JP3341050B2 - Face image creation device and face image creation method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

FIELD OF THE INVENTION The present invention relates to a face image creation device and
Regarding the method of creating face images , specify the age in detail,
The present invention relates to a face image creation device and a face image creation method in which a face image suitable for the age is automatically created.

[0002]

2. Description of the Related Art Conventionally, in order to create a face image, for example, a graphic display device using a microcomputer is used. In this device, each part (for example,
A face image is created by combining part images, which are part patterns , for each eye, eyebrow, mouth, etc.).

[0003]

However, when creating a face image using a conventional graphic display device, regardless of the case where a user's own face is created by combining part patterns for each part, a face corresponding to the age of another person is created. Suddenly, it was extremely difficult to create a combination of part patterns for each part, and it took a long time to create. In addition, special skills were required to create a face suitable for another person's age. Further, there is a problem that there is often a large difference between the age that is subjectively grasped from the created face image and the age that is objectively grasped.

Accordingly, the present invention provides a face image creating apparatus and a face image creating apparatus capable of quickly and easily creating an age appropriate face image .
And a method for creating a face image .
Another object of the present invention is to provide a face image creation device and a face image creation method that can objectively evaluate a discrepancy between an age that is subjectively grasped from a face image and an age that is objectively grasped. I have.

[0005]

To achieve the above object,
A face image creation device according to the invention has the following configuration.
That is, the face image creating apparatus according to claim 1 is a
A part image record that stores each part image that represents an image
Face feature data in association with memory means and age-related data
The face characteristic data storage means in which
Means for specifying the data to be specified, and
Facial feature data corresponding to the specified age-related data
From the face feature data storage means, and
According to the feature data, the corresponding
Read out the parts image and combine these parts images.
Face image creating means for creating a face image
It is characterized by. A face image creating apparatus according to claim 2
Stores face images composed by combining each part image
Face image storage means, and the face image storage means
Memorize the age data corresponding to the face image
Age storage means and stores facial feature data according to age
Specify the facial feature data storage means and age related data
Specifying means and age-related data by the specifying means.
Is specified, the specified data and the age
Based on the data relating to age stored in the storage means
Means for outputting age difference data,
Basic face image by reading face image from image storage
Is created and output from the age difference output means.
Stored in the facial feature data storage means and the age difference data
The face feature data based on the
Change the facial feature data stored in the storage means,
The basic face image based on the updated face feature data.
Face feature data creation means for creating a new face image by correcting
And characterized in that: In addition, according to claim 3
The face image creation device generates a plurality of part images representing the face image.
Parts stored in association with age-related data
Image storage means and data on the age of the face image to be created
Means for specifying the data, and
Each part image corresponding to the age-related data
Read from the image storage means,
Face image creation means for creating a face image by combining art images
And characterized in that:

[0006] A face image creating apparatus according to claim 4
Is the first face image composed of a combination of multiple part images
First display control means for displaying an image;
Data specifying means, and
The first display system based on the
Of the first face image displayed by the control of the control means
Replace at least one part image of
Creates a second face image corresponding to data on the age of the child
Face image creation means to be created and created by this face image creation means
Display control means for displaying the displayed second face image
And characterized in that:

[0007] According to claim 5 of the present invention.Face image creation method
IsFirst face image composed of a combination of multiple part images
A first display control step of displaying an image;
Step to specify the data to be
Based on the data on the age specified by
The first displayed by the control of the first display control step
Place at least one part image of one face image
Exchange the data corresponding to the specified age
A face image creation step for creating a second face image, and the face image
Displaying the second face image created by the image creation step.
And a second display control step of causing
You.

In a preferred embodiment, the face image data
The data storage means stores information about your face or the face of others.
The face image data may be stored. The age de
The data storage means stores actual year data as age-related data.
At least one of age, date of birth, years ahead, years after
You may make it memorize | store. The face feature data storage means
Is the aspect ratio of the face,
Memorize height, size of eyes, number of wrinkles, degree of retreat near hair
You may make it. The designating means includes data relating to age.
Actual age, date of birth, years ahead, years after
At least one may be specified. The face
The feature data creating means is configured to store the face feature data in the facial feature data storage means.
As the process of changing the remembered face feature data,
Change of contour parts according to ratio, change of eye position, hairstyle
Changes and addition of wrinkles, this changed face feature data
Create past or future faces based on
You may do it. Created by the face feature data creating means.
Means for displaying or printing the new face image created are
You may have it.

[0009]

According to the first aspect of the present invention, the age is specified by the designation means.
If you specify data related to
The signature data is read from the facial feature data storage means, and the
Support from part pattern storage means according to face feature data
The part images of each part to be read and combined
By using face images (for example, your own face or others'
Face) is created automatically. Therefore, special skills
Face images suitable for the specified age without need
Can be created quickly and easily.

According to the second aspect of the present invention, a face image (for example,
For example, your own face or the face of another person) and the age at that time
Is registered, and specify another age different from that age
Then, the age stored in the age data storage means is related to the age.
Age difference data is output from the data
Data and face features stored in the face feature data storage means.
And stored in the face feature data storage means based on the data
The face feature data that is
Phase in the age to correct the facial image of the underlying on the basis of the data
Suitable new face images (for example, past faces or future faces)
Expected face) is automatically created. Therefore, special skills
Past face or future with high accuracy without the need for ability
You can easily and quickly create the expected face.

[0011]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram showing one embodiment of a face image creation device according to the present invention. In FIG. 1, the face image creating apparatus is roughly divided into a CPU 1, a feature switch 2, a cursor switch 3, a display switch 4, an age input key 5, a program ROM 6, a work RAM 7, a parts screen ROM 8,
It comprises a VRAM 9, a table ROM 10, and a display unit 11. The CPU 1 controls the entire apparatus. When an operation of designating a face part, a feature, or the like is performed by the feature switch 2, the cursor switch 3, the display switch 4, and the age input key 5, the program is stored in the program ROM 6 in accordance with the operation information. According to the stored program, the face image data corresponding to the age data is read out from the table ROM 10, and the corresponding part patterns of the respective parts are read out from the part screen ROM 8 according to the face characteristic data and combined to obtain a face image. (For example, own face or another person's face) is processed. The CPU 1 has a function as a face image creating unit.

The feature switch 2 is a switch for designating a feature of the face, and sequentially designates each part (for example, a hairstyle, a contour of the face, eyebrows, eyes, nose, mouth, etc.) constituting the face. In this embodiment, six parts are prepared as each part constituting the face. The cursor switch 3 is used for each part (for example, a face) of the face image displayed on the display unit 11.
Hair, eyebrows, eyes, nose, mouth, etc.). Specifically, a part is selected by moving a cursor position (for example, represented by a blinking state) on the screen. Note that a mouse or the like may be used instead of the cursor switch 3. The use of a mouse is similar for other switches.

The display switch 4 is operated when the face image is displayed on the display unit 11 for correction, or when the created face image is in a desired state and is set as a completed screen. The age input key 5 is for inputting and specifying data relating to age, and the data relating to age includes the actual age and date of birth. Age input key 5
For example, a ten-key is used so that an age or a date of birth can be easily input. The age input key 5 constitutes a designating means for designating data relating to age.

The program ROM 6 stores a control program for the CPU 1, the contents of which are shown in the following figures. The work RAM 7 is used as a work area in the control performed by the CPU 1. The part screen ROM 8 stores a part pattern for each part representing a face image,
A part pattern storage unit is configured. Here, an example of a part pattern for each part stored in the parts screen ROM 8 is shown in FIG. In FIG. 2, there are various types of face parts (N) constituting the face. In this case, as the face part type (N), (N) =
1 is a hairstyle, (N) = 2 is a face outline, (N) = 3 is an eye,
For (N) = 4, a plurality of types are prepared for eyebrows. Note that the part type (N) is not limited to the example shown in FIG. 2 and other parts such as a nose and a mouth are prepared. Also,
Other part types (N) may be prepared.

On the other hand, the part pattern is a deformation mode of each part (particularly, has a feature according to age). In the example of FIG. 2, for example, when attention is paid to a male hairstyle of (N) = 1, Part pattern No. [01], [0
2], [03], etc., a plurality of types are provided in advance corresponding to various types, and the parts screen RO
It is stored in M8. Part pattern No. They are arranged so that their age increases as they become larger. Similarly, each part pattern is prepared in advance for the face contour, eyes, and eyebrows. Further, for each part pattern, a variation thereof is prepared and stored in advance. FIG. 3 shows a variation of the contour pattern [03]. In FIG. 3, there are 16 types of outline patterns from [A-11] to [A-44], and there are various variations in accordance with the fact that various face outlines exist.

The VRAM 9 stores a created image in units of one screen when a face image is created.
For example, a semiconductor memory is used. The table ROM 10 stores face feature data according to age, and constitutes face feature data storage means. The face characteristic data according to the age include the aspect ratio of the face, eye height, eye size, number of wrinkles, degree of retreat near the hair, and the like. Table RO
The face characteristic data stored in M10 will be specifically described, for example, as shown in FIG. In FIG. 4, wrinkles at the corners of the eyes, wrinkles on the forehead, cheeks, etc. are arranged as parts representing facial features on the vertical axis, and the horizontal axis indicates age from 30 years old to 100 years old by dividing age from 5 years old to 5 years old. Features are located. And, for example, focusing on the wrinkles of the outer corner of the eyes, 30
At age, wrinkles in the corners of the eyes are not present, but facial features according to age (in this case, wrinkles in the corners of the eyes) are stored in advance so that the wrinkles of the corners of the eyes increase with age. Note that the characteristics of the face according to the age are not limited to the example shown in FIG. 4 and may be other examples.

A display section (display means) 11 displays an image created and processed by the CPU 1, and displays a face image when selecting each part during creation while exchanging data with the VRAM 9. Or display the completed face image. The display unit 11 has, for example, a TV display 7 for displaying an image. Note that the image display portion is not limited to the TV display, and may be a device that displays an image using a liquid crystal such as an LCD instead of a dedicated monitor device or a CRT. Alternatively, a material that is also used for other purposes may be used.

Next, the operation will be described. FIG. 5 is a flowchart showing a main program of the face image creation processing.
When this program starts, first, in step S10
Perform initial setting. In the initial setting, various registers, the work RAM 7 and the VRAM 9 are cleared, a subroutine is initialized, flags are reset, and the like. Next, in step S12, the pointer M1 is cleared to [0]. The pointer M1 is used for designating information such as facial features and age, and its value is stored in a corresponding register in the CPU 1.

Next, in step S14, the contents of the VRAM 9 are displayed on the display unit 11. As a result, for example, a face image when selecting each part during creation or a completed face image is displayed on the display unit 11. Thereafter, the process waits at step S14, at which time necessary processing is performed based on an interrupt signal from each switch. In other words, the processing for selecting each part and the like are all executed by the following interrupt routine.

FIG. 6 is a flowchart showing a feature switch interrupt routine. When the feature switch 2 is operated, the process proceeds to the feature switch interrupt routine. When shifting to this interrupt routine, first, in step S20
The pointer M1 is incremented by [1]. Next, in a step S22, it is determined whether or not the pointer M1 is equal to [9]. Here, the reason why the pointer M1 is compared with [9] is to determine whether or not the value has reached [9], which is a value exceeding eight, because there are eight pieces of face feature data representing face features. is there.

If the pointer M1 is not equal to [9],
Proceeding to step S26, (M1
+ OFFSET1) The contents of the screen data are transferred to the VRAM 9 using the data at the address as a start address. For example, when M1 = 1, the data at the address (1 + OFFSET1) becomes the start address, and the contents of the screen data of the work RAM 7 are transferred to the VRAM 9.

Here, as shown in FIG. 7, the work RAM 7 mainly stores (OFFS1 + 1) starting at address (OFFSET1 + 1).
Various necessary data are temporarily stored until the address ET5 + 2). For example, an area whose address is (OFFSET1 + 1) stores data ADD1 specified by the pointer M = 1, and this data corresponds to the address of each part stored in the parts screen ROM8. Similarly, an area having an address of (OFFSET1 + 2) stores data ADD2 specified by the pointer M = 2.
An area having an address of FSET1 + 7) stores data ADD7 specified by the pointer M = 7. Finally, at least data ADD8 specified by the pointer M = 8 is stored.

The other areas of the work RAM 7 will be described. Address (OFFSET2 + 1), (OFFSET2 +
2) Data corresponding to the cursor position is stored in the address. (OFFSET3 + 1) address, (OFFSE
T3 + 2) is a y register for storing data relating to age. (OFFSET4 + 1) address,
(OFFSET4 + 2) address... Stores data representing facial features. Specifically, (OFFSET4 +
1) An area having an address as an address stores data relating to a hairstyle, and a gender parameter for distinguishing a man or a woman is stored in the most significant bit (portion indicated by a) of the data. The gender parameter is in 1-bit units. [1] indicates a male, and [0] indicates a female.

The upper bit area (upper bit group) b of the area whose address is (OFFSET4 + 1) stores data relating to the hairstyle, and the lower bit area (lower bit group) of the same area. Character data corresponding to the age of the hairstyle is stored in c.

The area whose address is (OFFSET4 + 2) stores data relating to the outline of the face, and the most significant bit a of the data stores a gender parameter. In the area whose address is (OFFSET4 + 2), data relating to the contour of the face is stored in the high-order bit group b, and characteristic data according to the age relating to the contour of the face is stored in the low-order bit group c of the area. .
The area whose address is (OFFSET4 + 3) stores data relating to the eyes, and stores the sex parameter in the most significant bit a of the data. (OF
In the area whose address is FSET4 + 3), data relating to the eyes is stored in the upper bit group b, and characteristic data corresponding to the age is stored in the lower bit group c in the area.

Hereinafter, similarly (OFFSET4 + 4)
In an area having an address as an address, data (for example, a nose, a mouth, etc.) is sequentially stored in such a manner that data on eyebrows is stored. Among the characteristic parts of the face, the above-mentioned hairstyles, contours, eyes 3
Therefore, as the feature data corresponding to the age, the aspect of the three types (hairstyle, contour, eyes) that has changed according to the age is stored as the feature data.
(OFFSET5 + 1) address, (OFFSET5 + 2)
In the address,..., Data representing face wrinkles are stored. Specifically, in an area having an address of (OFFSET5 + 1), data on wrinkles of the outer corner of the eye is stored.
In an area whose address is (OFFSET5 + 2), data relating to wrinkles of the forehead is stored.
Data related to cheek wrinkles is stored in an area whose address is T5 + 3).

Now, for example, as described above, the pointer M1
When = 1, the data at the address (1 + OFFSET1) becomes the start address and the contents of the screen data in the work RAM 7 are transferred to the VRAM 9;
The data at the address (1 + OFFSET1) in AM7 is ADD1, and the content is one of the screens for each part stored in the parts screen ROM 8 as shown in FIG. In FIG. 8, the screen data corresponding to the address of ADD1 is a screen for selecting a gender. Therefore, when M1 = 1, a screen as shown in FIG. 9A appears corresponding to ADD1, and [01] : Male or [0
2]: A screen prompting for designation of one of women appears.

Similarly, in FIG. 8, the screen data corresponding to the address of ADD2 is a screen for selecting a hairstyle. For example, [01] has a large amount of hair and is divided into seven, and [02] has a small amount of hair. It is divided into seven, three, ... A screen that prompts the user to select a hairstyle appears as shown in FIG. 9B corresponding to ADD2. The screen data corresponding to the address of ADD3 is a screen for selecting the outline of the face, and is, for example, [01], [02],... Although not shown in the figure corresponding to ADD3, a screen for prompting selection of a face outline appears. The screen data corresponding to the address of ADD4 is a screen for selecting an eye. For example, [01] is a round eye and a double eyelid, [02] is an oval eye, and [03] is a fox egg.
... and so on. A screen for prompting selection of the eye shape appears as shown in FIG. 9C corresponding to ADD4.

The screen data corresponding to the address of ADD5 is a screen for selecting an eyebrow. For example, [01] is a crescent-shaped eyebrow, [02] is a rain-end slanting type, and so on.
It is as follows. FIG. 9 corresponding to ADD5
As shown in (d), a screen prompting the selection of the eyebrow shape appears. The screen data corresponding to the address of ADD6 is a screen for selecting a nose, for example, [01], [02],
... and so on. Although not shown in the figure corresponding to ADD6, a screen for prompting selection of a nose appears. The screen data corresponding to the address of ADD7 is a screen for selecting a mouth, for example, [01], [0]
2], ... This ADD
Although not shown in FIG. 7, a screen for prompting the user to select a mouth appears. The screen data corresponding to the address of the ADD 8 is a screen for requesting the input of the age. Although not shown, a screen for prompting the user to input the age from the age input key 5 appears. .

Returning to the description of FIG. 6, the process returns after the process of step S26. Then, in the next feature switch interrupt routine, the same processing is repeated.
At this time, first, the pointer M1 is incremented in step S20, and when the pointer M1 becomes equal to [9] in step S22, the process proceeds to step S24, where the pointer M1 is returned to [1], and thereafter, the process proceeds to step S26. Thus, every time the feature switch 2 is operated, the pointer M1
Is incremented by [1], and when the pointer M becomes equal to [9], the pointer M1 is returned to [1] again. Therefore, the content of the screen data is set to V based on the data at the address (M1 + OFFSET1) of the work RAM 7 corresponding to the pointer M1 = 1 as the start address.
Each time the feature switch 2 is operated, the pointer M1 is incremented by [1], and the content of the screen data at the address (M1 + OFFSET1) is changed to V.
The data is transferred to the RAM 9 and displayed on the display unit 11.

Each time the feature switch 2 is operated, the content of the screen data changes as shown in FIG. That is,
Each time the feature switch 2 is operated, the process shifts to the feature switch interrupt routine, and the screen shown in FIG. 9 appears.
The operator selects facial features for gender, hairstyle, eyes, eyebrows,... While viewing the screen shown in FIG.

FIG. 10 is a flowchart showing an age switch interrupt routine. When the age input key 5 is operated, the routine shifts to this age switch interrupt routine.
When shifting to this interrupt routine, first, in step S5
At 0, the age data input by operating the age input key 5 is stored in the y register. For example, when the age is input as 30 years old, the age data of [30] is stored in the y register. Next, in step S52, the contents of the y register (ie, the age data) are written into the address (OFFSET3) of the work RAM 7. Next, step S54
Sets the pointer M to [1]. Since the pointer M = 1 corresponds to the hairstyle, M = 2 corresponds to the outline, M = 3 corresponds to the eye,..., The pointer M is set to [1] in step S54 first by setting the hairstyle. This is for selecting the characteristic data (for example, part pattern) according to the age in order of the contour.

Then, the process proceeds to a step S56 to determine whether or not the pointer M is in the range [1] to [3]. When the pointer M is in the range of [1] to [3], it is determined whether or not the routine is a routine for selecting hairstyle, contour, and eye feature data as face feature data. This is because these feature data such as hairstyle, contour, and eyes need to be changed according to age. If YES in step S56, that is, if the pointer M is in the range of [1] to [3] and the routine is to select any one of the hairstyle, outline, and eye characteristic data, the process proceeds to step S58 and the y register Is converted by the M-th table. For example, when the pointer M is [1] and the routine is for selecting hairstyle characteristic data, the contents of the y register are converted using the first table. Since the first table contains hairstyle characteristic data (for example, part patterns) corresponding to the age, it is converted into hairstyle part patterns according to the age (contents of the y register) input at this time. .

Next, the data (parts pattern) converted in step S60 is stored in the lower bit group c of the area whose address is (OFFSET4 + M).
For example, when the pointer M is [1] and the routine is to select hairstyle feature data, a hairstyle part pattern corresponding to age is stored in the lower bit group c. As a result, it is possible to display a feature corresponding to the age of the hairstyle. Similarly, when the pointer M is [2] and the routine is to select the characteristic data of the face outline, the part pattern of the outline corresponding to the age is stored in the lower bit group c. When the pointer M is [3] and the routine is to select the eye feature data, the eye part pattern corresponding to the age is stored in the lower bit group c.

Next, in step S61, the pointer M is incremented. In step S62, the pointer M is set to [7].
Is determined. This is for judging whether or not selection of all six characteristic data of hairstyle, contour, eyes,... As face characteristic data has been completed. M =
If not [7], the flow returns to step S56 to repeat the same loop. When the pointer M is not in the range of [1] to [3] in step S56,
Is in the range [4] to [6], the flow branches to step S64. In this case, processing is performed on face characteristic data other than the hairstyle, the outline, and the eyes, which need not be relatively changed according to the age. Therefore, in step S64, (OFF
(SET4 + M) A predetermined value is stored in the lower bit group c of the area whose address is the address. The reason why the predetermined value is stored is to fix feature data other than the hairstyle, the outline, and the eyes to a fixed state. For example, when the pointer M is [4] and the routine is to select the eyebrow feature data, a part pattern of the eyebrow having a fixed shape regardless of age is stored in the lower bit group c. Next, in step S61, the pointer M is incremented, and the determination in step S62 is performed. Thus, the above loop is repeated until M = [7], and when M = [7], this routine is ended.

FIG. 11 is a flowchart showing a cursor switch interrupt routine. When the cursor switch 3 is operated, the routine shifts to this cursor switch interrupt routine. When the process shifts to the interrupt routine, it is first determined in step S80 whether or not image data is being displayed (for example, determination is made based on a display flag). This is for determining whether or not any screen is displayed on the display unit 11, and if no screen is displayed, the cursor does not appear. Therefore, this routine returns unless image data is being displayed.

On the other hand, when the image data is being displayed, the process proceeds to the subsequent step S82, where (M + OFFS
ET2) The data at the address is changed according to the cursor position. Since the address (OFFSET2) stores data corresponding to the cursor position, for example, when M = 1, the data at the address (OFFSET2 + 1) is changed according to the cursor position for the hairstyle. When M = 2, the data at the address (OFFSET2 + 2) for the contour is changed according to the cursor position. For example, when the cursor switch 3 is operated to select a part pattern, one of the variations of the various part patterns related to the contour as shown in FIG. 2 is selected with a cursor.

Next, in step S84, the display of the cursor position is changed. Thereby, when the cursor switch 3 is operated and moved, the display position is changed and is displayed on the screen. Next, in a step S86, it is determined whether or not the pointer M is [1]. That is, it is determined whether or not the screen is a screen for determining gender. If M = [1], the flow advances to step S88 to determine whether or not the data at the address (OFFSET2 + M) represents a man. If it represents a man, first, in step S90, N = 1 is returned. N is a gender pointer. This is because the sex pointer N is sequentially incremented from the smallest value, that is, the area corresponding to the address (OFFSET2 + 1). (O
The address FFSET4 + M) stores data representing the characteristics of the face, and the most significant bit MSB (portion indicated by a) of the data stores a gender parameter for distinguishing between male and female. Gender parameters are in 1-bit units,
"1" indicates a male, and "0" indicates a female.

Next, the process proceeds to step S92 (OFF
SET4 + N) The MSB of the data at the address is set to "1". At this time, since N = 1, (OFFSE
The MSB of the data at the address (T4 + 1) is set to "1". Next, the sex pointer N is incremented in step S94. Thus, N = 2.
Next, it is determined whether or not N = 7 in step S96. Judgment of N = 7 is (OFFSET4 + N)
This is because the MSB is set to "1" up to the maximum address. This time, since N = 7, step S92
And the same processing is repeated. Therefore, this time N
= 2, the MSB of the data at the address (OFFSET4 + 2) is set to "1". Similarly,
(OFFSET4 + 3) address, ... (OFFSET4
+6) The MSB of each data at the address is set to "1".

When N = 7 in step S96, the current cursor switch interrupt routine is terminated and the program returns to the main program. On the other hand, step S
If the pointer M is not [1] at step 86, step S1
06 and jumps to the contents of the address (OFFSET2 + M) at {(OFFSET4 + (M-1)} M of the data at the address.
The data is transferred to the upper bit group b excluding SB. As a result, the data content at the position designated by the cursor switch 3 is transferred to the area storing the facial feature data. After step S106, the cursor switch interrupt routine ends, and the process returns to the main program. If NO in step S88, that is, if the data at the address (OFFSET2 + M) does not represent a man but a woman, the process proceeds to step S98, and the sex pointer N is returned to N = 1. This is because the sex pointer N is sequentially incremented from the smallest value, that is, the area corresponding to the address (OFFSET2 + 1).

Next, in step S100 (OFFSE
(T4 + N) The MSB of the data at the address is set to “0”. At this time, since N = 1, (OFFSET
4 + 1) The MSB of the data at address is set to "0". Next, the sex pointer N is incremented in step S102. Thus, N = 2.
Next, it is determined whether or not N = 7 in step S104. N = 7 is determined by (OFFSET4 +
N) The MSB is set to "0" up to the maximum address. Since N = 7 this time, step S
Returning to step 100, the same processing is repeated. Therefore, since N = 2, the MSB of the data at the address (OFFSET4 + 2) is set to "0". Similarly, in the same manner, the address (OFFSET4 + 3),.
T4 + 6) The MSB of each data at the address is set to “0”. Then, N = 7 in step S104.
, The current cursor switch interrupt routine is terminated and the program returns to the main program.

FIG. 12 is a flowchart showing a display switch interrupt routine. When the display switch 4 is operated, the process proceeds to the display switch interrupt routine.
When shifting to this interrupt routine, first, in step S1
At 50, the display flag is inverted. Therefore, the display flag is inverted each time the display switch 4 is operated. For example, at first, the display flag is “0”, and when operated, the display flag becomes “1”, and thereafter, each time the operation is performed, “0”, “1”
repeat. In this way, it is determined whether or not the display switch 4 has been operated with respect to the previous routine.

Then, in a step S152, it is determined whether or not the display flag is "1". The fact that the display flag is "1" is, for example, the case of the first routine. In this case, the process branches to step S154 to set M1 = 1, and further transfers the screen data with the contents stored at the address (OFFSET1 + 1) as the start address to the VRAM 9. At this time, (OFFSET
The data at address 1 + 1) is ADD1, and the screen data corresponding to the address of ADD1 is a screen for selecting a gender. Therefore, first, FIG.
Is displayed on the display unit 11. According to this screen, the operator operates the cursor switch 3 to designate either [01]: male or [02]: female. After step S154, the process returns to the main program.

On the other hand, after the end of the first routine, the display flag is inverted each time the display switch 4 is operated, so that the determination result of step S152 becomes YES next time, and the process proceeds to step S156. In step S156, the pointer M is returned to [1]. Pointer M = 1 is hairstyle, M =
Since 2 corresponds to the outline, M = 3 corresponds to the eye,..., The pointer M is returned to [1] in step S156 by first selecting the hairstyle feature data, This is for sequentially selecting and displaying feature data (for example, part patterns) according to the age.

Then, in a step S158, it is determined whether or not the pointer M is [3]. M = [3] specifies eye feature data. This is because, since only the eyes have the characteristic of rising according to the age, it is inconvenient to display them as they are, so that their positions are changed.
Therefore, unless M = [3], it is determined that the routine is not a routine for designating eye characteristic data, and step S160 is performed.
The screen data with the contents stored at the address (OFFSET4 + M) as the start address is transferred to the VRAM 9. At this time, (OFF
The data at the address SET4 + M) is an area for storing face feature data. A face image corresponding to the feature data other than the eyes is displayed on the display unit 11.

Next, in step S162, the pointer M is incremented, and in step S164, it is determined whether or not the pointer M is [7]. This is to determine whether or not selection of all six pieces of hair style, contour, and eye feature data as face feature data has been completed. M = [7]
If not, the flow returns to step S158 to repeat the same loop. At this time, if M = [3] in step S158, the process branches to step S166 to execute processing for displaying the eye characteristic data. That is, in step S166, the contents of the OFFSET3 address are transferred to the y register.
That is, the age data is transferred.

Next, in step S168, (OFFSE
(T4 + M) The screen data with the contents stored at the address as the start address is sequentially read, and the y-coordinate of the screen data read in step S170 is converted based on the contents of the y register and transferred to the VRAM 9. This allows
The position of the eye (particularly, the y coordinate position) changes according to the age, and a face image suitable for the age is displayed on the display unit 11. Generally, as the age increases, the position of the eyes tends to increase. Therefore, the face image along which the eyes are corrected according to the age becomes a face image. Step S170
, The process proceeds to step S162.

Thus, the pointer M is changed from [1] to
The above processing is repeated in the range of [6], and step S16
If M = [7] at 4, the process proceeds to step S172. In the step S172, it is determined whether or not the value of the y register is smaller than [30]. This is to determine whether or not the age is specified to be less than 30 years old. If the age is less than 30, the face is unlikely to have wrinkles, so this routine is terminated and the program returns to the main program. On the other hand, if the value of the y register is equal to or greater than [30] in step S172 and the age is specified to be 30 or older, step S172 is executed.
Proceed to 174. In step S174, the screen data with the contents stored at address OFFSET5 (that is, the wrinkles of the outer corner of the eye) as the start address is sequentially read, and the y coordinate of the screen data read in step S176 is converted based on the contents of the y register. To the VRAM 9.
As a result, the number and position (particularly, the y-coordinate position) of the wrinkles of the outer corners of the eyes vary according to the age of 30 to less than 40, and a face image having wrinkles of the outer corners suitable for the age is displayed on the display unit 11. Is done. In general, as the age increases, the number of wrinkles at the outer corner of the eye tends to change as the number of wrinkles at the outer corner of the eye increases, so that the number and position of wrinkles at the outer corner of the eye are corrected accordingly. Face image.

Then, the process proceeds to a step S178, wherein it is determined whether or not the value of the y register is smaller than [40]. This is for judging whether or not the designation of the age is 30 years old or more and less than 40 years old. 3 if you are under 40
Although it is more likely that the forehead has wrinkles than the age of 0, the number of wrinkles is smaller than that of the 50-year-old, so the wrinkle processing of the forehead is performed in the range of 30 to 40 this time. Step S178
If the answer is YES, that is, if the age designation is 40 years or older, the current routine is terminated and the process returns to the main program. On the other hand, when the age is specified to be 30 years old or more and less than 40 years old, the process proceeds to step S180 (OFFSE
T5 + 1) The screen data with the contents stored at the address (ie, wrinkles of the amount) as the start address is stored in the VRAM 9.
Transfer to As a result, the number of wrinkles on the forehead changes according to the age of 30 to less than 40, and a face image having the wrinkles of the forehead suitable for the age is displayed on the display unit 11. Generally, as the age increases, the number of forehead wrinkles tends to increase, so that a face image in which the number of forehead wrinkles is corrected along with it.

Then, the process proceeds to a step S182 to determine whether or not the value of the y register is smaller than [50]. This is for judging whether or not the designation of the age is 40 years old or more and less than 50 years old. 4 if you are under 50
It is more likely that there is a wrinkle on the face than the age of 0.
The number of wrinkles is smaller than the age, so this time 40 to 50
We perform wrinkle treatment in the range of age. When YES is determined in the step S182, that is, when the age is specified to be 50 years or older, the current routine is ended and the process returns to the main program. On the other hand, if the age designation is over 40 years old and 5
If the child is under the age of 0, the process proceeds to step S184 (O
FFSET5 + 2) The screen data with the contents stored at the address (ie, cheeks) as the start address is transferred to the VRAM 9. As a result, the number of cheek wrinkles changes according to the age of 40 to less than 50, and a face image having cheek wrinkles suitable for the age is displayed on the display unit 11. In general, as the age increases, the number of cheek wrinkles tends to increase, so that the face image has a corrected number of cheek wrinkles. After step S182, the current routine ends and the process returns to the main program.

As described above, in the present embodiment, when the power of the apparatus is turned on, an initial face image is first displayed on the display unit 11, and an arbitrary 30-year-old image is corrected based on the image. Are created and displayed by combining the part patterns by manual selection. An example of a 30-year-old face image is shown in FIG. 13A, where a male face image is used as a model. After that, when the age input key 5 is operated to input an age of, for example, 10 years, a face image of 30 years old (basic face image)
Of the parts, the eye part pattern moves to the lower position corresponding to the age of 10 and the hairstyle is changed to the hairstyle corresponding to the age of 10 so that the age of 10 years as shown in FIG. A face image suitable for the face is automatically created.

When the age input key 5 is operated to input an age of, for example, 40, the eye part pattern of the 30-year-old face image (basic face image) is slightly higher than the upper part. The wrinkle of the outer corner of the eye is added (the position of the outer corner of the eye is also slightly moved), the hairstyle is changed to a hairstyle corresponding to the age of 40, and wrinkles around the mouth are added.
A face image suitable for a 40-year-old face as shown in (b) is automatically created.

On the other hand, as an example in which the age has risen, if the age input key 5 is operated to input an age of, for example, 65 years, the eyes of the parts of the 30-year-old face image (basic face image) The part pattern moves further up, wrinkles at the outer corner of the eye are further added (the position of the outer corner is also moved),
The hairstyle is changed to a hairstyle corresponding to the age of 65, and a wrinkle around the mouth is further added, so that a face image suitable for the face of the age of 65 as shown in FIG. 13C is automatically created. You.

Therefore, a face image suitable for age can be quickly and easily created without requiring special skills. Further, it is possible to objectively evaluate a discrepancy between the age that is subjectively grasped from the created face image and the age that is objectively grasped. Note that by performing gender classification, it is possible to automatically create a face image according to age for a female face in the same process.
Further, whether the face image is a person's own face or another person's face, a face image corresponding to the age can be automatically created in the same manner. Further, in addition to displaying the face image corresponding to the age on the display unit 11, for example, the printing unit 1
1A may be provided, and the printing unit 11A may print on a label tape, plain paper, or the like.

[0055]

According to the first aspect of the present invention, the specifying means is provided.
If you specify data about age by
Read the corresponding face feature data from the face feature data storage means
From the part image storage means according to the facial feature data
By reading out the corresponding parts images and combining them
Face image (for example, your own face or the face of another person)
Need special skills because it is created dynamically
Quick and easy face image suitable for the specified age without
Can be created.

According to the second aspect of the present invention, a face image (for example, a face of oneself or another person's face) and the age of the face are registered as basic face images in advance, and are different from the age. If another age is specified, age difference data is output from the data on the age stored in the age data storage means, and based on the age difference data and the face feature data stored in the face feature data storage means, The face feature data stored in the face feature data storage unit is changed, and a basic face image is corrected based on the changed face feature data to obtain a new face image (for example, a past face or (Future expected face) is automatically created, so it is possible to easily and quickly create a highly accurate past face or future expected face related to the basic face without requiring special skills. This Can be. According to the third aspect of the present invention, when data relating to the age of the face image to be created is designated, each part image corresponding to the designated data relating to the age is read from the part image storage means, and A face image can be quickly and easily created by the face image creating means by combining the respective part images. According to the fourth aspect of the present invention, when the data relating to the age is specified after the first face image composed of the combination of the plurality of part images is displayed, the data is already determined based on the data relating to the specified age. At least one part image of the displayed first face image is replaced, a second face image corresponding to the specified age-related data is created, and the created second face image is displayed. Can be done. According to the invention of claim 5, wherein, after displaying the first face image composed of a combination of a plurality of parts images, specifying data about age, based on the data about the designated age
Te, the least of the first face image already displayed
It is replaced by one of the parts image, to create a second face image corresponding to the data relating to the specified age, this work
Second face image that is formed can be displayed.

[Brief description of the drawings]

FIG. 1 is a configuration diagram of an embodiment of a face image creation device according to the present invention.

FIG. 2 is a diagram showing an example of a part pattern for each part stored in a parts screen ROM of the embodiment.

FIG. 3 is a diagram showing an example of a variation of the contour pattern of the embodiment.

FIG. 4 is a diagram showing an example of face feature data according to age in the embodiment.

FIG. 5 is a flowchart showing a main program of a face image creation process of the embodiment.

FIG. 6 is a flowchart showing a feature switch interrupt routine of the embodiment.

FIG. 7 is a diagram illustrating an example of a data storage area of a work RAM according to the embodiment.

FIG. 8 is a diagram showing an example of screen data for each part stored in the parts screen ROM of the embodiment.

FIG. 9 is a diagram showing an example of a display screen of the embodiment.

FIG. 10 is a flowchart showing an age switch interrupt routine of the embodiment.

FIG. 11 is a flowchart showing a cursor switch interrupt routine of the embodiment.

FIG. 12 is a flowchart showing a display switch interrupt routine of the embodiment.

FIG. 13 is a diagram showing an example of a created face image of the embodiment.

[Explanation of symbols]

1 CPU (face image creation means, age difference output means, face feature data creation means) 2 feature switch 3 cursor switch 4 display switch 5 age input key (designation means) 6 program ROM 7 work RAM 8 parts screen ROM ( parts image storage Means , face image data storage means, age data storage means, face feature data storage means) 9 VRAM 10 table ROM (face feature data storage means) 11 display section (display means) 11A printing section (printing means)

Continuation of the front page (56) References Masamichi Nakagawa et al., Age change of face image using skeletal model, IEICE Technical Report HC 91-54-60, Japan, The Institute of Electronics, Information and Communication Engineers, Vol. 91, NO. 508, p39-46 (58) Fields investigated (Int. Cl. ⁷ , DB name) G06T 11/60-11/80 G06F 19/00

Claims (11)

(57) [Claims] 1. A part image storage unit in which each part image representing a face image is stored; a face feature data storage unit in which face feature data is stored in association with data relating to age; designating means for reads facial feature data corresponding to the data for the specified age by the designating means from the facial feature data storing means, a corresponding part image from said part image storage means in accordance with this facial feature data And a face image creating means for creating a face image by combining these part images. 2. A face image storage means for storing a face image formed by combining each part image, and an age storage means for storing data relating to an age corresponding to the face image stored in the face image storage means. A face feature data storage unit that stores face feature data according to age; a designation unit that designates data relating to age; and when the data relating to age is designated by the designation unit,
An age difference output unit that outputs age difference data based on the designated data and the age-related data stored in the age storage unit; and a basic face that reads a face image from the face image storage unit. When you create an image theft
Further , based on the age difference data output from the age difference output means and the face feature data stored in the face feature data storage means, the face feature data stored in the face feature data storage means is And a face feature data creating means for creating a new face image by modifying the basic face image based on the changed face feature data. 3. A part image storage means in which a plurality of part images representing a face image are stored in association with data relating to age; a designating means for designating data relating to the age of a face image to be created; Reading out each part image corresponding to the data relating to the designated age from the part image storage means, and creating a face image by combining the read out part images; and Face image creation device. 4. A first display control means for displaying a first face image composed of a combination of a plurality of part images, a designating means for designating data relating to age, and a data relating to age designated by the designating means. Replacing at least one part image of the first face images displayed under the control of the first display control means, and creating a second face image corresponding to the specified age-related data. And a second display control means for displaying the second face image created by the face image creating means. (5)Consists of a combination of multiple part images
A first display control step of displaying a first face image; A specifying step for specifying data regarding the age; Data about the age specified by this specification step
Based on the control of the first display control step
At least one of the displayed first face images
Replace the part image and save the data for the specified age.
Image creation step for creating a second face image corresponding to the data
And The second face image created by this face image creation step
A second display control step of displaying A face image creating method, comprising: 6. The face feature data storage means stores face aspect ratio, eye height, eye size, number of wrinkles, and degree of retreat near the hair as face feature data according to age. face image creation device according to claim 1 or claim 2, wherein the. Wherein said specifying means, a face image creation according to any one of claims 1 to 4, characterized in that the specified actual age as data relating to age, at least one of date of birth apparatus. Output means 8. A display output or print output face image created by said face image producing means, creating a face image according to any one of claims 1 to 3, characterized by further comprising apparatus. 9. The face image creating apparatus according to claim 1, wherein said face image storing means stores a face image of a face of the user or a face of another person. Wherein said age data storing means, according to claim claim 1, wherein the actual age as data relating to age, birth date, many years, to store at least one years later 3. The face image creation device according to any one of 3. 11. The face feature data creating means includes changing face parts according to the aspect ratio of the face, and changing the position of the eyes as a process of changing the face feature data stored in the face feature data storage means. , Change the hairstyle, add wrinkles,
3. The face image creating apparatus according to claim 2, wherein a past face or a predicted face in the future is created based on the changed face feature data.