JP2010176224A - Image processor and digital camera - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image for clearly reporting the feeling of an object person. <P>SOLUTION: A face expression detection part 23 detects a smiling face of an object person in an object image, and a balloon insertion part 27 automatically inserts a balloon having at least one of a shape and color suitable to the smiling face, and a text insertion part 29 automatically inserts a text suitable to the smiling face into the balloon, and insertion completion object image data into which the balloon and the text have been inserted are stored in a memory 16a. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus for adding predetermined information to an image and a digital camera including the image processing apparatus.

Conventionally, when adding predetermined information to a subject image taken with a digital camera, the subject image recorded on the recording medium is reproduced and displayed on a display, and manually added using image processing software while viewing the reproduced image. It was. However, the above-described conventional technique is a time-consuming operation because information to be added is selected and placed in the image while viewing the reproduced image on the display.
On the other hand, there has been proposed a camera having a function of recognizing a facial expression of a subject in an image and copying a text or character that matches the atmosphere below the film when the facial expression is a predetermined facial expression (for example, Patent Documents). 1).

JP 2001-51338 A

  However, in the camera described in the above-mentioned patent document, the place where the text or character is copied is always below the image. Therefore, whether the content of the text or character originates from the subject person or the photographer adds. There is a problem that the sentence is unclear.

(1) An image processing apparatus according to the first aspect of the present invention provides a facial expression detection means for detecting that a facial expression of a subject person in the subject image data is a predetermined facial expression, and a predetermined facial expression by the facial expression detection means. A balloon insertion means for automatically inserting a balloon having at least one of a shape and a color suitable for a predetermined facial expression, and text suitable for the predetermined facial expression detected by the facial expression detection means. Text insertion means for automatically inserting into a speech balloon, display means for displaying a reproduction image based on the inserted subject image data into which the speech balloon is inserted by the speech balloon insertion means and text is inserted by the text insertion means, and the inserted subject Storage means for storing image data.

  According to the image processing apparatus of the present invention, since a speech balloon and text suitable for the facial expression are automatically inserted into an image in which a predetermined facial expression of the subject person is detected, it is clear that the subject person has emitted. It becomes an easy-to-understand image.

It is a block diagram which shows the structure of the digital camera which concerns on embodiment of this invention. It is a figure which shows typically an example which inserted the balloon, the text, and the illustration into the subject person's face. It is a figure which shows typically another example of a speech balloon and a text. FIG. 3A corresponds to an angry expression, and FIG. 3B corresponds to a sad expression.

Hereinafter, a digital camera according to an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a configuration of a digital camera according to an embodiment of the present invention.
As shown in FIG. 1, the digital camera includes a photographic lens 11, a diaphragm 12, an image sensor 13, a buffer memory 14, and an image processing unit 15. The digital camera includes an image recording unit 16, a CPU (Central Processing Unit) 17, a ROM (Read Only Memory) 18, a bus 19, an image reading unit 20, a facial expression setting unit 36, a manual editing unit 37, and a display control unit 41. And a display 42.

  The image processing unit 15, the image recording unit 16, the CPU 17, the ROM 18, the image reading unit 20, the facial expression setting unit 36, the manual editing unit 37, and the display control unit 41 are connected to each other via the bus 19.

The CPU 17 functions as a face detection unit 21, a facial expression detection unit 23, a facial expression level determination unit 25, a balloon insertion unit 27, a text insertion unit 29, an age / gender reasoning unit 31, an illustration insertion unit 33, and a data storage instruction unit 35. To do. Further, the CPU 17 controls the photographing lens 11, the diaphragm 12, and the image sensor 13 that are photographing means.
The ROM 18 includes a face data storage unit 22, a facial expression data storage unit 24, a facial expression level data storage unit 26, a balloon data storage unit 28, a text data storage unit 30, an age / gender data storage unit 32, and an illustration data storage unit 34. Function.

  The photographing lens 11 includes a plurality of lenses including a zoom lens and a focus lens, and forms a subject image on the image sensor 13. In FIG. 1, for the sake of simplicity, the taking lens 11 is shown as a single lens. The imaging element 13 generates an image signal by photoelectrically converting the subject light L1 from the photographing lens 11.

  The image signal output from the image pickup device 13 is sent to the image processing unit 15 via the buffer memory 14, where predetermined various image processing is performed. At the stage before the start of photographing, the image signal from the image sensor 13 is sent to the display 42 via the buffer 19 via the buffer memory 14 and the image processing unit 15 and displayed as a through image. In the photographing stage, the image signal from the image sensor 13 is recorded in the image recording unit 16 via the bus 19 via the buffer memory 14 and the image processing unit 15.

  The image recording unit 16 records the image data and attribute data related to the image data in association with each other in a nonvolatile memory (storage medium) 16a. The image data includes subject image data from the image sensor 13 and subject image data input to the image recording unit 16 from an external device.

  The image reading unit 20 is an operation unit that searches for image data recorded in the memory 16a of the image recording unit 16 and reproduces an image based on attribute data.

  The face detection unit 21 inputs subject image data and compares it with face data stored in advance in the face data storage unit 22 to detect the face of the subject person in the image. When there are a plurality of subjects, the face of each person is detected. The face data storage unit 22 stores, for example, feature point data relating to the shape of eyebrows, eyes, nose, and lips.

  For the face detection, for example, a detection method disclosed in Japanese Patent Laid-Open No. 2001-16573 can be used. In this detection method, feature points are extracted from an input image to detect the face area, face size, etc. of the subject. The feature points include end points of eyebrows, eyes, nose, lips, and face contour points, such as the head vertex and the lower end point of the chin.

  As other face detection, for example, a detection method disclosed in JP-A-2005-157679 can be used. In this detection method, first, a luminance difference between two pixels in an input image is learned as a feature amount, and an estimated value indicating whether or not a face exists in a predetermined region in the input image based on the feature amount. And when the estimated value is 1 or more, it is determined that a face exists in the predetermined area.

The facial expression detection unit 23 compares the facial expression of the image of the face area detected by the face detection unit 21 with predetermined facial expression data stored in advance in the facial expression data storage unit 24, so that It is detected that the facial expression of the subject person corresponds to a predetermined facial expression. The facial expression detection unit 23 detects a facial expression for each person's face when there are a plurality of subject persons.
There are various types of facial expressions such as a smiling face, a crying face, an angry face, a surprised face, and a sleeping face, and the facial expression data storage unit 24 stores the plurality of facial expression data. For example, when detecting that the facial expression of the subject person in the subject image is a smile, the facial expression detection unit 23 outputs a detection signal to that effect. The image recording unit 16 records subject image data and attribute data based on the detection signal in the memory 16a in association with each other.

  When the facial expression detection unit 23 detects a facial expression of an image in the face area, a detection method disclosed in Japanese Patent Application Laid-Open No. 2008-42319 can be used. In this detection method, for example, in order to detect a smile, the type of facial expression is determined based on whether the face of the detected image is close to the two facial expressions of a smile and a normal face. .

  The facial expression level determination unit 25 compares the facial expression of the image of the facial area detected by the face detection unit 21 with a plurality of facial expression level data stored in advance in the facial expression level data storage unit 26. It is determined to which facial expression level the facial expression of the subject person in the image of the region corresponds. The facial expression level determination unit 25 outputs a determination signal corresponding to the facial expression level of the subject person. The image recording unit 16 associates the subject image data with attribute data indicating the level of the predetermined facial expression and records it in the memory 16a.

  The facial expression level data storage unit 26 stores, as the degree of facial expression (facial expression level) for each type of facial expression, for example, three levels of smile level data: smile, medium laughter, and big laughter for a smile. Yes.

  As a method for determining the degree of smile, for example, a method disclosed in Japanese Patent Application Laid-Open No. 2004-46591 can be used. This determination method evaluates the degree of smile for the smile of the input partial image, and calculates a smile evaluation value. When evaluating smiles, calculate the evaluation points for the shape of each element of the eyebrows, pupils, and lips by referring to the smile data stored in advance. Value.

  The balloon insertion unit 27 automatically inserts a balloon into a person's face in the subject image data in which it is detected by the facial expression detection unit 23 that the face of the subject person has a predetermined facial expression, and the subject image data Combining balloon image data. A speech balloon is a frame (figure) for writing a speech uttered by a person in the subject image, and there are various shapes and colors of the speech balloon.

  The balloon data storage unit 28 stores data representing various balloons having different shapes, colors, sizes, and the like. The balloon insertion unit 27 automatically extracts balloon data having a shape, color, and size suitable for the size of the face image and the type of facial expression from the balloon data stored in the balloon data storage unit 28, A speech bubble is automatically inserted into the subject image. At this time, the balloon insertion unit 27 also automatically determines the insertion position of the balloon in the subject image. Then, when the balloon insertion ends, the balloon insertion unit 27 generates a balloon insertion completed signal.

  The text insertion unit 29 automatically inserts text into a person in the subject image data in which the face expression of the subject person is detected by the facial expression detection unit 23 to have a predetermined facial expression, and the text image is added to the subject image. Synthesize. Text is a character or symbol that means a voice or a word uttered by a person in the subject image, and there are various text contents (sentences), text size, text color, and font. The text is inserted into the balloon frame.

  The text data storage unit 30 stores various types of text data having different sentences, character sizes, character colors, and fonts. The text insertion unit 29 automatically extracts text, character size, and text color suitable for the type of facial expression from the text stored in the text data storage unit 30, and the text insertion unit 27 extracts the text. Automatically inserts into the frame of the inserted callout. Then, when the text insertion is completed, the text insertion unit 29 issues a signal indicating that the text has been inserted.

  The age / sex inference unit 31 infers the age / sex of the subject person based on the image of the face area detected by the face detection unit 21. That is, the age / gender reasoning unit 31 has the feature amount of each feature point for each feature point in the face image of the subject person and each feature point of the face stored in advance in the age / sex data storage unit 32. The age or gender of the subject person is inferred by comparing color data and color data. Then, the age / sex reasoning unit 31 outputs the reasoning result, for example, reasoning data that the subject person's age is in their 20s and the sex is female. The age / gender data storage unit 32 stores, for example, feature data and color data possessed by feature points such as eyebrows, eyes, nose, and lips for each age of each gender.

  As a method for inferring age / sex, for example, a method disclosed in Japanese Patent Application Laid-Open No. 2004-222118 is used, and the above-described feature amount is input to a system called a support vector machine.

  The illustration insertion unit 33 automatically inserts an illustration into a person in the subject image data in which the face of the subject person is detected by the facial expression detection unit 23 to have a predetermined facial expression, and adds the illustration image to the subject image. Synthesize. Illustrations include star, cross, teardrop, and flower shapes.

  The illustration data storage unit 34 stores such various types of illustration data, and further stores some data having different sizes and colors for each type. For example, in the case of a star-shaped illustration, three types of sizes, large, medium, and small, and two types of colors, gold and silver, are prepared. The illustration insertion unit 33 automatically extracts illustrations of types, sizes, and colors suitable for the size of the facial image, the type of facial expression or the facial expression level from the illustrations stored in the illustration data storage unit 34. Insert an illustration into the subject image. At this time, the illustration insertion unit 33 also automatically determines the illustration insertion position and quantity. When the illustration insertion is completed, the illustration insertion unit 33 generates a signal indicating that the illustration has been inserted.

  FIG. 2 is a diagram schematically illustrating an example in which a balloon, text, and an illustration are inserted into the face of a subject person. As shown in FIG. 2, a balloon 101 and a text 102 “Ahahaha” written in the balloon 101 are displayed near the subject person 100, and a star shape is displayed on the left eye corner of the subject person 100. Two illustrations 103 are inserted.

  FIG. 3 is another example of a speech balloon and text. FIG. 3 (a) shows an angry expression with the sharp shape of the speech balloon, and FIG. Represents the expression. Of course, each facial expression is also represented by the content of the text.

The data storage instructing unit 35 converts the subject image data into which the speech balloon and the text have been inserted in accordance with the speech balloon inserted signal from the speech balloon inserting unit 27 and the text inserted signal from the text inserting unit 29 into the speech balloon and the text. Is issued together with attribute data indicating that it has been inserted into the memory 16a. The image recording unit 16 records the inserted subject image data on the basis of the instruction signal and the attribute data indicating the insertion in the memory 16a in association with each other.
Further, the data storage instruction unit 35 issues an instruction signal to store the subject image data into which the illustration has been inserted in the memory 16a together with the attribute data in accordance with the signal with the illustration inserted from the illustration insertion unit 33. The image recording unit 16 records the subject image data on which the illustration has been inserted based on the instruction signal and the attribute data indicating that the illustration has been inserted in the memory 16a in association with each other.

  The facial expression setting unit 36 is an operation unit for externally setting the facial expression type and facial expression level of the subject person, and can set a plurality of facial expressions including a smile and a level for each facial expression. For example, when the facial expression setting unit 36 sets smile as the facial expression, the image reading unit 20 reads the smiling subject image data from the memory 16 a of the image recording unit 16. Similarly, when the facial expression setting unit 36 sets a big smile as the facial expression level, the image reading unit 20 reads the subject image data of the big smile from the memory 16 a of the image recording unit 16.

  The manual editing unit 37 is an operation unit for manually changing the arrangement location and quantity of the balloons, texts, and illustrations inserted into the subject image, or replacing the already automatically inserted ones with another ones. The user can perform such a manual operation while viewing the subject image displayed on the display 42.

  The display control unit 41 controls display on the display 42. That is, the display control unit 41 controls the display mode when displaying the subject image temporarily recorded in the buffer memory 14 and reproducing and displaying the subject image stored in the memory 16a of the image recording unit 16.

  The display 42 displays a through image, displays a subject image temporarily recorded in the buffer memory 14, and displays a subject image stored in the memory 16 a, and relates to the subject image according to a command from the display control unit 41. Attribute data to be displayed is displayed.

The digital camera configured as described above operates as follows.
First, it is assumed that a smile is set as a facial expression by the facial expression setting unit 36. When shooting is performed and the image sensor 13 outputs the subject image data, the face detection unit 21 compares the subject person image of the subject image data with the face data stored in the face data recording unit 22 to compare the face of the subject person. Detect areas. The facial expression detection unit 23 compares the face area image detected by the face detection unit 21 with the facial expression data in the facial expression data storage unit 24, and the facial expression of the subject person is “smile”, “crying face” or the like. It is detected that it corresponds to the facial expression. Here, it is assumed that the facial expression detection unit 23 detects a smile.

  The balloon insertion unit 27 is a balloon 101 suitable for the smile, as shown in FIG. 2, near the face of the person in the subject image in which the facial expression detection unit 23 detects that the face of the subject person is smiling. For example, a balloon with a round shape and a bright color is extracted from the balloon data stored in the balloon data storage unit 28 and automatically inserted, and the balloon image data is synthesized with the subject image data. When the insertion of the balloon is completed, the balloon insertion unit 27 issues a signal indicating that the balloon has been inserted.

  When the balloon insertion is completed, the text insertion unit 29 automatically extracts text, text size, and text color suitable for the smile of the subject person from the text stored in the text data storage unit 30, and the subject image Text is automatically inserted into the frame of the balloon inside, and the text data is combined with the subject image data. As text suitable for a smile, for example, a text string of a laughing voice of “Ahahaha” as shown in FIG. 2 is shown in red. When the text insertion is completed, the text insertion unit 29 issues a signal indicating that the text has been inserted.

  Subsequently, the illustration insertion unit 33 automatically extracts from the illustrations stored in the illustration data storage unit 34 types, sizes and colors suitable for the smile of the subject person, and inserts the illustration into the subject image. Then, the illustration data is synthesized with the subject image data. At this time, the illustration insertion unit 33 also automatically determines the illustration insertion position and quantity. As an illustration suitable for a smile, for example, a star-shaped glow illustration as shown in FIG. When the illustration insertion unit 33 finishes inserting the illustration, the illustration insertion unit 33 generates a signal indicating that the illustration has been inserted. In addition to smiles, facial expressions of sadness may use illustrations that image ectoplasm.

When the above-described balloon insertion, text insertion, and illustration insertion are completed, the inserted subject image data as shown in FIG. 2 is obtained.
A reproduced image based on the inserted subject image data is displayed on the display 42. At that time, if necessary, the user operates the manual editing unit 37 to change the placement location and quantity of the speech balloons, texts, and illustrations while viewing the inserted subject image on the display 42, for example, to smile. It is possible to change a balloon already inserted as appropriate to another type, or change the text content (sentence).

  The data storage instructing unit 35 responds to the speech balloon, text, and text inserted from the speech balloon insertion unit 27, the text inserted signal from the text insertion unit 29, and the illustration inserted signal from the illustration insertion unit 33. An instruction signal is issued to save the subject image data into which the illustration has been inserted in the memory 16a together with the attribute data. The image recording unit 16 records the inserted subject image data on the basis of the instruction signal and the attribute data indicating the insertion in the memory 16a in association with each other. Note that the original subject image data into which no balloon, text, or illustration has been inserted is stored in the memory 16a as it is along with its attribute data. Accordingly, when it is troublesome to display a balloon, text, or illustration, the original subject image may be displayed.

The digital camera according to the present embodiment has the following operational effects.
(1) By inserting a balloon and text in a subject image in which the smile of the subject person is detected, an image that can instantly and clearly convey the joyful feeling of the subject person as if it were a word issued by the subject person.
(2) Inserting an illustration into the subject image in which the smile of the subject person has been detected gives richness to the facial expression of the subject person and makes the image fun to see.

The digital camera according to the present embodiment can also perform the following operations.
(1) In the above-described embodiment, the facial expression detection unit 23 inserts a speech balloon or text on the subject image for which a smile is detected. It is natural that the content of the text (sentence) is different from that of laughter.
For example, the facial expression detection unit 23 detects a smile and the facial expression level determination unit 25 determines that the smile level of the subject person is a big laughter for the subject image in which the text of a laughing voice “Ahahaha” is inserted. In that case, a text of a laughing voice “Wawahaha!” Suitable for a big laughter is more suitable for the subject image. In this case, the text insertion unit 29 changes the text based on the determination signal from the facial expression level determination unit 25, and the image recording unit 16 indicates that the subject image data and the smile level of the subject person are laughing. The attribute data is associated and recorded in the memory 16a. Also, the illustration insertion unit 33 can increase or decrease the number of illustrations 103 in FIG. 2 or change the size of the illustrations 103 according to the smile level.

(2) When there are a plurality of subject persons in the subject image, the facial expression detection unit 23 detects the facial expression of each subject person, and for example, the facial expression setting unit 36 sets a smile as a predetermined facial expression. If it is, a speech balloon and text can be automatically inserted for each person image for which a smile is detected.

(3) In the above-described embodiment, the facial expression detection unit 23 inserts a speech balloon or text into the subject image for which a smile has been detected. However, the age / sex reasoning unit 31 determines the age and sex of the subject person. It may be configured such that at least one is inferred, and the balloon insertion unit 27 changes the shape and color of the balloon based on the inference result. For example, when the inferred result of the subject person is in his twenties and a woman is obtained by the age / sex reasoning unit 31, the color of the balloon is changed from light blue to pink according to the young woman. Similarly, the text color of the text is changed from the blue color to the red color. Thereby, even if it is the same smile, the speech balloon and the text suitable for the age and gender of the subject person can be inserted. The image recording unit 16 records the subject image data and the attribute data representing the age and sex of the subject person in the memory 16a in association with each other.

The digital camera according to the present embodiment can be modified as follows.
(1) In the embodiment described above, before the subject image data is recorded in the memory 16a, the balloon insertion by the balloon insertion unit 27, the text insertion by the text insertion unit 29, and the illustration insertion by the illustration insertion unit 33 are performed. The image recording unit 16 records the completed subject image data in the memory 16a.

  In this modification, the subject image data from the image sensor 13 is recorded in the memory 16a without performing the smile detection operation of the subject person. Thereafter, the image reading unit 20 reads the subject image data recorded in the memory 16a, and the facial expression detection unit 23 detects the smile of the subject person in the read subject image data. Then, for the person image of the subject image data in which a smile is detected, balloon insertion, text insertion, and illustration insertion are performed as in the present embodiment, and the inserted subject image data is recorded in the memory 16a. In this way, it is possible to read out subject image data recorded in the memory 16a and perform smile detection, balloon insertion, text insertion, and illustration insertion.

(2) In the above-described embodiment, the balloon insertion and the text insertion are performed at the same time, but it is also possible to perform the text insertion after the balloon insertion.
(3) In the above-described embodiment, it has been described that all three of balloon insertion, text insertion, and illustration insertion are performed. However, the digital camera may be configured to perform only balloon insertion and text insertion, or only illustration insertion. It is good also as composition which performs.
(4) In the above-described embodiment, the image recording unit 16 records the inserted subject image data and the attribute data indicating the insertion in the memory 16a in association with each other. The subject image data that has already been inserted may be stored in a specific folder without adding any attribute data. When the image data is read later, the inserted subject image data is stored in a specific folder without adding the attribute data indicating that it has been inserted, which is convenient for reading.
(5) In the above-described embodiment, a balloon having a shape and color suitable for a smile is inserted. However, if one of the shape and color corresponds to a smile, the balloon may be inserted.
(6) In the above-described embodiment, the shape and color of the speech balloon are changed based on the inference result by the age / gender reasoning unit 31 and the text color of the text is also changed. It is good also as composition which changes only one side.

In the above-described embodiment, the digital camera has been described. However, in the present invention, the image processing apparatus and application software (image viewing / editing software) that does not include the photographing unit, the buffer memory 14, and the image processing unit 15 in FIG. It is also applicable to.
The present invention is not limited to the embodiments described above as long as the characteristics are not impaired.

16: Image recording unit 16a: Memory 20: Image reading unit 23: Facial expression detection unit 24: Facial expression data storage unit 25: Facial expression level determination unit 26: Facial expression level data storage unit 27: Speech balloon insertion unit 28: Speech balloon data Storage unit 29: Text insertion unit 30: Text data storage unit 31: Age / gender reasoning unit 32: Age / gender data storage unit 33: Illustration insertion unit 34: Illustration data storage unit 35: Data storage instruction unit 36: Facial expression setting Part 37: Manual editing part

Claims (14)

Facial expression detection means for detecting that the facial expression of the subject person in the subject image data is a predetermined facial expression;
Balloon insertion means for automatically inserting a balloon having at least one of a shape and a color suitable for the predetermined facial expression into the subject image data detected by the facial expression detection means as the predetermined facial expression;
Text insertion means for automatically inserting text suitable for the predetermined facial expression detected by the facial expression detection means into the balloon;
Display means for displaying a reproduction image based on the inserted subject image data into which the balloon is inserted by the balloon insertion means and the text is inserted by the text insertion means;
An image processing apparatus comprising: storage means for storing the inserted subject image data. The image processing apparatus according to claim 1.
The storage means further stores the subject image data,
2. An image processing apparatus according to claim 1, wherein before the subject image data is stored in the storage unit, the balloon insertion unit automatically inserts the balloon and the text insertion unit performs automatic insertion of the text. The image processing apparatus according to claim 1.
The storage means further stores the subject image data,
An image processing apparatus, wherein the balloon insertion unit automatically inserts the balloon and the text insertion unit automatically inserts the text for the subject image data read from the storage unit. The image processing apparatus according to claim 1.
An image processing apparatus that performs automatic insertion of the balloon by the balloon insertion unit and automatic insertion of the text by the text insertion unit at the same time. The image processing apparatus according to claim 1.
The image processing apparatus, wherein the text insertion means automatically inserts the text after the speech balloon is automatically inserted by the speech balloon insertion means. The image processing apparatus according to claim 1.
Level determination means for determining that the degree of facial expression of the subject person in the subject image data corresponds to a predetermined facial expression level;
The image processing apparatus, wherein the text insertion unit performs the automatic insertion by changing the content of the text based on the facial expression level determined by the level determination unit. The image processing apparatus according to claim 1.
The facial expression detection means detects that the face expression of each of a plurality of subject persons in the subject image data is the predetermined facial expression;
The speech balloon insertion means and the text insertion means automatically insert the speech balloon and the text for each of the subject persons detected by the facial expression detection means as the predetermined facial expression, respectively. Image processing device. The image processing apparatus according to claim 1.
The text insertion unit performs the automatic insertion by changing at least one of the text content, character size, and character color according to the predetermined facial expression detected by the facial expression detection unit. An image processing apparatus. The image processing apparatus according to claim 1.
An inference means for inferring at least one of the age and sex of the subject person in the subject image data;
The image processing apparatus, wherein the balloon insertion unit performs the automatic insertion by changing at least one of a shape and a color of the balloon based on an inference result of the inference unit. The image processing apparatus according to claim 1.
An inference means for inferring at least one of the age and sex of the subject person in the subject image data;
The image processing apparatus according to claim 1, wherein the text insertion unit performs the automatic insertion by changing a character color of the text based on an inference result of the inference unit. Facial expression detection means for detecting that the facial expression of the subject person in the subject image data is a predetermined facial expression;
Illustration insertion means for automatically inserting an illustration having a shape and color suitable for the predetermined facial expression into the subject image data detected by the facial expression detection means as the predetermined facial expression;
Display means for displaying a reproduction image based on the inserted subject image data into which the illustration is inserted by the illustration insertion means;
An image processing apparatus comprising: storage means for storing the inserted subject image data. The image processing apparatus according to any one of claims 1 to 11,
The image processing apparatus, wherein the storage unit stores the inserted subject image data in a specific folder. The image processing apparatus according to any one of claims 1 to 11,
The storage means stores the inserted subject image data and the attribute data indicating the inserted in association with each other. A digital camera comprising the image processing apparatus according to claim 1.

Images