JPH09161086A - Face picture preparing device and picture generator - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a face picture preparing device capable of obtaining a face picture exaggerating its feature by an easy processing. SOLUTION: A face picture inputted by means of an image reader, etc., is stored by a picture memory 15. A control part 11 measures the value of the feature of prescribed components, namely the position and the size, of the face picture stored by the picture memory 15. The control part 11 obtains a feature value by comparing the value of the measured feature and a reference value being an average value previously stored in a control memory 19 and corrects this feature value with an exaggeration ratio previously stored in a control memory 19. The control part 11 based on this corrected value corrects the position and the size of the component of the picture stored in the picture memory 15 to emphasize the feature.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a face image creating apparatus and an image generating apparatus capable of obtaining a face image after exaggerating the features of the face image.

[0002]

2. Description of the Related Art A portrait creation method for automatically creating a portrait of a person is known. The conventional caricature creation method is
(1) A plurality of face parts prepared in advance (hair, contour, eyebrows,
Select the parts that match the real image (face) from the figures (eyes, nose, mouth, etc.) and combine them to create a portrait. (2) Create a face image obtained by the image capture device. Originally, there is a known method for creating a trace by tracing an image or designating points on a main image, connecting each point to create a line drawing, and transforming to create a portrait.

[0003]

The creation method by exchanging parts in (1) requires many parts in order to approximate a portrait to a real image. However, as the number of parts increases,
There is a drawback that the time and effort for selecting the parts are increased and the usability is deteriorated. In addition, in the method of creating by tracing (2), it is necessary to trace the line to obtain the line drawing. Therefore, there is a drawback that the amount of information to be processed for transforming the line drawing is large, the system becomes large when it is put into practical use, and it is difficult to adopt it in a large-scale system. Further, the method of (2) tracing has a problem that a relatively faithful caricature can be obtained in the input image, but it is not possible to obtain an image peculiar to the caricature with the characteristic portions exaggerated. Note that these problems are not limited to face images, and are common problems when creating an image depicting an arbitrary tangible object.

The present invention has been made in view of the above situation, and an object of the present invention is to provide a face image creating apparatus capable of obtaining a face image with exaggerated features by a simple process.
Another object of the present invention is to provide an image generating apparatus capable of obtaining an image of an arbitrary tangible object with exaggerated features.

[0005]

In order to solve the above object, a face image creating apparatus according to a first aspect of the present invention is a face image storing means for storing a face image, and the face image storing means. Characteristic measuring means for measuring the characteristic of a predetermined part of the face image stored in, and reference value storing means for pre-storing a reference value related to the reference facial characteristic for each part,
An exaggeration rate designating means for storing the exaggeration rate for each facial feature item,
The characteristic value measured by the characteristic measuring means and the reference value stored in the reference value storage means are compared for each component to obtain a characteristic value, and the characteristic value is set in the exaggeration rate designating means. Image correction means for correcting the image based on the correction value.

The face image stored in the face image storage means is, for example, one of a face image created by combining parts or a face image input from an image input device such as a camera or an image reader.

The feature measuring means extracts, for example, a part constituting a face from the face image stored in the face image storing means, and measures the feature of the part.

The characteristic measuring means measures, for example, the position and size of a predetermined component included in the face image, and the reference value storage means stores the reference value of the position and size of the component. Then, the image correction means corrects the position and size of a predetermined component included in the face image based on the correction value.

An image generating apparatus according to a second aspect of the present invention comprises an image storing means for storing an image of an object made up of a plurality of parts, and at least one of an arrangement position and a size of the parts in the image. The measuring means for measuring, the reference value storing means for storing the reference value of at least one of the arrangement position and the size of the parts of the object, the reference value stored in the reference value storing means, and the measurement by the measuring means. It is characterized by comprising a correction means for comparing at least one of the position and the shape of the component in the image according to the comparison result with the value.

With such a configuration, it is possible to obtain an image in which the features of an arbitrary object are emphasized.

[0011]

BEST MODE FOR CARRYING OUT THE INVENTION A face image forming apparatus according to an embodiment of the present invention will be described below with reference to the drawings.
FIG. 1 shows the configuration of a face image creating apparatus according to this embodiment. As shown in the figure, the face image creating apparatus includes a control unit 11 and an image input device 13 connected to the control unit 11.
The image memory 15, the key input unit 17, the control memory 19, the display unit 21, and the printing unit 23 are included.

The control unit 11 performs the operation of the entire face image creating apparatus according to the program stored in the control memory 19 and the reference value, in particular, the image input process, the feature extraction process, the feature enhancement process, etc., which will be described later. The image input device 13 is composed of an electronic camera, an image reader, etc., and inputs a face image. The image memory 15 stores the face image acquired by the image input device 13.

The key input unit 17 includes an image input key, a portrait creation key, a print key, etc., and inputs data and commands to the control unit 11. The control memory 19 stores a control program for performing image acquisition processing, feature extraction processing, feature enhancement processing, etc., which will be described later. The control memory 19 further stores, as a reference value Q, the average value of the heights, the heights, the widths, and the distances between the eyes of the faces of a large number of people classified by age group, nationality, race, sex, and the like. , The extraction reference value S and the exaggeration rate T for extracting the feature are stored for each feature. Display unit 21
Displays the face image and the like stored in the image memory 15. The printing unit 23 prints the face image and the like displayed on the display unit 21.

Next, a procedure for acquiring an image of an arbitrary person and creating a portrait from the image will be described with reference to the flowchart of FIG.

First, the user operates the key input unit 17 to instruct the input of a face image. According to this instruction, the control unit 11 activates the image input device 13 to acquire a face image (step S1). The control unit 11 uses the image input device 13
The image data supplied from the above are sequentially stored in the image memory 15 (step S1). In addition, the control unit 11 has
As shown in (A), the face image stored in the image memory 15 is displayed on the display unit 21 (step S2).

In this state, when the user operates the key input unit 17 to instruct the emphasizing process, this instruction causes step S3.
In step S4, the emphasis process from step S4 is started.

First, the control unit 11 selects the parts (eyes, nose, face, etc.) that make up a face from the face images stored in the image memory 15.
The eyes showing the most characteristic of the mouths are extracted (step S4). As an eye extraction method, for example, after normalizing the size of the entire face (enlarging or reducing so that the height LL becomes a predetermined size), the face image and the planned size and position of the eyes are included. An image corresponding to this mask may be extracted by comparing with the mask.

Next, the characteristics of the extracted eyes are measured (step S5). Specifically, the position and size of the eyes are measured. A specific example of the measuring method will be described with reference to FIG. Eye position (height) is a straight line LU indicating the height of the chin
Alternatively, the straight line LO indicating the height position of the crown can be used as a reference. Here, the distance from the straight line LU indicating the height position of the chin is shown.

The straight lines LA and LB are lines showing the heights of the upper side and the lower side of the right eye, and the height of the right eye is represented by the distance VReye between the center line of the straight lines LA and LB and the straight line LU, and the vertical width of the right eye is It is represented by the distance HReye between the straight lines LA and LB. Similarly, the upper and lower sides of the left eye can be represented by straight lines LC and LD. The height of the left eye is represented by the distance VLeye between the center line of the straight lines LC and LD and the straight line LU, and the height of the left eye is the distance H between the straight lines LC and LD.
Represented by Leye. The lateral position on the outside of the right eye (outside of the eye) and the lateral position of the inside of the right eye (on the inside of the eye) are straight lines LE and L.
F is the width of the right eye and the distance between the straight lines LE and LF is WReye
It is represented by Similarly, the lateral position of the outer side of the left eye (outside the outer corner of the eye) and the lateral position of the inner side of the left eye (the inner corner of the eye) are straight lines LG.
And the horizontal width of the left eye is the distance W between the straight lines LG and LH.
Represented by Leye. The distance between the right eye and the left eye is represented by the distance DR-L between the center lines of the straight lines LE and LF and the center lines of the straight lines LG and LH.

The control unit 11 controls the individual values P described above for the extracted eye image, that is, the height VReye of the right eye, the height HReye of the right eye, the height VLeye of the left eye, the height HLeye of the left eye, and the width of the right eye. WReye, left eye width WLeye, distance D between right and left eyes
Ask for RL.

The individual value P thus obtained has individual differences. Therefore, the obtained individual value P and the control memory 1
Reference value Q (VKre, VKle, HKr preset to 9)
e, HKle, WKre, WKle, DKR-L) is calculated as a characteristic value R as shown in FIG. 6 (step S6). The reference value Q is, as described above, the average value of the heights, the vertical widths, the horizontal widths, and the intervals between the eyes of the faces of a large number of people for each of a plurality of age groups (grouped in units of 10 years). It is obtained and preset in the control memory 19. In FIG. 3 (A), 30
Reference face of an average Japanese adult man in his teens, Fig. 3 (B)
The reference face of an average Japanese child male in his teens is illustrated.

Next, preset extraction reference values S1 to S
7, it is determined whether or not each feature value R satisfies the equations 1 to 7, and the feature value R satisfying the formula is exaggerated as a feature value R ′.
(Step S7).

[0023]

[Formula 1] ΔVre / VKre ≧ S1

[Formula 2] ΔVle / VKle ≧ S2

[Formula 3] ΔHre / VKre ≧ S3

[Formula 4] ΔHle / HKle ≧ S4

[Formula 5] ΔWre / WKre ≧ S5

[Equation 6] ΔWle / WKle ≧ S6

[Equation 7] ΔDR-L / DKR-L ≧ S7

For the extracted exaggeration target feature value R ', the control unit 11 refers to an exaggeration rate T stored in advance in the control memory 19 as shown in FIG.
The values of the corrected position, width, etc. are obtained according to equation 14 (step S8).

[0025]

[Equation 8] VReye ′ = VReye + (t1 × ΔVre)

[Equation 9] VLeye '= VLeye + (t2 × ΔVle)

[Equation 10] HReye '= HReye + (t3 × ΔHre)

[Equation 11] HLeye '= HLeye + (t4 × ΔHle)

[Equation 12] WReye ′ = WReye + (t5 × ΔWre)

[Equation 13] WLeye ′ = WLeye + (t6 × ΔWle)

[Equation 14] DR-L '= VR-L + (t7 × ΔDR-L)

Next, according to the numerical values obtained by the formulas 8 to 14, the positions and sizes of the right and left eyes which are determined to have the exaggeration target feature value R ′ are determined for the face image stored in the image memory 15. Adjustment (movement and enlargement or reduction)
(Step S9). The control unit 11 displays the position-adjusted image on the display unit 21 (step S10). If there is a print instruction from the key input unit 17,
Print the modified face image. For example, the positions of the eyes of the person in FIG. 4A are slightly displaced from the positions of the eyes indicated by the reference value of the reference face shown in FIG. Therefore, in order to exaggerate this point, the figure of the face corrected by lowering the position of the eyes is shown in FIG.
Shown in FIG. 5 shows a face with both eyes lowered and the left eye reduced in the same manner. Through the above processing, a series of processing from the input of the face image to the exaggeration of the features is completed.

The above extraction reference values S1 to S7 and the exaggeration rate T
(T1 to t7) is obtained by experiments or the like so that an optimal feature-enhanced image can be obtained.

As described above, according to this embodiment, feature extraction and exaggeration are realized by a simple operation of setting simple name coefficients, moving a graphic, and enlarging (reducing) it. Therefore, it can be widely applied to electronic devices such as portable devices having limited hardware and software.

In the above description, the case where the figure of the eye, which is the most characteristic part of the human face, is corrected has been mainly described, but other parts such as nose, mouth, eyebrows, ears, etc. May be corrected by the same method. Further, in the above description, an example of moving and enlarging (or reducing) a component in order to exaggerate the characteristics has been shown, but for example, for the eyes, eyebrows, etc., each element may be rotated. in this case,
For example, the inclination of the line connecting the inner corner of the eye and the outer corner of the eye with respect to the horizontal line is obtained, and when the ratio between the inclination and the reference value of the inclination exceeds a predetermined extraction reference value, the figure is rotated to exaggerate the feature.

The layout of the face parts is determined by gender, age,
It depends on race and so on. For example, in the standard face of a Japanese male child shown in FIG. 3B, the eye height is lower than that of an adult. Therefore, the reference value Q shown in FIG. 6 may be prepared on the control memory 19 for each of these types.
In this case, when emphasizing the features, the type (sex, age, race) of the portrait to be created is input from the key input unit 17, and the corresponding reference value is read from the control memory 19 and used.

In the above embodiment, the numbers 1 to 1
Although the feature is emphasized only for the feature satisfying the equation 7, all the features may be corrected (corrected) according to the equations 8 to 14.

In the above embodiment, a face image is input by the image input device and the input image is corrected to emphasize the features. For example, a memory stores a plurality of parts of a plurality of face portions. The face image formed by selecting and combining arbitrary parts may be stored in the image memory 15 by the key operation of the key input unit 17.

The present invention is applicable not only to face images but also to the case of creating an image in which the features of an arbitrary tangible object are emphasized. In this case, the control memory may be stored in advance with reference values and the like regarding the positions and the like of the parts constituting the tangible object.

[0034]

According to the present invention, it is possible to acquire an image in which the features of a person's face are emphasized with a simple configuration and processing.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a face image creating apparatus according to an embodiment of the present invention.

FIG. 2 is a flowchart for explaining the operation of the face image creating apparatus shown in FIG.

FIG. 3 (A) shows a reference face of an average Japanese adult man in his thirties, and (B) shows a reference face of an average Japanese child man in his / her thirties.

FIG. 4A is a diagram for explaining values that specify the position and size of a face image and eyes. (B) is an example of a diagram in which the characteristic portion of the face image of (A) is emphasized.

5 is an example of a diagram emphasizing a characteristic portion of the face image of FIG.

FIG. 6 is a diagram showing a relationship among the obtained individual value P, reference value Q, and characteristic value R.

FIG. 7 is a diagram showing a relationship between an exaggerated target feature value R ′ and an exaggerated rate T.

[Explanation of symbols]

11 ... Control unit, 13 ... Image input device, 15 ... Image memory, 17 ... Key input unit, 19 ... Control memory, 21 ...
・ Display, 23 ... Printing

Claims (7)

[Claims] 1. A face image storing means for storing a face image, a feature measuring means for measuring a feature of a predetermined part of a face image stored in the face image storing means, and a reference face feature. The reference value storage means stores the reference value in advance for each part, the exaggeration rate designating means stores the exaggeration rate for each feature item of the face, and the feature value and the reference value storage means measured by the feature measuring means. A characteristic value is obtained by comparing the stored reference value for each part, the characteristic value is corrected by the exaggeration rate set in the exaggeration rate designating means, and the image is corrected based on the correction value. A face image creating apparatus comprising: an image correcting unit. 2. The face image storage means comprises at least one of a face image creation means for creating a face image and a face image shooting means, and a storage means for storing a face image supplied from the one. The face image creating apparatus according to claim 1. 3. The face according to claim 1 or 2, wherein the feature measuring means includes an extracting means for extracting a component forming a face from the face image stored in the face image storing means. Image creation device. 4. The feature measuring means measures the position and size of a predetermined component included in the face image, and the reference value storage means stores the reference value of the position and size of the component. The face image creation device according to claim 1, 2 or 3. 5. The face image creating apparatus according to claim 4, wherein the image correcting means corrects the position and size of a predetermined part included in the face image based on the correction value. 6. The face image creating apparatus according to claim 1, further comprising an output unit that outputs the image corrected by the image correcting unit. 7. An image storage means for storing an image of an object composed of a plurality of parts, a measuring means for measuring at least one of an arrangement position and a size of the part in the image, and an arrangement position of the object part. And a reference value storage means for storing at least one reference value of the size, the reference value stored in the reference value storage means and the value measured by the measuring means are compared, and according to the comparison result, in the image An image generation apparatus comprising: a correction unit that corrects at least one of the position and the shape of the component.