JP2017184021A - Content providing device and content providing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a content suitable for a user for each photographic scene.SOLUTION: A content providing device 10 comprises an image acquisition unit 11 that acquires a target image as an image to be processed, an evaluation information acquisition unit 13 that acquires evaluation information associated with a plurality of evaluation items including a photographic scene to the target image, a scene dependent user information extraction unit 17 that extracts scene dependent user information being information associated with a user for each photographic scene on the basis of the evaluation information, a content storage unit 19 that stores a plurality of contents associated with imaging, a content selection unit 20 that selects the content from the plurality of contents stored in the content storage unit 19 on the basis of the scene dependent user information, and an output unit 22 that outputs the content selected by the content selection unit 20.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a content providing apparatus and a content providing program.

  Conventionally, in order to improve a user's photographing technique, there is a method of providing advice based on an image photographed by a user. For example, Patent Document 1 describes a camera that divides shooting advice for beginners, intermediate users, and advanced users and displays shooting advice according to the shooting level of the user.

JP 2000-333045 A

  However, the user's shooting technique, user's preference, and the like may differ depending on the shooting scene. For example, there may be a user who is good at shooting landscapes but is not good at portrait shooting. In addition, a photographer who likes the user may differ between a landscape photograph and a night view photograph. In the camera described in Patent Literature 1, the user's shooting technique and preference for each shooting scene are not considered. For this reason, there is a possibility that advice suitable for the user may not be displayed. In this technical field, it is desired to provide content such as advice suitable for the user for each shooting scene.

  The present invention provides a content providing apparatus and a content providing program capable of providing content suitable for a user for each shooting scene.

  A content providing apparatus according to an aspect of the present invention relates to an image acquisition unit that acquires a target image that is an image to be processed, and a plurality of evaluation items that include a shooting scene with respect to the target image acquired by the image acquisition unit. Evaluation information acquisition means for acquiring evaluation information, extraction means for extracting user information by scene, which is information relating to the user for each shooting scene, based on the evaluation information acquired by the evaluation information acquisition means, and a plurality of contents relating to shooting Content storage means for storing the content, selection means for selecting content from a plurality of contents stored in the content storage means based on the user information for each scene extracted by the extraction means, and the content selected by the selection means Output means for outputting.

  A content providing program according to another aspect of the present invention includes an image acquisition unit that acquires a target image that is a processing target image, and a plurality of evaluation items that include a shooting scene with respect to the target image acquired by the image acquisition unit. The evaluation information acquisition means for acquiring the evaluation information regarding, the extraction means for extracting user information for each scene, which is information about the user for each shooting scene, based on the evaluation information acquired by the evaluation information acquisition means, and the extraction means Based on the scene-specific user information, the computer functions as a selection unit that selects content from a plurality of content related to shooting and an output unit that outputs the content selected by the selection unit.

  In the content providing apparatus and the content providing program, evaluation information regarding a plurality of evaluation items including a photographic scene is acquired for the acquired target image, and a scene that is information regarding a user for each photographic scene based on the evaluation information. Another user information is extracted. Then, based on the user information for each scene, the content is selected from a plurality of contents related to shooting and output. As a result, the content is selected in consideration of information related to the user according to the shooting scene, so that it is possible to provide content suitable for the user for each shooting scene.

  The evaluation information may include an evaluation value calculated based on a predetermined evaluation criterion. The extraction means calculates the evaluation value for each scene, which is the evaluation value for each shooting scene, by counting the evaluation values acquired by the evaluation information acquisition means for each shooting scene, and uses the evaluation value for each scene as the user information for each scene. It may be extracted. The evaluation value for each scene can be regarded as a value reflecting the user's shooting technique for each shooting scene. For this reason, the content is selected in consideration of the user's shooting technique for each shooting scene, and therefore it is possible to provide content according to the user's shooting technique for each shooting scene.

  The extraction means may extract the preference information by scene indicating the photographer preferred by the user for each shooting scene among the plurality of photographers as the user information by scene. The scene-specific preference information represents the user's preference for each shooting scene. For this reason, since the user's preference for each shooting scene is taken into consideration, the content is selected according to the user's preference for each shooting scene.

  The extraction unit is configured to analyze each scene based on feature information indicating a tendency of a shooting scene taken by the photographer for each of the plurality of photographers and preference information indicating a photographer preferred by the user among the plurality of photographers. Preference information may be calculated. In this case, the preference information for each scene can be obtained without selecting the photographer preferred by the user for each shooting scene.

  The content providing apparatus may further include update means for updating the preference information for each scene. In this case, the selected content can be changed according to a change in the user's preference.

  The content providing apparatus may further include an editing unit that edits the content selected by the selection unit based on the scene-specific user information. The output unit may output the content edited by the editing unit. In this case, for example, the user's interest can be attracted by reflecting the information about the user for each shooting scene in the content. Thereby, it becomes possible to improve a user's browsing rate with respect to the provided content.

  According to the present invention, it is possible to provide content suitable for the user for each shooting scene.

It is a block diagram which shows the function structure of the content provision apparatus which concerns on 1st Embodiment. It is a block diagram which shows the hardware constitutions of the content provision apparatus of FIG. It is a figure which shows an example of evaluation information. It is a figure which shows an example of user preference information. It is a figure which shows an example of photographer information. It is a figure which shows an example of the evaluation table classified by scene. It is a figure which shows an example of the preference photographer table classified by scene. It is a figure which shows an example of a content table. It is a figure which shows the example of the synthesized image output by the content provision apparatus of FIG. It is a figure which shows the example of the synthesized image output by the content provision apparatus of FIG. It is a figure which shows the example of the synthesized image output by the content provision apparatus of FIG. It is a figure which shows the example of the synthesized image output by the content provision apparatus of FIG. It is a figure which shows the example of the synthesized image output by the content provision apparatus of FIG. It is a figure which shows an example of the preference photographer table updated by the user preference information update part of FIG. It is a flowchart which shows a series of processes of the content provision method which the content provision apparatus of FIG. 1 performs. It is a figure for demonstrating a content provision program. It is a block diagram which shows the function structure of the content delivery system containing the content provision apparatus which concerns on 2nd Embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

(First embodiment)
A content providing apparatus according to the first embodiment will be described. FIG. 1 is a block diagram illustrating a functional configuration of the content providing apparatus according to the first embodiment. A content providing apparatus 10 shown in FIG. 1 is an apparatus used by a user. The content providing device 10 is a terminal device including, for example, a digital camera, a mobile phone, a smartphone, a tablet terminal, and a PC (Personal Computer). In the following description, the content providing apparatus 10 will be described mainly assuming that the content providing apparatus 10 is a terminal such as a smartphone having a camera function. However, the content providing apparatus 10 is not limited to a terminal having a camera function. .

  The content providing apparatus 10 is an apparatus that selects content based on scene-specific user information that is information related to a user for each shooting scene, and provides the selected content with respect to a target image that is a processing target image. Examples of the target image include photographs including subjects such as people, animals, and landscapes. Shooting scenes include, for example, landscapes, portraits, airplanes, underwater, celestial bodies, macros, and night views. The provided content is content related to shooting, and examples of content types include advice, articles, advertisements, and photos. The content providing apparatus 10 is configured by, for example, hardware shown in FIG.

  FIG. 2 is a diagram illustrating a hardware configuration of the content providing apparatus 10. As shown in FIG. 2, the content providing apparatus 10 physically includes one or more CPUs (Central Processing Units) 101, a RAM (Random Access Memory) 102 and a ROM (Read Only Memory) that are main storage devices. 103, a communication module 104 that is a data transmission / reception device, an auxiliary storage device 105 such as a hard disk and a semiconductor memory, an input device 106 that accepts user input such as input keys and touch sensors, an output device 107 such as a display, And a camera module 108. Each function of the content providing apparatus 10 shown in FIG. 1 is configured such that one or a plurality of predetermined computer software is read on hardware such as the CPU 101 and the RAM 102, so that the communication module 104 and the input device are controlled under the control of the CPU 101. 106, the output device 107, and the camera module 108 are operated, and data is read and written in the RAM 102 and the auxiliary storage device 105.

  With reference to FIG. 1 again, details of each function of the content providing apparatus 10 will be described. Functionally, the content providing apparatus 10 functionally includes an image acquisition unit 11, an image information storage unit 12, an evaluation information acquisition unit 13, an evaluation information storage unit 14, a user preference information storage unit 15, and photographer information storage. Unit 16, scene-specific user information extraction unit 17, scene-specific user information storage unit 18, content storage unit 19, content selection unit 20, content editing unit 21, output unit 22, and user preference information update unit 23.

  The image acquisition unit 11 functions as an image acquisition unit that acquires a target image. The image acquisition unit 11 is realized by the camera module 108, for example. Specifically, the image acquisition unit 11 includes a plurality of optical system components such as lenses and optical elements, a plurality of control system circuits that drive and control them, and an electrical signal that represents a target image acquired by the light receiving element. A signal processing system circuit unit for converting the signal into an image signal which is a digital signal. The image acquisition unit 11 stores image information including an image signal in the image information storage unit 12. The acquired image information may be moving image information or still image information.

  When the content providing apparatus 10 does not have a camera function, the image acquisition unit 11 receives, for example, an image captured by another apparatus (for example, a terminal having the camera function described above) from the other apparatus. Get an image. For example, when the content providing apparatus 10 receives an image file from another apparatus via a communication network, a part that performs image file reception processing (such as the communication module 104) functions as the image acquisition unit 11. The target image (each frame in the case of a moving image) acquired by the image acquisition unit 11 is, for example, image information indicating a pixel value of each pixel (for example, a numerical value related to a pixel such as luminance, brightness, and color). Get as. The image acquisition unit 11 outputs and stores such image information to the image information storage unit 12.

  The image information storage unit 12 functions as an image information storage unit that stores the image information acquired by the image acquisition unit 11. The image information stored in the image information storage unit 12 is referred to by the evaluation information acquisition unit 13 and the output unit 22.

  The evaluation information acquisition unit 13 functions as an evaluation information acquisition unit that acquires evaluation information regarding a plurality of evaluation items including a shooting scene for the target image acquired by the image acquisition unit 11. The evaluation information includes an evaluation value related to the overall appearance of the target image, shooting information related to the shooting conditions of the target image, and shooting scene information indicating the shooting scene of the target image. The evaluation value is calculated based on an evaluation criterion that is predetermined for each of the plurality of evaluation items.

  FIG. 3 is a diagram illustrating an example of the evaluation information. In the example shown in FIG. 3, the evaluation items include “total score”, “Comp”, “Noise”, “Pint”, “Vivid”, “Cont”, “F”, “Ss”, “Iso”, “Focal distance”, “Body name”, and “Shooting scene” are included.

  The “total score” is an evaluation item for comprehensive evaluation of the target image. The evaluation information of “total score” is an evaluation value obtained by summing evaluation values of “Comp”, “Noise”, “Pint”, “Vivid”, and “Cont”. “Comp” is an evaluation item as to whether or not the target image is faithful to a preset composition pattern. The evaluation information “Comp” is an evaluation value that can take a value of +100 to −100, for example. “Noise” is an evaluation item as to whether or not there is an unnecessary reflection in the target image. The evaluation information of “Noise” is an evaluation value that can take a value of +100 to −100, for example. “Pint” is an evaluation item as to whether or not the target image is in focus (the subject is not blurred). The evaluation information of “Pint” is an evaluation value that can take a value of +100 to −100, for example. “Vivid” is an evaluation item as to whether or not the color of the target image is moderately vivid. The evaluation information “Vivid” is, for example, an evaluation value that can take a value of +100 to −100. “Cont” is an evaluation item as to whether or not the contrast of the target image is appropriate. The evaluation information “Cont” is an evaluation value that can take a value of +100 to −100, for example.

  “F” is an evaluation item for the aperture of the lens of the camera. The evaluation information “F” is a set value (F value) with respect to the aperture of the lens of the camera that captured the target image. For example, 1.4, 2.0, 2.8, 4.0, and 5.6. Etc. “Ss” is an evaluation item for the shutter speed of the camera. The evaluation information “Ss” is a set value for the shutter speed of the camera that captured the target image. “Iso” is an evaluation item for the ISO sensitivity of the camera. The evaluation information “Iso” is a set value for the ISO sensitivity of the camera that has captured the target image. “Focal distance” is an evaluation item for the distance from the imaging surface of the camera to the focal point. The evaluation information of “focal length” is a set value with respect to the distance from the imaging surface of the camera that captured the target image to the focal point, and is set to be short for a wide angle and set to be long for a telephoto. “Body name” is an evaluation item for the name of the camera body. The evaluation information of “body name” is a character string indicating the name of the camera body that captured the target image. The “shooting scene” is an evaluation item for the shooting scene of the target image. The evaluation information of “shooting scene” is shooting scene information indicating the shooting scene of the target image.

  First, an example of processing for acquiring an evaluation value for a target image will be described. For example, the evaluation information acquisition unit 13 divides the target image into partial regions. The partial area is an area obtained by dividing the target image using an arbitrary area dividing method. Since the method of area division itself is known, detailed description thereof is omitted. For example, the evaluation information acquisition unit 13 refers to the image information stored in the image information storage unit 12 and based on the pixel value of each pixel. To execute processing such as edge detection. By executing such region division processing, the evaluation information acquisition unit 13 satisfies the uniformity criteria set in advance for each partial region, and the union of two adjacent partial regions is the above one. The image is divided into a plurality of partial regions that do not overlap with each other so as not to satisfy the criteria for the appearance.

  The evaluation information acquisition unit 13 calculates area information for each of the divided partial areas. The area information is information in which pixel coordinates that identify each pixel of the target image are associated with an area ID (Identification) that identifies a partial area to which the pixel belongs. The pixel coordinates are expressed by, for example, XY coordinates that define the horizontal direction of the target image as the X-axis direction and the vertical direction of the target image as the Y-axis direction. As an example in the present embodiment, the pixel coordinates are the coordinates of the pixel at the upper left corner of the target image as the origin coordinates (0, 0), the right direction of the target image is the positive direction of the X axis, and the downward direction of the target image is Y It is expressed as XY coordinates when the axis is in the positive direction.

  The evaluation information acquisition unit 13 calculates each score of a plurality of evaluation items for each partial region. In this embodiment, as an example, the evaluation information acquisition unit 13 calculates Comp (i, j), Noise (i), Pint (i), Vivid (i), and Cont (i) for each partial region i.

  The evaluation information acquisition unit 13 extracts pixels (pixel coordinates) included in the partial area i from the area information of the partial area i. Thereby, the evaluation information acquisition unit 13 grasps the range occupied by the partial area i in the target image. Further, the evaluation information acquisition unit 13 grasps the pixel values of the pixels included in the partial region i by referring to the image information stored in the image information storage unit 12. The evaluation information acquisition unit 13 calculates the score of each evaluation item described above based on the range occupied by the partial area i in the target image and the pixel value of each pixel included in the partial area i. Hereinafter, an example of a method for calculating the score of each evaluation item will be described.

  Comp (i, j) is a score of an evaluation item regarding whether or not the partial area i is faithful to a composition pattern j set in advance (for example, a composition pattern selected by default setting or user setting). For example, the evaluation information acquisition unit 13 holds in advance composition pattern information indicating the evaluation logic of the composition pattern j (for example, a three-part composition). By using the composition pattern information, Comp (i , J). Here, the evaluation logic is information such as an evaluation function (calculation formula) used to calculate a score related to the composition, which is the degree that the partial area i is faithful to the composition pattern j.

  Hereinafter, a case where the composition pattern j is a three-part composition will be described as a specific example. The closer the center of gravity of the subject is to the intersection of virtual lines that divide the target image vertically and horizontally (intersection of virtual lines extending in the vertical direction and virtual lines extending in the horizontal direction), the more faithful to the three-division composition. For this reason, as the composition pattern information of the three-part composition, an evaluation function can be used such that the value increases as the distance between the center of gravity of the partial region i and the intersection point decreases. Further, for example, when the outline of a background portion such as the sea and the sky (for example, a horizontal line and a horizon line) matches the virtual line, it can be said to be faithful to the three-part composition. Therefore, an evaluation function that increases as the degree of coincidence between the contour of the partial region i and the virtual line can be used as the composition pattern information of the three-part composition.

  Noise (i) is a score of an evaluation item regarding whether or not the partial area i is not an unnecessary reflection. Noise (i) is calculated to be large when the partial area i is not an unnecessary reflection, and to be small when the partial area i is an unnecessary reflection. For example, the evaluation information acquisition unit 13 determines whether or not the partial area i is in contact with the end of the target image based on the range occupied by the partial area i extracted from the area information of the partial area i. Specifically, the evaluation information acquisition unit 13 determines whether or not the partial area i includes a pixel corresponding to the pixel coordinate at the end of the target image. It is determined that it touches the edge of the image. When it is determined that the partial area i is not in contact with the end of the target image, the evaluation information acquisition unit 13 determines that the partial area i is not an unnecessary reflection. On the other hand, the evaluation information acquisition unit 13 determines that the partial area i is in contact with the end of the target image (that is, that a part of the subject corresponding to the partial area i is outside the target image. If it is assumed), it is determined that the partial area i is an unnecessary reflection.

  Here, when the partial area i is unnecessary reflection, it is considered that the larger the area of the partial area i, the higher the possibility that the partial area i has an adverse effect on the appearance of the target image. Therefore, when it is determined that the partial area i is an unnecessary reflection, the evaluation information acquisition unit 13 calculates Noise (i) so that the larger the area of the partial area i is, the smaller Noise (i) is. To do. Note that the background portion is in contact with the edge of the target image, but it cannot be said to be an unnecessary reflection. Therefore, the evaluation information acquisition unit 13 excludes such a background portion from an object to be determined as unnecessary reflection, for example, a partial area i (in contact with four sides (or more than three sides) of the target image). It may be determined that the partial area i) that is likely to be a background part is not an unnecessary reflection.

  Pint (i) is a score of an evaluation item regarding whether or not the partial area i is in focus (whether the partial area i is not blurred). For example, the evaluation information acquisition unit 13 calculates the spatial frequency in the partial region i from the pixel values of the pixels included in the partial region i. In general, the spatial frequency tends to be low in a region where the image is out of focus and the image is blurred. Therefore, the evaluation information acquisition unit 13 calculates Pint (i) so that Pint (i) increases as the spatial frequency increases.

  Vivid (i) is a score of an evaluation item regarding whether or not the color of the partial area i is moderately vivid. For example, the evaluation information acquisition unit 13 increases the Vivid (Saturation) representative value (for example, an average value) of a pixel included in the partial area i and the smaller the error between a preset appropriate level (appropriate value). Vivid (i) is calculated so that the value of i) increases. In addition, when the image information (pixel value of each pixel) stored in the image information storage unit 12 is expressed in the RGB color space, the evaluation information acquisition unit 13 is a well-known one from the RGB color space to the HSV color space. Information on saturation (S), which is one component of the HSV color space, may be obtained by performing the conversion process.

  Cont (i) is a score of an evaluation item regarding whether or not the partial area i contributes to the optimization of the contrast of the target image. The evaluation information acquisition unit 13 calculates Cont (i) so that Cont (i) increases as the degree to which the partial region i contributes to optimization of the contrast of the target image is larger. For example, the evaluation information acquisition unit 13 calculates the contrast value Cnt1 of the target image and calculates the contrast value Cnt2 of the target image when the partial region i is excluded from the target image. Here, the absolute value A1 (= | Cnt1-Cnt0 |) of the difference between the preset appropriate contrast level (proper value) Cnt0 and the contrast value Cnt1 is the absolute value of the difference between the appropriate contrast level Cnt0 and the contrast value Cnt2. If it is smaller than A2 (= | Cnt2-Cnt0 |), it can be said that the partial region i contributes to optimization of the contrast of the target image. That is, it can be said that the presence of the partial region i brings the contrast of the target image close to an appropriate value. In addition, it can be said that the greater the difference (A2−A1) between the absolute value A1 and the absolute value A2, the greater the extent that the partial region i contributes to the optimization of the contrast of the target image. Therefore, the evaluation information acquisition unit 13 calculates Cont (i) based on the difference (A2−A1) between the absolute value A1 and the absolute value A2 so that the larger the difference is, the larger Cont (i) is. May be.

  The evaluation information acquisition unit 13 adds Comp (i, j), Noise (i), Pint (i), Vivid (i), and Cont (i) of each partial area for each evaluation item, and thereby Comp Evaluation values for evaluation items of, Noise, Pint, Vivid, and Cont are acquired.

  When the camera module 108 conforms to the EXIF (Exchangeable image file format) standard, the shooting information regarding the shooting condition of the target image is attached as metadata to the target image. The evaluation information acquisition unit 13 acquires shooting information from the metadata. The evaluation information acquisition unit 13 may acquire shooting information from the camera module 108.

  The evaluation information acquisition unit 13 acquires shooting scene information of the target image by a known scene recognition technique. For example, the evaluation information acquisition unit 13 extracts the feature amount of the target image based on the image information of the target image, and recognizes the shooting scene by comparing the feature amount of the target image with the feature amount of each shooting scene. . The evaluation information acquisition unit 13 outputs the evaluation information of the target image to the evaluation information storage unit 14 and stores it.

  The evaluation information storage unit 14 functions as an evaluation information storage unit that stores the evaluation information acquired by the evaluation information acquisition unit 13. The evaluation information stored in the evaluation information storage unit 14 is referred to by the scene-specific user information extraction unit 17, the content selection unit 20, and the content editing unit 21.

  The user preference information storage unit 15 functions as a user preference information storage unit that stores user preference information. The user preference information is preference information indicating a preference relating to a user's photograph. FIG. 4 is a diagram illustrating an example of user preference information. In the example shown in FIG. 4, the user preference information is preference information indicating a photographer preferred by the user among a plurality of photographers, and has “photographer” and “preference level”. “Photographer” is identification information for uniquely identifying a photographer. The “preference level” is assigned to each photographer and is a value indicating the degree to which the user likes the photographer (photographed by the photographer). It shows that a user likes the photographer, so that a photographer's preference degree is large. In this example, the photographer's preference of the user is in the order of “Photographer 1”, “Photographer 2”, and “Photographer 3”.

  The user preference information is input in advance to the content providing apparatus 10 by the user and stored in the user preference information storage unit 15. The user preference information stored in the user preference information storage unit 15 is referred to by the scene-specific user information extraction unit 17.

  Further, the content providing apparatus 10 may include a user preference information acquisition unit (not shown). The user preference information acquisition unit may display a plurality of photographers on the display (output device 107), and allow the user to directly input the points (numerical values) distributed to the favorite photographers. In this case, the user preference information acquisition unit may cause the user to input a score so that the total is 100 points. The user preference information acquisition unit may display a group of photos associated with each photographer on the display (output device 107), and allow the user to select a user's favorite photo. In this case, the user preference information acquisition unit may acquire user preference information by digitizing the number of photos selected for each photographer. For example, ten photos are selected, of which six photos associated with photographer 1 are selected, and three photos associated with photographer 2 are selected and associated with photographer 3. When one photograph is selected, the user preference information acquisition unit sets the preference level of the photographer 1 to 60, the preference level of the photographer 2 to 30, and the preference level of the photographer 3 to 10. . In addition, the user preference information acquisition unit may allow the user to select three photos from the displayed photo group and give priority to the selected photos. For example, the user preference information acquisition unit sets the preference degree of a photographer associated with the photograph with the highest priority to 60, and sets the preference degree of the photographer associated with the photograph with the second highest priority to 30. And the preference of the photographer associated with the photograph with the third highest priority is 10.

  The photographer information storage unit 16 functions as a photographer information storage unit that stores photographer information. The photographer information is characteristic information indicating a tendency of a shooting scene taken by the photographer for each of a plurality of photographers. FIG. 5 is a diagram illustrating an example of photographer information. In the example shown in FIG. 5, “shooting scene” is identification information for uniquely identifying a shooting scene. Examples of shooting scenes include landscapes, portraits, airplanes, underwater, celestial bodies, and macros. In the photographer information, 100 feature values are assigned to each photographer, and the feature values are distributed to the shooting scenes photographed by the photographer. The larger the feature value, the more the photographer frequently photographs the scene (that is, he is good at it). In this example, photographer 1 takes portrait photos most frequently and then takes landscape photos. In other words, it can be said that the photographer 1 is best at taking portrait photographs and then at landscape photography.

  The photographer information is set in advance. For example, the photographer information may be manually set based on the result of the investigation of the shooting scene that is good for each photographer. In addition, for each photographer, photographs published in photo collections and magazines are collected, and each photograph is classified into a photographing scene by manual or photographing scene analysis technology, so that the number of photographs per photographing scene can be reduced. can get. The photographer information may be manually set based on the number of photographs for each shooting scene. The photographer information stored in the photographer information storage unit 16 is referred to by the scene-specific user information extraction unit 17.

  The scene-specific user information extraction unit 17 functions as an extraction unit that extracts scene-specific user information based on the evaluation information acquired by the evaluation information acquisition unit 13. The user information for each scene is information regarding the user for each shooting scene. The scene-specific user information includes scene-specific evaluation values and scene-specific preference information. The evaluation value for each scene is an evaluation value for each shooting scene. The preference information for each scene is information indicating a photographer preferred by the user for each shooting scene among a plurality of photographers.

  The scene-specific user information extraction unit 17 extracts scene-specific evaluation values as scene-specific user information. The scene-specific user information extraction unit 17 calculates the scene-specific evaluation value by counting the evaluation values acquired by the evaluation information acquisition unit 13 for each shooting scene. Specifically, the scene-specific user information extraction unit 17 reads the scene-specific evaluation table stored in the scene-specific user information storage unit 18, and the shooting scene acquired by the evaluation information acquisition unit 13 in the scene-specific evaluation table. The evaluation value for each scene is calculated by adding the evaluation value acquired by the evaluation information acquisition unit 13 to the value corresponding to.

  FIG. 6 is a diagram illustrating an example of the scene-specific evaluation table. In the example shown in FIG. 6, “total score accumulation”, “Comp accumulation”, “Noise accumulation”, “Pint accumulation”, “Vivid accumulation”, “Cont accumulation”, and “F1.4 shooting” are taken for each shooting scene. The “number of times” and the like are stored. The “total score accumulation” value is an evaluation value for each scene obtained by classifying a plurality of target images for each shooting scene and accumulating the evaluation value of the “total score” of the target images of each shooting scene. The value of “Comp cumulative” is an evaluation value for each scene obtained by accumulating the evaluation value of “Comp” of the target image of each shooting scene. The value of “Noise accumulation” is an evaluation value for each scene obtained by accumulating the evaluation values of “Noise” of the target image of each shooting scene. The value of “Pint accumulation” is an evaluation value for each scene obtained by accumulating the evaluation value of “Pint” of the target image of each shooting scene. The value of “Vivid accumulation” is an evaluation value for each scene obtained by accumulating the evaluation value of “Vivid” of the target image of each shooting scene. The value of “Cont accumulation” is an evaluation value for each scene obtained by accumulating the evaluation values of “Cont” of the target image of each shooting scene. “F1.4 number of photographing” is an evaluation value for each scene indicating the number of target images having an F value of 1.4 among a plurality of target images.

  The scene-specific user information extraction unit 17, for example, “total score accumulation”, “Comp accumulation”, “Noise accumulation”, “Pint accumulation” corresponding to the “shooting scene” shown in FIG. , “Vivid Accumulation”, and “Cont Accumulation” values are evaluated in the evaluation items of “Comprehensive Score”, “Comp”, “Noise”, “Pint”, “Vivid”, and “Cont” shown in FIG. Add each value. When “F” shown in FIG. 3 is 1.4, the scene-specific user information extraction unit 17 performs “F1.4 shooting corresponding to“ shooting scene ”shown in FIG. Increase the number of times by one. The scene-specific user information extraction unit 17 stores the updated scene-specific evaluation table in the scene-specific user information storage unit 18.

  The scene-specific user information extraction unit 17 extracts scene-specific preference information as scene-specific user information. The scene-specific user information extraction unit 17 obtains scene-specific preference information based on the user preference information stored in the user preference information storage unit 15 and the photographer information stored in the photographer information storage unit 16. calculate. In the preference information by scene, the preference by scene is assigned to each photographer for each shooting scene. The scene-specific user information extraction unit 17 multiplies the preference level assigned to each photographer in the user preference information by the feature value of the photographed scene of the photographer in the photographer information, for example. Calculate the degree. The preference for each scene is a value indicating the degree to which the user likes the photographer (photographed by the photographer) in each shooting scene. The greater the photographer's preference for each scene, the more the user likes the photographer in the shooting scene. The scene-specific user information extraction unit 17 stores the scene-specific preference information in the scene-specific user information storage unit 18 in the form of a scene-specific preference photographer table.

  FIG. 7 is a diagram illustrating an example of a scene-specific preference photographer table. In the example shown in FIG. 7, for example, the user likes the photographer 1's photograph most about the landscape photograph, and then likes the photographer 3 photograph.

  The scene-specific user information storage unit 18 functions as a scene-specific user information storage unit that stores scene-specific user information. The scene-specific user information storage unit 18 stores, for example, scene-specific evaluation values and scene-specific preference information as scene-specific user information. That is, the scene-specific user information storage unit 18 stores a scene-specific evaluation table and a scene-specific preference photographer table. The scene-specific user information stored in the scene-specific user information storage unit 18 is referred to by the scene-specific user information extraction unit 17, the content selection unit 20, and the content editing unit 21.

  The content storage unit 19 functions as a content storage unit that stores a plurality of contents. As described above, the content stored in the content storage unit 19 is content related to shooting, and examples of content types include advice, articles, advertisements, and photos. More specifically, a preset document, link information of an external site, a group of photos, a photo taken in the past at the same location as the target image, an editing method such as image processing and correction, an edited photo, an image There are processing filters, advertisements for lenses compatible with the body of the camera used to capture the target image, information about the equipment group owned by the user, and the like. The content storage unit 19 manages a plurality of contents using a content table.

  FIG. 8 is a diagram illustrating an example of a content table stored in the content storage unit 19. In the example shown in FIG. 8, each content is managed by “condition”, “content ID”, “title”, “type”, and “content”. “Condition” is information indicating a condition for selecting content by the content selection unit 20. “Content ID” is identification information for uniquely identifying a content. “Title” is a character string indicating the title of the content. “Type” is information indicating the type of content. “Content” is information indicating the content. For example, the content with the content ID “1” has a title “Let's take a picture by the three-division method”, and the content type is “advice”. This content is selected when the shooting scene of the target image is “landscape” and the total of Comp accumulation is less than 2000.

  The content selection unit 20 functions as a selection unit that selects content from a plurality of contents stored in the content storage unit 19 based on the scene-specific user information extracted by the scene-specific user information extraction unit 17. The content selection unit 20 satisfies the conditions shown in the content table based on the evaluation information stored in the evaluation information storage unit 14 and the scene-specific user information stored in the scene-specific user information storage unit 18. Select content. For example, in the evaluation information shown in FIG. 3, “shooting scene” is “portrait”, and in the preference information by scene shown in FIG. 7, the total degree of preference by scene of photographer 1 is 6000. Since the evaluation value by scene of the total score accumulation of the portrait shown in FIG. 6 is 9000, the content with the content ID “8” is selected. The content selection unit 20 outputs the selected content to the content editing unit 21.

  When the number of contents that match the conditions shown in the content table is 2 or more, the content selection unit 20 assigns a priority to each of the selected plurality of contents. The content selection unit 20 determines the priority order of the content based on, for example, the popularity order of the content for the entire user. For example, the content browsing history of each user is stored in a server device (not shown) and aggregated to calculate the popularity order of the content for the entire user. The popularity order may be set so as to indicate that the more the number of browsing times, the higher the popularity, that is, the higher the popularity order. For example, the content selection unit 20 increases the priority of the content as the popularity of the content increases.

  The content editing unit 21 functions as an editing unit that edits the content selected by the content selection unit 20 based on the scene-specific user information. For example, if the type of content selected by the content selection unit 20 is advice, the content editing unit 21 is for “{photographer} who likes the photograph of {photographer} {photographing scene} photographing {user's photographing technology}” Is added to the content selected by the content selection unit 20. In addition, evaluation information and scene-specific user information are reflected in the portion {}. The content editing unit 21 adds a character string indicating the shooting scene to {shooting scene} based on the shooting scene information acquired from the evaluation information stored in the evaluation information storage unit 14. The content stored in the content selection unit 20 may include a template in which evaluation information and scene-specific user information are reflected.

  Based on the scene-specific preference information stored in the scene-specific user information storage unit 18, the content editing unit 21 has the highest scene-specific preference level for the shooting scene indicated by the shooting scene information acquired from the evaluation information. Extract photographers. The content editing unit 21 adds a character string indicating the extracted photographer to {photographer}. The content editing unit 21 reads out the scene-specific evaluation value of the total score accumulated in the scene-specific user information storage unit 18 for the shooting scene indicated by the shooting scene information acquired from the evaluation information, and the shooting technique of the user Determine. For example, the content editing unit 21 determines whether the level is an elementary level, an intermediate level, or an advanced level based on a preset threshold value. The content editing unit 21 adds the determined shooting technique to {user shooting technique}. The content editing unit 21 outputs the edited content to the output unit 22.

  The output unit 22 functions as an output unit that outputs the content edited by the content editing unit 21. The output unit 22 is realized by the output device 107. When the content providing device 10 is a device having a finder such as a digital camera, the output unit 22 may be realized by a display device such as a liquid crystal display provided inside the finder. Specifically, the output unit 22 generates a composite image based on the content edited by the content editing unit 21 and the target image acquired by the image acquisition unit 11, and displays the composite image as an output image.

  The output unit 22 displays the target image acquired by the image acquisition unit 11 as an output image when the evaluation mode is not ON in the content providing apparatus 10. The evaluation mode is a mode in which the processes of the evaluation information acquisition unit 13, the scene-specific user information extraction unit 17, the content selection unit 20, and the content editing unit 21 are executed to output a composite image. The output unit 22 may display the output image using, for example, photo management software and a web service. When the content providing apparatus 10 does not have a display function such as a display, the output unit 22 outputs an output image to, for example, another apparatus (for example, a terminal having the above-described display). For example, when the content providing apparatus 10 transmits an output image to another apparatus via a communication network, a part (communication module 104 or the like) that performs output image transmission processing functions as the output unit 22.

  9 to 13 are diagrams illustrating examples of composite images output by the content providing apparatus. As shown in FIG. 9A, the output unit 22 generates the composite image G by reducing the target image Po and arranging the content C in a different area from the reduced target image Po. The image G may be displayed. As shown in FIG. 9B, when the content is composition advice, the composition image G is generated by superimposing the composition pattern and advice on the target image, and the composition image G is displayed. May be. As illustrated in FIG. 10A, the output unit 22 may generate the composite image G by superimposing the content display icon V on the target image Po and display the composite image G. In this case, in response to the user clicking on the icon V, the output unit 22 may display the content C as shown in FIG.

  When a plurality of contents are selected by the content selection unit 20, the output unit 22 may display a combination of the plurality of contents C1 and C2, as shown in FIG. Also, as shown in FIGS. 12A to 12C, the output unit 22 provides one content C1, one content C2, and one content C3 based on the priority order of the plurality of contents C1, C2, and C3. You may display in order.

  As shown in FIG. 13A, the output unit 22 may display the content C at the end of shooting. For example, the output unit 22 determines that the photographing has ended when the evaluation mode is turned off. Further, when the content providing apparatus 10 acquires a target image from an external camera, the output unit 22 may determine that the shooting has ended by detecting that the connection with the external camera has been disconnected. Further, as illustrated in FIG. 13B, the output unit 22 may display a content C when viewing the target image Po by setting the photographed photograph as the target image Po. That is, the output unit 22 may generate the composite image G by reducing the target image Po and arranging the content C in a different area from the reduced target image Po, and display the composite image G.

  The user preference information updating unit 23 functions as an updating unit that updates the scene-specific preference information. The user preference information update unit 23 updates the preference information for each scene stored in the user information storage unit for each scene 18 by updating the user preference information stored in the user preference information storage unit 15, for example. For example, when the content output by the output unit 22 is content related to one of a plurality of photographers, the user preference information update unit 23 detects that the content has been browsed by the user Then, in the user preference information, the degree of preference for the photographer related to the content is increased. As illustrated in FIG. 14, when the content of the photographer 1 is browsed, the user preference information update unit 23 increases the preference level of the photographer 1 by one in the user update information, for example. Thereby, in the process of the next target image, the scene-specific user information extraction unit 17 calculates the scene-specific preference information using the updated user preference information, so that the scene-specific preference information can be updated.

  For example, the content display icon (see FIG. 10A, FIG. 13A, and FIG. 13B) is pressed by the input device 106 to detect that the content has been browsed. It is done depending on whether or not. When the content includes link information to an external site, detection that the content has been browsed may be performed based on whether or not the external site has been accessed.

  Next, a series of processes of the content providing method in the content providing apparatus 10 will be described with reference to FIG. FIG. 15 is a flowchart showing a series of processes of the content providing method. Here, a case where the user takes a picture using the camera function (camera application and camera module 108) of the content providing apparatus 10 (a smartphone with a camera function as an example) will be described as an example. The series of processes shown in FIG. 15 is started when the user activates the camera application, for example.

  First, the image acquisition unit 11 acquires a target image (step S01). Specifically, after the user activates the camera application of the content providing apparatus 10, an image in the direction in which the lens is directed is acquired as the target image. The acquired image information of the target image is temporarily stored in the image information storage unit 12.

  Subsequently, it is determined whether or not the evaluation mode is turned on in the content providing apparatus 10 (step S02). When it is determined that the evaluation mode is ON (step S02: YES), processing related to content provision (step S03 to step S07) is executed.

  Hereinafter, a process when it is determined that the evaluation mode is ON (step S02: YES) will be described. First, the evaluation information acquisition unit 13 acquires evaluation information regarding a plurality of evaluation items including a photographic scene with respect to the target image acquired by the image acquisition unit 11 (step S03). Then, the evaluation information acquisition unit 13 outputs the evaluation information of the target image to the evaluation information storage unit 14 and stores it.

  Subsequently, the scene-specific user information extraction unit 17 extracts scene-specific user information based on the evaluation information acquired by the evaluation information acquisition unit 13 (step S04). The scene-specific user information includes scene-specific evaluation values and scene-specific preference information. Specifically, the scene-specific user information extraction unit 17 reads the scene-specific evaluation table stored in the scene-specific user information storage unit 18, and the shooting scene acquired by the evaluation information acquisition unit 13 in the scene-specific evaluation table. The evaluation value for each scene is calculated by adding the evaluation value acquired by the evaluation information acquisition unit 13 to the value corresponding to. Then, the scene-specific user information extraction unit 17 stores the updated scene-specific evaluation table in the scene-specific user information storage unit 18.

  The scene-specific user information extraction unit 17 also selects the scene-specific preference based on the user preference information stored in the user preference information storage unit 15 and the photographer information stored in the photographer information storage unit 16. Calculate information. For example, the scene-specific user information extraction unit 17 multiplies the preference level assigned to each photographer in the user preference information by the feature value of the photographed scene of the photographer in the photographer information, thereby obtaining the scene-specific preference. Calculate the degree. The scene-specific user information extraction unit 17 stores the scene-specific preference information in the scene-specific user information storage unit 18 in the form of a scene-specific preference photographer table.

  Subsequently, the content selection unit 20 selects content from the plurality of contents stored in the content storage unit 19 based on the scene-specific user information extracted by the scene-specific user information extraction unit 17 (step S05). Specifically, the content selection unit 20 is based on the evaluation information stored in the evaluation information storage unit 14 and the user information by scene stored in the user information storage unit 18 by scene. Select content that meets the conditions. Then, the content selection unit 20 outputs the selected content to the content editing unit 21.

  Subsequently, the content editing unit 21 edits the content selected by the content selection unit 20 based on the scene-specific user information (step S06). Then, the content editing unit 21 outputs the edited content to the output unit 22.

  Subsequently, the output unit 22 outputs the content edited by the content editing unit 21 (step S07). Specifically, the output unit 22 generates a composite image based on the content edited by the content editing unit 21 and the target image acquired by the image acquisition unit 11, and outputs the composite image as an output image. In the present embodiment, the output unit 22 displays an output image.

  On the other hand, when it is determined in step S02 that the evaluation mode is not turned on (step S2: NO), the output unit 22 outputs the target image acquired in step S01 as an output image (step S08). In the present embodiment, the output unit 22 displays an output image.

  Thereafter, when the output image output in step S07 or step S08 is confirmed by the user (photographer) and a predetermined determination operation is performed, the content providing apparatus 10 captures and records the target image (step S09).

  Subsequently, in the content providing apparatus 10, it is determined whether or not the end of the shooting process has been received from the user (step S10). Specifically, it is determined whether an end operation of the camera application has been accepted. If it is determined that the end of the shooting process has not been received (step S10: NO), the processes of step S1 to step S10 are repeatedly executed, and the process of the second and subsequent target images is executed. On the other hand, if it is determined in step S10 that the end of the photographing process has been received (step S10: YES), the operation of the content providing apparatus 10 (here, the photographing process by the camera application as an example) is terminated. In this way, a series of processing of the content providing method ends.

  The series of processes may be repeatedly executed periodically or at a timing when the direction in which the lens is directed changes. As a result, a composite image including content is presented to the user while being updated almost in real time for the image that can be captured at the current time. In this case, the user can confirm the composite image, for example, and adjust the composition or the like according to the advice.

  Next, a content providing program P for causing a computer to function as the content providing apparatus 10 will be described with reference to FIG.

  The content providing program P includes a main module P10, an image acquisition module P11, an evaluation information acquisition module P13, a scene-specific user information extraction module P17, a content selection module P20, a content editing module P21, an output module P22, and a user preference information update module P23. Is provided. The main module P10 is a part that comprehensively controls processing related to content provision. The functions realized by executing the image acquisition module P11, the evaluation information acquisition module P13, the scene-specific user information extraction module P17, the content selection module P20, the content editing module P21, the output module P22, and the user preference information update module P23. The functions of the image acquisition unit 11, the evaluation information acquisition unit 13, the scene-specific user information extraction unit 17, the content selection unit 20, the content editing unit 21, the output unit 22, and the user preference information update unit 23 in the above embodiment, respectively. It is.

  The content providing program P may be provided in a state of being fixedly recorded on a tangible recording medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), and a semiconductor memory. . Alternatively, the content providing program P may be provided via a communication network as a data signal superimposed on a carrier wave.

  In the content providing apparatus 10 and the content providing program P described above, evaluation information regarding a plurality of evaluation items including a photographic scene is acquired for the acquired target image, and user information for each scene is extracted based on the evaluation information. The Then, based on the user information for each scene, the content is selected from a plurality of contents related to shooting and output. As a result, the content is selected in consideration of information related to the user according to the shooting scene, so that it is possible to provide content suitable for the user for each shooting scene.

  Further, the scene-specific user information extraction unit 17 calculates the scene-specific evaluation value by counting the evaluation values acquired by the evaluation information acquisition unit 13 for each shooting scene, and uses the scene-specific evaluation value as the scene-specific user information. Extract. This scene-specific evaluation value can be regarded as a value reflecting the user's shooting technique for each shooting scene. For this reason, the content is selected in consideration of the user's shooting technique for each shooting scene, and therefore it is possible to provide content according to the user's shooting technique for each shooting scene.

  The scene-specific user information extraction unit 17 extracts scene-specific preference information as scene-specific user information. This scene-specific preference information represents the user's preference for each shooting scene. For this reason, since the user's preference for each shooting scene is taken into consideration, the content is selected according to the user's preference for each shooting scene.

  The scene-specific user information extraction unit 17 also includes photographer information indicating a tendency of a shooting scene taken by the photographer for each of a plurality of photographers, and a user preference indicating a photographer preferred by the user among the plurality of photographers. Based on the information, the preference information for each scene is calculated. Therefore, it is possible to obtain scene-specific preference information without selecting a photographer preferred by the user for each shooting scene.

  Moreover, the user preference information update part 23 updates the preference information classified by scene. For example, the user preference information update unit 23 can reflect the change in the preference of the user by updating the preference information for each scene according to the content browsed by the user. For this reason, it becomes possible to change the selected content according to a change in the user's preference.

  Further, the content editing unit 21 edits the content selected by the content selection unit 20 based on the scene-specific user information. For this reason, for example, the content can be edited so as to attract the user's interest by reflecting the information about the user for each shooting scene in the content. Thereby, a user's understanding degree with respect to the provided content can be raised, and a user's browsing rate with respect to the provided content can be improved.

(Second Embodiment)
A content providing apparatus according to the second embodiment will be described. FIG. 17 is a block diagram illustrating a functional configuration of the content providing apparatus according to the second embodiment. As illustrated in FIG. 17, the content providing apparatus 10A according to the second embodiment includes the server apparatus 2A and the terminal apparatus 3A as compared to the content providing apparatus 10 according to the first embodiment. The main difference. The server device 2A is, for example, a server that distributes content to the terminal device 3A. The terminal device 3A is a device that is carried and used by a user. The terminal device 3A is a terminal device including a digital camera, a mobile phone, a smartphone, a tablet terminal, and a PC, for example. The terminal device 3A acquires content from the server device 2A and displays the acquired content. The server device 2A and the terminal device 3A are connected to be communicable with each other via a network such as a mobile communication network. A plurality of terminal devices 3A may be communicably connected to the server device 2A.

  The terminal device 3A includes an image acquisition unit 11, an image information storage unit 12, an evaluation information acquisition unit 13, an evaluation information storage unit 14, a user preference information storage unit 15, a photographer information storage unit 16, A user information extraction unit 17, a scene-specific user information storage unit 18, an output unit 22, a user preference information update unit 23, and a communication control unit 31 are provided. The communication control unit 31 controls transmission / reception of data to / from the server device 2A. The server device 2 </ b> A includes a content storage unit 19, a content selection unit 20, a content editing unit 21, and a communication control unit 24. The communication control unit 24 controls transmission / reception of data to / from the terminal device 3A.

  Evaluation information stored in the evaluation information storage unit 14 and scene-specific user information stored in the scene-specific user information storage unit 18 are transmitted to the content selection unit 20 and the content editing unit via the communication control unit 31 and the communication control unit 24. Is transmitted to the unit 21. Further, the content edited by the content editing unit 21 is transmitted to the output unit 22 via the communication control unit 24 and the communication control unit 31. The communication control unit 31 transmits evaluation information and scene-specific user information to the server device 2A together with a terminal ID for uniquely identifying the terminal device 3A. Based on the terminal ID transmitted together with the evaluation information and the user information for each scene, the communication control unit 24 transmits the content to the terminal device 3A that has transmitted the evaluation information and the user information for each scene.

  The content providing apparatus 10A according to the second embodiment described above also provides the same effects as those of the content providing apparatus 10 according to the first embodiment described above.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment. For example, the image acquisition unit 11 may acquire an image on the Internet as a target image. Moreover, the image acquisition part 11 may acquire the image which a user shows interest as a target image in SNS (Social Networking Service). For example, the image acquisition unit 11 acquires, as a target image, an image with a “Like” flag by the user in Facebook, Instagram, or the like. The image acquisition unit 11 acquires the image with the flag from, for example, a public account and an open SNS that can be browsed by the user.

  Further, in the content providing apparatuses 10 and 10A, it may be determined that the shooting technique of a user who simply has a large number of shootings is advanced. On the other hand, the scene-specific user information extraction unit 17 may calculate a scene-specific evaluation value for a predetermined number of photographs (for example, 5000) taken most recently since the processing of the target image. The scene-by-scene evaluation value may be calculated for photos taken from a predetermined period (for example, half a year) before the processing of the image to the processing of the target image. By doing in this way, it becomes possible to improve the determination precision of a user's imaging technique.

  Further, the content storage unit 19 may store a content group associated with the captured target image and a content group associated with the target image being captured. In this case, the content selection unit 20 may select content from the content group to be selected depending on whether the target image is a captured image or an image being captured.

  Further, the content storage unit 19 may store content to be selected for each user. The content storage unit 19 may store content selected by the user. Further, the content stored in the content storage unit 19 may be updated according to the usage tendency of the content. This usage tendency is determined based on browsing information indicating that the user has browsed. The browsing information includes, for example, the number of times the user has browsed the content, the number of times the content has been evaluated, the number of times that shooting has been performed according to the content, and information indicating that the shooting technique has been improved according to the content.

  The content selection unit 20 may select content from a plurality of contents stored in the content storage unit 19 by collaborative filtering. In addition, the content selection unit 20 may select content from a plurality of contents stored in the content storage unit 19 based on a regression equation or a discriminant. The regression equation is calculated by, for example, multiple regression analysis. The discriminant is calculated by, for example, logistic regression and a support vector machine. In this case, the content selection unit 20 may determine the priority order of the content based on the fitness score for the user.

  For example, it is assumed that two contents (content ID = 101, 102) are selected by the content selection unit 20. The content with the content ID 101 has a regression coefficient of +40 when the F value is 1.4 and +30 when the shooting scene is a portrait, and the content with the content ID 102 has an F value of 1. It is assumed that it has a regression coefficient of +40 in the case of 4 and −10 in the case where the shooting scene is a portrait. At this time, when the F value of the target image is 1.4 and the shooting scene is a portrait, the fitness score of the content with the content ID 101 is 70, and the fitness score of the content with the content ID 102 is 30. For this reason, the content selection unit 20 assigns a higher priority to the content with the content ID 101 than the content with the content ID 102.

  The content selection unit 20 may assign a high priority to content popular in SNS.

  In addition, the content editing unit 21 is, for example, “Thanks for taking the {shooting scene} photo of {time}. Taking advantage of this {composition}, {shooting scene} the skill of the photo is {user's shooting technique} In addition, the template text such as “The photographer} has introduced the {shooting scene} photography technique using a fisheye lens to you, who is aiming for {user's shooting technique + 1}." It may be added. When the shooting time is included as the evaluation information, the content editing unit 21 can acquire, for example, the time when a series of shooting was performed from the evaluation information. The content editing unit 21 adds a character string corresponding to the acquired time to {time}. For example, when the shooting time of the first image is 23:00 and the shooting time of the last image is 5 o'clock in a series of shootings, the content editing unit 21 reads “Long time from midnight to early morning”. Add the string “time”. The content editing unit 21 adds a character string indicating a level higher than the current user's imaging technique to {user's imaging technique + 1}. If the evaluation information includes “Comp (j)” instead of “Comp” and the evaluation value of Comp (j) is higher than the evaluation value of the other evaluation items in a series of shooting, the content is edited. The unit 21 adds a character string indicating the composition pattern j to {composition}. In this case, since the text corresponding to the user's shooting history, preference, shooting technique, and the like is added to the content, the possibility that the user views the content output by the output unit 22 can be increased.

  The output unit 22 may output the content selected by the content selection unit 20 without editing the content by the content editing unit 21.

  DESCRIPTION OF SYMBOLS 10,10A ... Content provision apparatus, 11 ... Image acquisition part (image acquisition means), 13 ... Evaluation information acquisition part (evaluation information acquisition means), 17 ... Scene-specific user information extraction part (extraction means), 19 ... Content storage part (Content storage means), 20 ... content selection section (selection means), 21 ... content editing section (editing means), 22 ... output section (output means), 23 ... user preference information update section (update means), P ... content Offer program.

Claims (7)

Image acquisition means for acquiring a target image that is an image to be processed;
Evaluation information acquisition means for acquiring evaluation information regarding a plurality of evaluation items including a shooting scene for the target image acquired by the image acquisition means;
Based on the evaluation information acquired by the evaluation information acquisition means, extraction means for extracting user information by scene, which is information related to the user for each shooting scene,
Content storage means for storing a plurality of contents related to shooting;
Selection means for selecting content from the plurality of contents stored in the content storage means based on the scene-specific user information extracted by the extraction means;
Output means for outputting the content selected by the selection means;
A content providing apparatus comprising: The evaluation information includes an evaluation value calculated based on a predetermined evaluation criterion,
The extraction means calculates the evaluation value for each scene, which is the evaluation value for each shooting scene, by summing up the evaluation values acquired by the evaluation information acquisition means for each shooting scene. The content providing apparatus according to claim 1, wherein a value is extracted as the user information for each scene.   The content provision according to claim 1, wherein the extraction unit extracts, as the user information by scene, scene-specific preference information indicating a photographer preferred by the user for each shooting scene among a plurality of photographers. apparatus.   The extraction means includes, for each of the plurality of photographers, feature information indicating a tendency of the shooting scene taken by the photographer, and preference information indicating a photographer preferred by the user among the plurality of photographers. The content providing apparatus according to claim 3, wherein the scene preference information is calculated based on the scene information.   The content providing apparatus according to claim 3, further comprising updating means for updating the scene-specific preference information. An editing unit that edits the content selected by the selection unit based on the scene-specific user information,
The content providing apparatus according to claim 1, wherein the output unit outputs the content edited by the editing unit. Image acquisition means for acquiring a target image that is an image to be processed;
Evaluation information acquisition means for acquiring evaluation information regarding a plurality of evaluation items including a shooting scene for the target image acquired by the image acquisition means;
Based on the evaluation information acquired by the evaluation information acquisition means, extraction means for extracting user information by scene, which is information related to the user for each shooting scene,
Selection means for selecting content from a plurality of contents related to shooting based on the user information by scene extracted by the extraction means;
Output means for outputting the content selected by the selection means;
Content providing program that allows computers to function.

Images