 created corresponding to FIG. The metadata includes an area ID, identification information (bib number), and priority. In the metadata shown in FIG. 9, the priority corresponding to the area ID “302” corresponding to the identification area 302 is set to “1” corresponding to the result of FIG. The corresponding priority is set to “0”.
In the example illustrated in FIG. 8B, the attention area 802 is included in the determination area 705. For this reason, “1” is set to the priority corresponding to the identification information (bib number) “789” obtained from the identification area 505, and “0” is set to the priority corresponding to other identification information. The In the example illustrated in FIG. 8C, the attention area 803 is not included in any of the determination areas 701 to 705. Therefore, the priority corresponding to all the identification information is “0”.

FIG. 10 is a diagram illustrating a processing result of a captured image 1000 different from the captured image 300. In the photographed image 1000, four identification regions 1001 to 1004 corresponding to four participants are extracted. Here, as illustrated in FIG. 10A, the attention area 1020 is included in the determination area 1014 corresponding to the identification area 1004. In this case, as shown in FIG. 10B, in the metadata, the priority of the area ID “1004” corresponding to the identification area 1004 is set to “1”, and the priority of other area IDs is “ 0 "is set.
As described above, the image processing apparatus 100 according to the present embodiment sets a higher priority as a participant search result for an image in which the head of the participant positioned at the upper part of the identification area matches the focus point. can do.

FIG. 11 is a flowchart showing image search processing by the image processing apparatus 100. In S1100, the search unit 206 receives a designation input of identification information (bib number) as a search query (acceptance process). In step S1101, the search unit 206 searches the registered image metadata registered in the hard disk 103 for a registered image including identification information that matches the search query, and acquires a search result (search processing, acquisition). processing). In step S1102, the display unit 207 arranges the registered images obtained by the search based on the priority, and displays the results as a search result (display processing).
FIG. 12 is a diagram illustrating a display example of search results when identification information (bib number) “123” is input as a search query. Assume that the metadata shown in FIGS. 9 and 10B is given to the captured images 300 and 1000 shown in FIG. Among the photographed images 300 and 1000, the photographed image 300 having a higher priority corresponding to the identification information (bib number) “123” is arranged higher than the photographed image 1000. Further, the captured image 300 having a high priority is highlighted with a thick frame.
As described above, the image processing apparatus 100 according to the present embodiment displays the images obtained by the search in order of priority. Therefore, it is possible to appropriately search for an image that meets the user's wish and present it to the user.

As a first modification of the image processing apparatus 100 according to the first embodiment, the image processing apparatus 100 uses only registered images with the priority “1” among the registered images obtained in the search process as search results. It may be displayed. FIG. 13 is a flowchart showing image search processing according to the first modification. In addition, the same number is attached | subjected to the process same as each process in the image search process shown in FIG.
In S1101, when a registered image is obtained by a search using the identification information (bib number) as a search query, the search unit 206 advances the process to S1300. In S1300, the search unit 206 extracts a registered image to which metadata having a priority “1” is assigned from the obtained registered images (image extraction processing). Next, in S1301, the display unit 207 displays the registered image extracted in S1300 as a search result (display process).
FIG. 14 is a diagram illustrating a display example of a search result according to the first modification example when the identification information (bib number) “123” is input as a search query. In the example shown in FIG. 12, the captured images 300 and 1000 including the participant with the identification information (bib number) “123” are displayed, whereas in the search result shown in FIG. 14, the priority “1” is displayed. Only the captured image 1000 to which metadata is assigned is displayed.

As a second modification, the image processing apparatus 100 may determine three or more priority levels. In this case, the image processing apparatus 100 displays a list of search results in which registered images obtained in the image search process are arranged in order of priority.
For example, the image processing apparatus 100 may set the ratio of the area of the overlapping area of the attention area and the determination area to the area of the attention area as the priority. As another example, the image processing apparatus 100 may set the priority according to the position of the attention area. For example, when the attention area is located at the upper center of the image, it is estimated that the participant is reflected in the center. Therefore, in this case, the image processing apparatus 100 sets the priority of the participant corresponding to the attention area at the center of the image to a higher value than the priority of the participant corresponding to the attention area at the edge of the image.

As another example, the image processing apparatus 100 may determine the priority based on the size and position of the identification area. The image processing apparatus 100 may determine a higher priority as the ratio of the size of the identification area to the captured image increases. This corresponds to the fact that the larger the size of the identification area with respect to the size of the image, the higher the possibility that the participant with the number is shown larger.
As another example, the image processing apparatus 100 may determine the priority according to the number of identification regions detected from one image. Specifically, the image processing apparatus 100 determines a higher priority for the participant specified from the identification area of the image as the number of the identification areas detected from one image is smaller. This corresponds to the fact that when there is one participant, there is a high possibility that the participant is in focus.

As a third modification, the image processing apparatus 100 may set the size and shape of the determination area according to the position of the attention area. For example, as shown in FIGS. 15A and 15B, the attention area 1501 of the captured image 1500 is arranged near the center of the image 1500, whereas the attention area 1502 is compared with the attention area 1501. The image 1500 is disposed at a position close to the end of the image 1500. In this case, the image processing apparatus 100 sets a determination area 1511 that is larger than the determination area 1512 corresponding to the attention area 1502 for the attention area 1501. This corresponds to the fact that the person at the center of the image 1500 is more likely to be shown larger than the person at the end.
Furthermore, the image processing apparatus 100 may set determination regions having different sizes and shapes for the same target image according to the vertical and horizontal directions of the image. A photographed image 1520 shown in FIG. 15C is obtained by rotating the photographed image 1500 to the left by 90 °, and an attention area 1503 is an attention area 1502 shown in FIG. 15B shown in FIG. It is placed at the same position. In this case, the determination area 1513 of the attention area 1503 is different in size, size, and size from the determination area 1512, corresponding to the vertical and horizontal directions of the captured image.

As a fourth modified example, information (identification information) for specifying a participant, that is, a person included in an image, is not limited to a bib number. Other examples of information for specifying a person include a name tag, a number assigned to a uniform, and the like. In these cases, the identification area extraction unit 201 extracts a name tag area or a name area in a uniform instead of the race bib area as the identification area. And the character recognition part 202 should just obtain a user's name as identification information by the character recognition of a name tag area | region or a name area.
In the present embodiment, the case where a person in a captured image is registered as a search target has been described as an example. However, the search target may be an object other than a person.

(Second Embodiment)
There may be a case where a plurality of focus points are set when shooting the target image. When there are a plurality of focus points, this image is considered to be an image that is in focus from a short distance to a long distance, that is, a pan focus image. The second image processing apparatus 100 sets a multi-point focus point image in which a plurality of focus points are set as a processing target.
FIG. 16 is a flowchart showing registration processing by the image processing apparatus 100 according to the second embodiment. Here, a process different from the registration process according to the first embodiment described with reference to FIG. 4 will be described. Of the processes of the registration process shown in FIG. 16, the same processes as those of the registration process according to the first embodiment shown in FIG.

In S402, after the identification information and the initial value of the priority are set in the metadata, in S1600, the attention area setting unit 203 sets an area including a plurality of focus points as an attention area (attention area setting processing). Specifically, the attention area setting unit 203 sets a circumscribed rectangle of all focus points as the attention area. FIG. 17 is a diagram illustrating an example of a region of interest. As shown in FIG. 17, it is assumed that three focus points 1701 to 1703 are specified. In this case, the attention area setting unit 203 sets a circumscribed rectangle 1710 of the three focus points 1701 to 1703 as a determination area.
Returning to FIG. 16, after setting the attention area in S <b> 1600, in S <b> 1601, the priority determination unit 204 selects one identification area from the identification areas extracted in S <b> 400 as the target identification area to be processed. . Next, in S1602, the priority determination unit 204 determines whether the target identification area is included in the attention area. In the present embodiment, the priority determination unit 204 determines that the target identification area is included in the attention area when a certain percentage of the total area of the target identification area is included in the attention area. To do. As another example, the priority determination unit 204 may determine that the target identification area is included in the attention area when the target identification area is included in the attention area.

If the target identification area is included in the attention area (Yes in S1602), the priority determination unit 204 advances the process to S1603. If the target identification area is not included in the attention area (No in S1602), the priority determination unit 204 advances the process to S1604. In step S1603, the priority determination unit 204 changes the priority associated with the identification information corresponding to the target identification area to a higher value. Specifically, the priority determination unit 204 changes the priority from “0” to “1”.
In step S1604, the priority determination unit 204 checks whether there is an unprocessed identification area that has not been subjected to the processing in steps S1602 and S1603. If there is an unprocessed identification area (Yes in S1604), the priority determination unit 204 advances the process to S1601. In this case, the priority determination unit 204 selects one identification area from unprocessed identification areas in S1601. If there is no unprocessed identification area (No in S1604), the priority determination unit 204 advances the process to S409.

In the example illustrated in FIG. 17, the identification area 502 is included in the attention area 1710. Therefore, when the identification area 502 is set as the target identification area, the process proceeds to S1603, and “1” is set as the priority. On the other hand, an identification area other than the identification area 502 is not included in the attention area 1710. Therefore, when an identification area other than the identification area 502 is set as the target identification area, the process proceeds to S1604, and “0” is set as the priority. Other configurations and processes of the image processing apparatus 100 according to the second embodiment are the same as the configurations and processes of the image processing apparatus 100 according to the first embodiment.
As described above, the image processing apparatus 100 according to the second embodiment can set an appropriate priority for a search result with a captured image having multiple focus points as a processing target.

(Third embodiment)
The image processing apparatus 100 according to the third embodiment detects a face area in a photographed image and sets the face area as a region of interest. Specifically, in S403, the attention area setting unit 203 performs face recognition processing on the captured image and sets the detected face area as the attention area. In step S406, the priority determination unit 204 confirms whether the target determination area includes the attention area.
In S403, when a plurality of attention areas are set, in S406, when the target determination area includes any one attention area among the plurality of attention areas set in S403, target determination is performed. It is determined that the area includes the attention area. Then, the priority determination unit 204 sets the priority to “1” when the target determination area includes the attention area, and sets the priority to “0” when the target determination area does not include the attention area. .

  In the example illustrated in FIG. 18, attention areas 1802 to 1805 are set. Determination areas 702 to 705 corresponding to the identification areas 502 to 505 include attention areas 1802 to 1805, respectively. Therefore, the priority “1” is set for the identification information corresponding to the determination areas 702 to 705. Other configurations and processes of the image processing apparatus 100 according to the third embodiment are the same as the configurations and processes of the image processing apparatus 100 according to the other embodiments.

  As described above, the image processing apparatus 100 according to the third embodiment specifies the attention area by face recognition, and searches for each participant based on the positional relationship between the attention area and the determination area determined from the identification area. The result priority can be set. Note that the image processing apparatus 100 may set the attention area based on the information obtained from the captured image as described above, and specific processing for that purpose is not limited to the embodiment.

(Fourth embodiment)
The image processing apparatus 100 according to the fourth embodiment sets priorities based on the angle between the identification area and the attention area instead of setting the determination area. FIG. 19 is a flowchart showing registration processing by the image processing apparatus 100 according to the fourth embodiment. Here, a process different from the registration process according to the first embodiment will be described. Among the processes of the registration process shown in FIG. 19, the same processes as the processes of the registration process according to the first embodiment shown in FIG.
In the present embodiment, as shown in FIG. 20, the image processing apparatus 100 has a coordinate system in which the upper left corner of the captured image is the origin, the x axis is from left to right, and the y axis is from top to bottom. In FIG. 3, the captured image is processed.

Referring back to FIG. 19, after the attention area is set in S403, in S1900, the priority determination unit 204 selects one identification area from among the identification areas extracted in S400 as the target identification area to be processed. . In step S1901, the priority determination unit 204 confirms whether the target identification area is below the attention area. The priority determination unit 204 determines that the identification area is below the attention area when the coordinate value of the upper end of the target identification area is larger than the coordinate value of the lower end of the attention area.
For example, it is assumed that the attention area 2100 shown in FIG. 21 is set. In this case, the identification areas 502 to 505 are determined to be below the attention area 2100, and the identification area 501 is determined not to be below the attention area 2100.

If the target identification area is below the attention area (Yes in S1901), the priority determination unit 204 advances the process to S1902. If the target identification area is not below the attention area (No in S1901), the priority determination unit 204 advances the process to S1904. In S1902, the priority determination unit 204 calculates tan θ with respect to an angle θ formed by a straight line 2000 extending in parallel to the x axis from the attention area and a straight line 2001 connecting the identification area and the attention area as shown in FIG. . Then, the priority determination unit 204 compares tan θ with the threshold value α. Here, tan θ is less than the threshold value when the attention area and the identification area are in substantially the same positional relationship in the x-axis direction.
If tan θ is less than the threshold α (Yes in S1902), the priority determination unit 204 advances the process to S1903. If tan θ is greater than or equal to the threshold α (No in S1902), the priority determination unit 204 advances the process to S1904. In S1903, the priority determination unit 204 changes the priority associated with the identification information corresponding to the target determination area to a higher value in the metadata.

  In step S1904, the priority determination unit 204 checks whether there is unprocessed identification information that has not been subjected to the processing in steps S1902 and S1903. If there is unprocessed identification information (Yes in S1904), the priority determination unit 204 advances the process to S1900. In this case, the priority determination unit 204 selects one identification area from unprocessed identification information. If there is no unprocessed identification information (No in S1904), the priority determination unit 204 advances the process to S409. The other configurations and processes of the image processing apparatus 100 according to the fourth embodiment are the same as the configurations and processes of the image processing apparatus 100 according to the other embodiments.

As described above, the image processing apparatus 100 according to the fourth embodiment compares the threshold value with the angle θ formed by the straight line 2000 extending parallel to the x-axis from the attention area and the straight line 2001 connecting the identification area and the attention area. . Therefore, the image processing apparatus 100 can make a determination according to the positional relationship by changing the threshold value according to the positional relationship between the identification area and the attention area. For example, the case where the participant's head is at a position inclined from the upper part of the bib number may be considered. Even in such a case, an appropriate priority can be set by setting an appropriate threshold. In this case, the image processing apparatus 100 may set the range of tan θ and set the priority according to whether the range is within the range.
The image processing apparatus 100 may determine the priority based on the positional relationship between at least one of the distance and the angle between the identification region and the attention region, and the specific positional relationship is not limited to the embodiment. .

<Other embodiments>
The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media. Then, the computer (or CPU, MPU, etc.) of the system or apparatus reads and executes the program.

  As mentioned above, according to each embodiment mentioned above, the image suitable for a user's hope can be searched appropriately, and it can present to a user.

  The preferred embodiments of the present invention have been described in detail above, but the present invention is not limited to such specific embodiments, and various modifications can be made within the scope of the gist of the present invention described in the claims.・ Change is possible.

100 Image processing apparatus 101 CPU
201 Identification area extraction section 203 Attention area setting section 204 Priority determination section 205 Registration section 206 Search section 207 Display section

Claims (15)

An identification area extracting means for extracting an identification area in which information for identifying a specific object is present from an image to be searched;
A specifying means for specifying identification information of the object from the identification region;
As a search result when searching for an image including the object from a plurality of images, the priority of the image is a region of interest set for the image and the identification region in the image Determining means for determining based on the positional relationship;
An image processing apparatus comprising registration means for registering the identification information and the priority in a storage means in association with the image. Receiving means for receiving the identification information;
In the storage means, search means for searching for an image associated with the identification information;
Image extraction means for extracting an image to be displayed as a search result based on the priority from the images obtained by the search means;
The image processing apparatus according to claim 1, further comprising display means for displaying an image extracted by the image extraction means. Receiving means for receiving the identification information;
Search means for searching for an image associated with the identification information;
The image processing apparatus according to claim 1, further comprising: a display unit that arranges and displays the images obtained by the search unit based on the priority.   The image processing apparatus according to claim 1, wherein the registration unit registers the identification information and the priority in a storage unit as metadata of the image.   The image processing apparatus according to claim 1, wherein the specifying unit specifies identification information from the identification area by character recognition processing. The image is a photographed image photographed by a photographing device,
It further has attention area setting means for setting a focus point at the time of shooting the image as an attention area,
6. The determination unit according to claim 1, wherein the determination unit determines the priority based on a positional relationship between the attention region set by the attention region setting unit and the identification region. The image processing apparatus according to item.   The image processing apparatus according to claim 6, wherein the attention area setting unit sets an area including each focus point as the attention area when there are multiple focus points. The object is a person;
From the image, further comprising attention area setting means for setting a human face area as the attention area,
6. The determination unit according to claim 1, wherein the determination unit determines the priority based on a positional relationship between the attention region set by the attention region setting unit and the identification region. The image processing apparatus according to item. A determination area setting means for setting a determination area based on the position of the identification area;
The determination means determines a higher priority when the determination area includes the attention area than when the determination area does not include the attention area. The image processing apparatus according to item.   The said determination means determines the said priority based on the positional relationship of at least one among the distance and the angle between the said attention area | region and the said identification area | region, The said priority is characterized by the above-mentioned. The image processing apparatus described. Accepting means for accepting designation of identification information of a specific object included in an image to be searched;
An image including an object specified by the identification information from among a plurality of images based on a positional relationship in the image between an identification region where the identification information exists and a region of interest set for the image An image search apparatus comprising: an acquisition means for acquiring a search result of An image processing method executed by an image processing apparatus,
An identification region extraction step for extracting an identification region in which information for identifying a specific object exists from an image to be searched; and
A specific step of identifying identification information of the object from the identification region;
As a search result when searching for an image including the object from a plurality of images, the priority of the image is a region of interest set for the image and the identification region in the image A determination step for determining based on the positional relationship;
An image processing method comprising: a registration step of registering the identification information and the priority in a storage unit in association with the image. An image search method executed by an image search device,
An accepting step for accepting specification of identification information of a specific object included in an image to be searched;
An image including an object specified by the identification information from among a plurality of images based on a positional relationship in the image between an identification region where the identification information exists and a region of interest set for the image An image search method comprising: an acquisition step of acquiring a search result of Computer
An identification area extracting means for extracting an identification area in which information for identifying a specific object is present from an image to be searched;
A specifying means for specifying identification information of the object from the identification region;
As a search result when searching for an image including the object from a plurality of images, the priority of the image is a region of interest set for the image and the identification region in the image Determining means for determining based on the positional relationship;
A program for functioning as registration means for registering the identification information and the priority in a storage means in association with the image. Computer
Accepting means for accepting designation of identification information of a specific object included in an image to be searched;
An image including an object specified by the identification information from among a plurality of images based on a positional relationship in the image between an identification region where the identification information exists and a region of interest set for the image A program for functioning as an acquisition means for acquiring the search results.

Images