JP2013183259A - Image reproduction device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To run background music linked with a picture being reproduced in a slide show as against a conventional slide show in which background music not linked with a picture being reproduced, that is selected from predetermined background music, is run.SOLUTION: An image reproduction apparatus comprises: a display unit which displays an image; an analysis unit which analyzes a color tone and facial expression in the image and sorts them into predetermined types; and a control unit which holds plural pieces of music data and reproduces a predetermined piece of the music data corresponding to the types of the color tone and the expression in the image when displaying the image on the display unit.

Description

  The present invention relates to an image reproduction device.

  2. Description of the Related Art Conventionally, a slide show reproduction system that switches photos and display effects for slide show display based on emotions selected by a user is known (see, for example, Patent Document 1). On the other hand, a study of associating a color tone with an emotion has been made (for example, see Non-Patent Document 1). In addition, a slide show reproduction system that produces photos and effects that are displayed as a slide show based on the atmosphere of BGM sound is also considered.

JP2011-160032A

URL: http: //www.sipec-square.net/~mt-home/students/miyazono/project/kanjyo/page06.html

  However, since the facial expressions of the photographed faces are generally smiles, it is difficult to extract slides and display facial expressions that match emotions such as emotions corresponding to background music (BGM). There may be no photo of facial expressions corresponding to emotions. In addition, when a slide show is played, if the photos to be played are determined and you want to play a BGM that matches the emotions of those photos, the conventional slide show is selected from the predetermined BGMs. There is a problem that unrelated BGM is flown.

  In view of the above problems, an object of the present invention is to provide an image reproducing apparatus that can analyze the facial expression and color tone included in photos to be reproduced in a slide show and play the optimum BGM for the atmosphere of the photos to be reproduced. That is.

  An image reproduction apparatus according to the present invention holds a display unit that displays an image, an analysis unit that analyzes the color tone and facial expression of the image and classifies the image into a plurality of predetermined types, and a plurality of music data And a control unit that reproduces the predetermined music data corresponding to the tone of the image and the classification of the facial expression when the image is displayed on the display unit.

  In particular, when there are a plurality of images to be displayed on the display unit, the analysis unit statistically analyzes a color tone classification result of each of the plurality of images and a facial expression classification result of an image including a face among the plurality of images. Analysis to obtain a maximum frequency tone classification and a maximum frequency facial expression classification, and the control unit determines in advance corresponding to the maximum frequency color tone classification and the maximum frequency facial expression classification. The music data is reproduced.

  In addition, when there are a plurality of images to be displayed on the display unit, the analysis unit analyzes the color tone of the representative image set in advance and the facial expression of the plurality of images into a plurality of predetermined types. The control unit reproduces the predetermined music data corresponding to the color tone and the facial expression classification of the representative image when the plurality of images are displayed on the display unit.

  Alternatively, an additional information acquisition unit that acquires at least one additional information of a shooting date and time, a shooting location, and a shooting mode of the image displayed on the display unit is further provided, and the control unit includes the color classification and the facial expression classification. The predetermined music data corresponding to the additional information is reproduced.

  Alternatively, the display unit further includes an additional information acquisition unit that acquires at least one additional information of a reproduction date and time and a reproduction place for displaying an image, and the control unit includes the color classification, the facial expression classification, and the additional information. The predetermined music data corresponding to the above is reproduced.

  Furthermore, the analysis unit analyzes a color tone of a predetermined main subject or a specific area in the image.

  In particular, the main subject or the specific region is a subject or region whose focus shift is equal to or less than a preset threshold value.

  Furthermore, it is characterized by having a table indicating the correspondence between the color and facial expression classification analyzed by the analysis unit and the plurality of music data.

  Further, the color tone and facial expression classification corresponding to the music are added in advance as header information of the music data, and the control unit converts the music data of the header information corresponding to the analysis result of the analysis unit. If there are a plurality of search results, the music data to be played is determined according to preset conditions.

  In particular, when there are a plurality of search results, the control unit determines the music data to be played according to at least one of the shooting date / time, shooting location, playback date / time, and playback location of the image to be displayed. .

  The image reproducing apparatus according to the present invention can play BGM that is optimal for the atmosphere of photos to be reproduced in a slide show.

1 is a block diagram of an image playback device 101 according to the present embodiment. It is a figure which shows an example of the facial expression analysis. It is a figure which shows an example of the emotional atmosphere of a color tone. It is a figure which shows an example of the music classification table 162. FIG. It is a flowchart which shows the process example at the time of slide show execution. 10 is a block diagram of an electronic camera 101a according to application example 1. FIG. It is a block diagram of the image reproduction apparatus 101b (electronic camera 101b) which concerns on the application example 2. FIG. It is a flowchart which shows the process example at the time of slide show execution.

Hereinafter, an image reproducing apparatus according to the present invention will be described with reference to the drawings.
(First embodiment)
FIG. 1 shows a block diagram of an image reproduction apparatus 101 according to the first embodiment. The image reproduction device 101 basically includes a display unit 102, an audio output unit 103, an operation unit 104, a control unit 105, an image analysis unit 106, and a storage unit 107. The blocks are connected to each other via a common bus 108, and input / output of image data, audio data, control commands and parameters necessary for operation, and the like. Further, the image reproduction device 101 may be provided with an image input unit 109 for inputting image data stored in an external storage medium such as a memory card 109a.

  The image reproduction apparatus 101 according to the present embodiment is an apparatus that performs a slide show in which image data stored in the storage unit 107 or the memory card 109a is read and displayed on the screen of the display unit 102. In particular, the image playback apparatus 101 according to the present embodiment automatically selects BGM (background music) that matches the emotional atmosphere of the image displayed on the display unit 102 from the music data stored in the storage unit 107. And a function of reproducing from the speaker 103a of the audio output unit 103. Hereinafter, each block of FIG. 1 will be described.

  The display unit 102 includes a liquid crystal monitor and a display circuit, and converts image data input via the common bus 108 into an image signal by the display circuit and displays the image signal on the liquid crystal monitor. Note that an image signal output terminal may be provided in the display unit 102 without displaying a liquid crystal monitor in the image reproducing apparatus 101 so as to display on an external television or monitor.

  The audio output unit 103 is configured by a D / A conversion circuit, an amplifier, and the like, converts audio data input via the common bus 108 into an audio signal by the D / A conversion circuit, and outputs the audio signal to the speaker 103a. Note that the audio output unit 103 may be provided with an audio signal output terminal without providing the speaker 103a in the image reproduction apparatus 101 and output to an external television or audio device.

  The operation unit 104 includes a power button, a menu button, a cursor key, a determination button, and the like. The user operates the image display apparatus 101 by selecting an operation menu displayed on the screen of the display unit 102 using a cursor key or a determination button. Note that the operation unit 104 may be configured by a touch panel arranged on the screen of the display unit 102, and an operation button displayed graphically on the screen may be operated.

  The control unit 105 is configured by a CPU or the like, and operates according to a program stored in advance therein, and controls the operation of the entire image reproduction apparatus 101. For example, when the power button of the operation unit 104 is pressed, the image playback apparatus 101 is activated, and when the menu button is pressed, an operation menu is displayed on the screen of the display unit 102. The operation menu includes, for example, an image selection button for displaying in a slide show, a start button for starting a slide show with selected images, and the like. For example, when the image selection button is selected with the cursor key and the determination button is pressed, the thumbnail image and the file name of the image data 163 stored in the storage unit 107 are displayed on the display unit 102. Then, use the cursor key to select an image to be displayed in the slide show and press the enter button. Although details of the operation method are well-known techniques, a detailed description thereof is omitted, but an arbitrary plurality of images may be selected, or all image data in a folder may be selected. For example, when a slide show start button is selected with the cursor key and the enter button is pressed, a slide show of the selected image is started.

  The image analysis unit 106 analyzes images displayed in the slide show. In particular, the image reproduction apparatus 101 according to the present embodiment includes a facial expression analysis unit 151 and a color analysis unit 152. When there is a face in the image, the facial expression analysis unit 151 performs facial expression analysis and classifies it into a preset type. The color analysis unit 152 analyzes the color tone of the image and classifies it into a preset type. The analysis process will be described in detail later.

  The storage unit 107 is configured by a nonvolatile memory, a hard disk, or the like. The storage unit 107 basically stores music data 161 and a music classification table 162. Further, the image data 163 to be displayed in the slide show may be stored in the storage unit 107, or the image data stored in the memory card 109a attached to the image input unit 109 may be used. Similarly, the music data 161 may be stored in the memory card 109a. In this case, the image input unit 109 operates as a general memory card interface.

As described above, the image reproducing apparatus 101 according to the present embodiment is configured, and can analyze the image displayed on the display unit 102 and reproduce BGM that matches the emotional atmosphere of the image from the speaker 103a.
[Analysis of emotional atmosphere of images]
Next, analysis of the emotional atmosphere of the image will be described. FIG. 2 is a diagram illustrating an example of facial expression analysis performed by the facial expression analysis unit 151. In the example of FIG. 2, the facial expression is changed from the shape of the mouth, eyes, and eyebrows to “joy (F1)”, “anger (F2)”, “sadness (F3)”, “easy (F4) using a method such as principal component clustering. ) ”. For example, “joy” represents an expression of joy, for example, both ends of the mouth are characterized by a raised shape. “Anger” represents an angry expression, for example, characterized by a shape in which both ends of the mouth are lowered and eyes and eyebrows are lifted. “Sorrow” represents an expression of sadness. For example, the corners of the eyes and eyebrows are characterized by a lowered shape. “Raku” expresses a fun expression, and is characterized by, for example, a shape with a wide mouth and eyes. As described above, by detecting the face in the image and analyzing the characteristics of the mouth, eyes, and eyebrows, it is possible to estimate the emotion of the person. Note that the above feature analysis is an example, and other methods and other features may be discriminated to analyze facial expressions.

  Next, FIG. 3 is a diagram illustrating an example of image color analysis performed by the color analysis unit 152. In the example of FIG. 3, the color analysis unit 152 analyzes the color tone of the entire image, determines the most contained color in the image, and classifies it into nine types of colors. The nine colors are, for example, “red (C1)”, “green (C2)”, “blue (C3)”, “cyan (C4)”, “yellow (C5)”, “magenta” (C6), “white (C7)”, “ash (C8)”, and “black (C9)”. Each color has a range of a certain color tone. For example, in a red system, not only red but also orange and red are included.

  Examples of “red” images include the sun and flames, and the emotional atmosphere is, for example, active, passion, or excitement. Examples of “green” images include forests and lawns, and the emotional atmosphere is, for example, peace and peace. Examples of “blue” images include a deep sky and the sea, and the emotional atmosphere is, for example, sincerity and cleanliness. Examples of “cyan” images include bright sky, and the emotional atmosphere is, for example, open or refreshing. Examples of “yellow” images include lemons and sunflowers, and the emotional atmosphere is, for example, cheerful or fine. Examples of “magenta” images include Fuji flowers and violets, and the emotional atmosphere is, for example, noble or mysterious. Examples of “white” images include snow and clouds, and the emotional atmosphere is, for example, cleanliness or innocence. Examples of “ash-based” images include smoke and rain clouds, and the emotional atmosphere is, for example, depression or anxiety. Examples of “black” images include darkness and mourning, and the emotional atmosphere is, for example, fear or sadness. Thus, by analyzing the color tone in the image, it is possible to estimate the emotional atmosphere that the image gives to the viewer. Note that the emotional atmosphere of each color is an example, and other emotional atmospheres may be set for each color.

In this way, the image reproduction device 101 according to the present embodiment can analyze the emotional atmosphere of the image displayed on the display unit 102. Then, music that matches the emotional atmosphere analyzed in the images displayed in the slide show can be automatically selected from the music data stored in the storage unit 107 and reproduced from the speaker 103a.
[Example of music classification table 162]
Next, an example of the music classification table 162 is shown in FIG. The music classification table 162 is a table in which a matrix is created by the classification of the analysis results of the expression analysis unit 151 and the color analysis unit 152 described above, and the file name of music data that matches the emotional atmosphere of each element of the matrix is described. It is. For example, when the analysis result of the color tone of the image is “red (C1)” and the analysis result of the facial expression is “joy (F1)”, it corresponds to the elements C1 and F1 of the matrix of FIG. The music data of BGM1 is selected. Similarly, when the analysis result of the color tone of the image is “white (C7)” and the analysis result of the facial expression is “Easy (F4)”, it corresponds to the elements C7 and F4 of the matrix of FIG. BGM 34 music data is selected.

In this way, the image playback apparatus 101 according to the present embodiment can select and play music that matches the emotional atmosphere of the images displayed in the slide show from the music data stored in the storage unit 107. it can.
[Process during slide show execution]
Next, the processing at the time of executing the slide show will be described with reference to the flowchart of FIG. 5 is a process executed by the control unit 105 and the image analysis unit 106.
(Step S101) The user operates a menu button, a cursor key, an enter button, etc. of the operation unit 104 to select a plurality of images from the image data 163 stored in the storage unit 107 as described above. Select the slide show start button on the screen with the cursor keys and press the enter button. In response to this, the control unit 105 starts a slide show of the selected images. Here, a user's favorite representative image may be selected from among a plurality of images. The representative image may be one or a plurality of images.
(Step S <b> 102) The control unit 105 reads the image data of the selected image from the storage unit 105 and outputs it to the image analysis unit 106.
(Step S103) The image analysis unit 106 performs face detection for each image. The face detection method is a well-known technique and will not be described in detail. However, a method such as pattern matching that extracts features such as the contour of the face and the arrangement of eyes, nose, mouth and the like is used.
(Step S104) The control unit 105 determines whether or not a face is detected in the image. If a face is detected in the image, the process proceeds to step S105, and if no face is detected, the process proceeds to step S106.
(Step S105) The facial expression analysis unit 151 of the image analysis unit 106 performs facial expression analysis of the image from which the face is detected. In the image reproducing apparatus 101 according to the present embodiment, as described with reference to FIG. 2, the facial expression is expressed by four expressions of “joy”, “anger”, “sorrow”, and “easy” based on the shape of the mouth, eyes, and eyebrows. Classify into: Here, when there are a plurality of images in which a face is detected, for example, the classification of the analysis result is statistically processed, and the classification of the most facial expressions is set as the representative expression. For example, if a face is included in five images, “joy” is four and “anger” is one, the representative expression is “joy”. Alternatively, the representative image may be selected in step S101, and only the result of analyzing the facial expression included in the representative image may be used. When there are a plurality of representative images, statistical processing is performed in the same manner as described above.
(Step S106) The color analysis unit 152 of the image analysis unit 106 performs color tone analysis of each image. In the image reproducing apparatus 101 according to the present embodiment, as described in FIG. 3, “red”, “green”, “blue”, “cyan”, “yellow”, “magenta”, “ It is classified into nine color systems of “white”, “ash”, and “black”. Here, when there are a plurality of images, as described in step S105, for example, the classification of the analysis result is statistically processed, and the classification of the most color tone is set as the representative color tone. For example, when five images are selected, if “red” is one and “green” is four, the representative expression is “green”. Alternatively, the representative image may be selected in step S101, and only the result of analyzing the facial expression included in the representative image may be used. When there are a plurality of representative images, statistical processing is performed in the same manner as described above.
(Step S107) The control unit 105 determines music (background music: BGM) to be played back during the slide show based on the analysis results of steps S105 and S106. The background music is determined with reference to the music classification table 162 stored in advance in the storage unit 107 as described above with reference to FIG.
(Step S108) The control unit 105 reads out the music data determined in step S107 from the storage unit 107, converts the music data into an audio signal by the audio output unit 103, outputs the audio signal from the speaker 103a, and displays the image selected in step S101. Data is sequentially read from the storage unit 105, and an image is displayed on the display unit 102 in accordance with a predetermined slide show setting (image display interval, image switching effect, etc.). Note that the reading order may be read from an image with the oldest shooting date and time, or the file names may be rearranged in order and read.
(Step S109) The control unit 105 determines whether or not the reproduction of the selected image has been completed. If all of the slide shows are finished, the slide show is finished. If the slide shows remain, the process returns to step S108 and the same processing is repeated. Note that the same image may be repeatedly displayed from the beginning until the music reproduction ends.

  As described above, the image reproducing apparatus 101 according to the present embodiment can automatically select music that matches the emotional atmosphere of the image displayed on the display unit 102 in a slide show and reproduce it from the speaker 103a.

Note that if all the images selected in step S101 do not include a face, the music to be played back is determined based on the color tone classification. In this case, for example, referring to the music classification table 162 in FIG. 4, there are four types of music data F1 to F4 in each color tone from C1 to C9. Select music data. Alternatively, music data when no face is included may be set in the music classification table 162.
(Application 1)
In the above embodiment, as shown in FIG. 1, it is assumed that an image captured in advance is stored in the storage unit 107 or the memory card 109a. However, as shown in FIG. The electronic camera 101a provided with the unit 110 may be used. In this case, an image captured by the imaging unit 110 can be added to the storage unit 107 or the memory card 109a.

In the case of the electronic camera 101a, every time an image is captured by the imaging unit 110, the emotional atmosphere of the captured image is analyzed by the image analysis unit 106, and the analysis results (color tone classification, facial expression classification, etc.) You may add as header information of data. This eliminates the need for the image analysis unit 106 to perform image analysis when the captured images stored in the storage unit 107 or the memory card 109a are displayed as a slide show, thereby reducing the processing load when executing the slide show. For example, in the flowchart of FIG. 5, it is not necessary to execute the processing from step S103 to step S106.
(Application example 2)
In the image reproducing device 101 in FIG. 1 or the electronic camera 101a in FIG. 6, as shown in FIG. 7, a communication unit 111 may be further provided, and the electronic camera 101b having the image reproducing device 101b or the imaging unit 110 may be used. Alternatively, the mobile phone 101b or the smart phone 101b may be used.

  In the case of FIG. 7, the control unit 105 can acquire music data and image data on a network connected via the communication unit 111, and is suitable for, for example, a shooting date / time, playback date / time, or a shooting location / playback location. Music data can be acquired from the network and reproduced from the speaker 103a when the slide show is executed. As a result, the storage capacity of the storage unit 107 can be reduced, and optimal music data can be reproduced from an enormous number of music data on the network such as the latest music data. Even in this case, since it is necessary to know to which color classification and facial expression classification the music acquired from the network corresponds, a music title list corresponding to the color classification and facial expression classification is stored in the music classification table 162. It is assumed to be stored in advance.

  Alternatively, the music classification table 162 itself may be held in a specific server on the network so that it can be shared by a plurality of users. In this case, the manufacturer of the image playback apparatus 101 can manage the server and appropriately update and maintain the music title, so that it can be used for a huge amount of music data around the world. As a result, the image playback device 101b (or the electronic camera 101b) does not need to store the music data 161 and the music classification table 162 in the storage unit 107, and the image analysis unit 106 analyzes the images displayed in the slide show, and the analysis result. It is possible to acquire and reproduce music data suitable for an image to be reproduced by inquiring a server on the network for information on color classification, facial expression classification, and the like. In consideration of the copyright of music data and the like, it may be played back in real time using a streaming distribution technique instead of being played back after downloading, or may be charged further.

  Further, not only the image stored in the storage unit 107 or the memory card 109a but also the image data on the network that matches the analysis result of the image is acquired and woven into the image stored in the storage unit 107 or the memory card 109a. You may make it perform a slide show. Thereby, for example, various images related to the shooting date and time, the shooting location, or the playback date and time and the playback location can be acquired from the network, so that the slide show can be enjoyed more enjoyably. As with the music data, the image on the network is managed by a specific server, and the emotional atmosphere analysis result (color tone classification, facial expression classification, etc.) of the image on the network is added in advance. As a result, only images having the same emotional atmosphere as the images stored in the storage unit 107 or the memory card 109a for slide show display can be acquired from the network and displayed.

  Here, in the above-described embodiment and each application example, the color analysis unit 152 of the image analysis unit 106 is intended for all regions in the image, but the color tone of the central region is analyzed. May be. Or you may make it analyze the color tone of the to-be-photographed object or area | region whose focus shift | offset is below a preset threshold value. In addition, when focus position information is added to image data, for example, the color tone of an area centered on an AF (autofocus) position may be analyzed. Alternatively, the image may be divided into a plurality of regions, the high frequency component of the image is analyzed for each region, and the region having a high high frequency component may be selected as the focused region. In this way, color analysis may be performed with the central portion and focus position of the image as the main subject of the image. You may make it analyze a color tone. Furthermore, the color tone of the image may be classified by weighting a specific area such as the central area, the focus area, and the main subject area and other areas. In this case, analysis is performed such that the specific area is emphasized at a ratio of 0.7 for the color tone of the specific area and 0.3 for the color tone of the other areas.

  Further, in the above-described embodiment and each application example, it has been described that one face is captured in the image. For example, when a plurality of faces are captured, the facial expression analysis unit 151 of the image analysis unit 106 is the center. Only facial expressions in the vicinity of the part may be analyzed, or all facial expressions may be analyzed and subjected to statistical processing to adopt the most facial expressions. Alternatively, the facial expression of the largest face may be analyzed, or the facial expression of the most focused face may be analyzed.

  Furthermore, in the flowchart of FIG. 5, two expressions, facial expression and color tone, are analyzed, but as shown in FIG. 8, a step S106a is provided between step S106 and step S107, and other than facial expression and color tone. The analysis may be performed under the conditions (for example, shooting date / time, shooting location, shooting mode, playback date / time, playback location, etc.). In this case, in the next step S107, optimal music data can be selected by adding other conditions to the expression and tone analysis results. For example, in the music classification table 162 of FIG. 4, one music is assigned to one element of the matrix, but a plurality of music is assigned to one element of the matrix. As an example, three pieces of music BGM1, BGM1a, and BGM1b are assigned to the elements C1 and F1, and the music to be selected is switched by analyzing conditions other than the color tone and facial expression in step S106a of the flowchart of FIG. For example, BGM1, BGM1a and BGM1b are all music with an emotional atmosphere corresponding to C1 and F1, but there is a subtle difference in the atmosphere. It is assumed that BGM1a is a song suitable for a brighter daytime atmosphere than BGM1 and BGM1b, and BGM1b is a song suitable for a calm atmosphere at night than BGM1 and BGM1a. In this case, from the information added to the image data of the image to be displayed, BGM1 is selected when the shooting time is morning, BGM1a is selected at noon, and BGM1b is selected at night. In addition, when there are a plurality of images corresponding to the same time zone, statistical processing is performed, and the determination is made with the most time (for example, the night when the time after 18:00 is the most). Similarly, when discriminating by shooting date, music for May is selected when there are the most images shot in May. Similarly, for the shooting location, music related to the region may be selected according to the region (Tohoku, Kanto, Kansai, Japan, USA, Europe, etc.).

  In addition, when information on a shooting mode (night view, landscape, sports, portrait, etc.) at the time of shooting is added as header information of image data, information such as a shooting mode may be used. For example, in the case of an image shot in the night view mode, there are many cases that it is night or dark. Therefore, music with a calm feeling is selected, and music with a refreshing feeling is selected in the landscape mode. Similarly, in the case of an image shot in the night view mode, it is often night or dark, so calm music is selected, and in the landscape mode, refreshing music is selected.

  Further, the control unit 105 of the image reproduction apparatus 101 is provided with a clock function or a GPS (Global Positioning System) function to acquire a reproduction date and time and a reproduction place for executing the slide show, and the same concept as the photographing date and time and the photographing position. Thus, music suitable for the playback date and the playback location may be selected.

  As described above, the image playback device 101 (or the image playback devices 101a and 101b (or the electronic cameras 101a and 101b) according to each embodiment automatically plays music that matches the emotional atmosphere of the images displayed on the display unit 102 in a slide show. Can be selected and reproduced from the speaker 103a.

  As described above, the image reproducing apparatus according to the present invention has been described by way of example in each embodiment, but can be implemented in various other forms without departing from the spirit or main features thereof. Therefore, the above-described embodiment is merely an example in all respects and should not be interpreted in a limited manner. The present invention is defined by the claims, and the present invention is not limited to the text of the specification. Further, all modifications and changes belonging to the equivalent scope of the claims are within the scope of the present invention.

101... Image reproduction apparatus 101 a... Electronic camera 101 b... Image reproduction apparatus (electronic camera)
102 ... Display unit 103 ... Audio output unit 104 ... Operation unit 105 ... Control unit 106 ... Image analysis unit 107 ... Storage unit 108 ... Common bus 109 ... Image input Unit 109a ... Memory card 110 ... Imaging unit 111 ... Communication unit 151 ... Expression analysis unit 152 ... Color analysis unit 161 ... Music data 162 ... Music classification table 163 ... image data

Claims (10)

A display for displaying an image;
Analyzing the color tone and facial expression of the image and classifying the image into a plurality of predetermined types;
A controller that holds a plurality of music data and reproduces the predetermined music data corresponding to the color tone and facial expression classification of the image when the image is displayed on the display unit. An image playback device. The image reproduction apparatus according to claim 1,
When there are a plurality of images to be displayed on the display unit,
The analysis unit statistically analyzes the color tone classification result of each of the plurality of images and the facial expression classification result of an image including a face among the plurality of images, respectively, and performs the maximum frequency color tone classification and maximum frequency. Seeking facial expression classification
The control unit reproduces the predetermined music data corresponding to the maximum frequency tone classification and the maximum frequency facial expression classification. The image reproduction apparatus according to claim 1,
When there are a plurality of images to be displayed on the display unit,
The analysis unit analyzes the color tone and facial expression of a representative image set in advance among the plurality of images and classifies them into a plurality of predetermined types,
The control unit reproduces the predetermined music data corresponding to the classification of the color tone and the facial expression of the representative image when the plurality of images are displayed on the display unit. The image reproduction apparatus according to claim 1,
An additional information acquisition unit that acquires at least one additional information of a shooting date and time, a shooting location, and a shooting mode of the image displayed on the display unit;
The control unit reproduces the predetermined music data corresponding to the color classification, the facial expression classification, and the additional information. The image reproduction apparatus according to claim 1,
An additional information acquisition unit that acquires at least one additional information of a reproduction date and time and a reproduction place for displaying an image on the display unit;
The control unit reproduces the predetermined music data corresponding to the color classification, the facial expression classification, and the additional information. In the image reproducing device according to any one of claims 1 to 5,
The image reproduction apparatus characterized in that the analysis unit analyzes a color tone of a preset main subject or a specific area in the image. The image reproduction apparatus according to claim 6, wherein
The image reproducing apparatus according to claim 1, wherein the main subject or the specific region is a subject or region whose focus shift is equal to or less than a preset threshold value. In the image reproducing device according to any one of claims 1 to 7,
An image reproducing apparatus comprising: a table indicating correspondence between color tone and facial expression classification analyzed by the analysis unit and the plurality of music data. In the image reproducing device according to any one of claims 1 to 8,
As the header information of the music data, the color and the facial expression classification corresponding to the music are added in advance,
The control unit searches the music data of the header information corresponding to the analysis result of the analysis unit, and when there are a plurality of search results, determines the music data to be reproduced according to a preset condition. An image reproducing apparatus. The image reproduction apparatus according to claim 9, wherein
When there are a plurality of search results, the control unit determines the music data to be played back according to at least one of the shooting date / time, shooting location, playback date / time, and playback location of an image to be displayed. apparatus.

Images