JPH10240919A - Image forming device, its method and image forming program storage medium - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prepare a plurality of kinds of images which are different in the image kinds of picture style, facial expression, etc., based on single image data. SOLUTION: A face part library 11 consists of image libraries 11a to 11g of respective facial parts such as eyes, noses, mouths, etc. One image library stores a plurality of image groups of the respective facial parts of different image elements concerning each of image kinds i=1 to n. An eye image library 11a stores an image group consisting of a plurality of images of eyes which are different in the image elements of inclination and roundness. These image elements are also the measuring items of a feature value extracted from inputted image data. A rule library 12 consists of a selecting rule library 12a, a deforming rule library 12b and an arranging rule library 12c. The libraries 12a to 12c store a rule group consisting of a plurality of rules of each facial part concerning each of the image kinds i=1 to n.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image creating apparatus for creating an image corresponding to a preselected type based on input image data.

[0002]

2. Description of the Related Art In recent years, portraits have been frequently used not only in mass media such as newspapers and magazines, but also in OA equipment such as icon display of personal computers and insertion into documents created by word processors.

However, in order to draw a portrait, it is necessary to have an observing ability to extract a characteristic part of the face, an expressive power to exaggerate and reproduce the characteristic part, and the like. It's not easy. Therefore, there is an increasing demand for a device that automatically creates a portrait based on an arbitrary input image.

Therefore, conventionally, feature values of face parts such as eyes, nose, mouth, eyebrows and ears in an input face image are extracted, and a face component stored in advance is selected based on the extracted feature values. Alternatively, a technique for creating a portrait by deforming and arranging a portrait has been proposed. Such a technique can also be applied to the case of creating an image other than a portrait composed of a single or a plurality of image components, for example, an image of a crop, an industrial product, an animal, a landscape, or the like.

[0005]

However, in the conventional technology for automatically creating an image of a portrait or the like, the selection and deformation of an image part based on the feature amount of the image part extracted from the input image is performed in a single manner. It was done. For this reason, for example, it is not possible to create a portrait in a plurality of styles having different styles such as styles and expressions based on a single input face image, and to create a plurality of portraits having different tastes for the same person. I couldn't.

SUMMARY OF THE INVENTION It is an object of the present invention to store a plurality of pieces of image part information such as the shape and arrangement position of an image part for each of a plurality of types having different characteristic amount tendencies in accordance with the characteristic amount. By selecting the image part information based on the feature amount of the image part extracted from the input image data and the selected and input type and creating an image, the style and expression based on the single input image data It is an object of the present invention to provide an image creating apparatus capable of creating a plurality of types of images having different types such as the above.

[0007]

According to the first, sixth and eleventh aspects of the present invention, a plurality of pieces of image component information having different feature amounts are stored for each of a plurality of image types having different feature amount trends. The input of image data and the selection input of any one of a plurality of image types are received, and the image component information is stored in the storage unit based on the feature amount of the image component extracted from the input image data and the image type selected and input. Is selected to create an image. Therefore, according to the first, sixth and eleventh aspects of the present invention, an image based on the input image data is created based on the image component information corresponding to the selected and input image type, and the image style and the style are created from the single image data. A plurality of types of images having different image types such as facial expressions are created.

[0008] The invention described in claims 2, 7 and 12 is:
The image part information includes an image part selection rule.

Therefore, according to the second, seventh and twelfth aspects of the present invention, image components are selected based on different selection rules for each image type, and the image components are finely selected according to the image type.

[0010] The invention described in claims 3, 8 and 13 provides:
The image data is image data captured by an image capturing unit.

Therefore, according to the third, eighth and thirteenth aspects, an image corresponding to the selected image type is created based on an arbitrary image picked up by the image pickup means. The invention described in claims 4, 9 and 14 is characterized in that the image part information is face part information and a portrait is created based on the input face image data.

Therefore, according to the present invention, a portrait based on the input face image data is created based on the face part information corresponding to the image type selected and input, and a single face is created. A plurality of portraits having different image types such as styles and expressions are created from the image data.

[0015] The inventions described in claims 5, 10 and 15 are characterized in that the plurality of image types are classified according to style, expression, age or gender.

Therefore, in the inventions set forth in claims 5, 10 and 15, a plurality of portraits having different styles, expressions, ages or genders are created from a single face image data.

[0015]

FIG. 1 is a block diagram showing a configuration of an image forming apparatus according to an embodiment of the present invention. The image creation device 1 creates a portrait in which any one of a plurality of image types such as a style and a facial expression is specified based on the feature amount of the face part extracted from the input face image data. What are facial parts?
Eyes, nose, mouth, eyebrows, ears, contours and hair. In addition, the style of painting refers to the manner of exaggeration and deformation of each unified face part, which differs from painter to painter, and that even in the same painter, a cartoon character style, a handsome or beautiful woman style, or an accurate portrait style It depends on the style. What is an expression?
It is a state of the face that expresses emotions and sorrows.

The image creating apparatus 1 includes a control means 2 for selecting, deforming and arranging each face part as an image part to create a portrait, a storage means 3 for storing a plurality of pieces of face part information, a camera for taking in image data, and the like. Image input means 4, feature amount extracting means 5 for extracting feature amounts of face parts included in image data,
It is composed of a type input unit 6 for receiving a selection input of an image type such as a style or a facial expression, and an image output unit 7 such as a printer for outputting a created image.

The control means 2 controls the image input means 4, the feature quantity extraction means 5, the type input means 6 and the image output means 7 in a centralized manner. The control means 2 reads out a selection rule, a deformation rule, and an arrangement rule corresponding to the input image type from the storage means 3, and reads a face part from the storage means 3 according to the read selection rule. It includes a part deforming means 9 for deforming a face part according to a deformation rule and a part arranging means 10 for arranging a deformed face part according to an arrangement rule.

The storage means 3 selects a face part and a face part,
Face part information including rules for deformation and arrangement is stored. For this reason, the storage unit 3 stores the face part library 11 in which a plurality of images are classified and stored for each image type for each face part, and the rule group used when selecting, deforming, and arranging the face part. And a rule library 12 stored by classifying each image type.

As shown in FIG. 2, the face part library 11 includes image libraries 11a to 11g of face parts such as eyes, nose, mouth, eyebrows, ears, contours, and hair. One image library stores a plurality of image groups of face parts having different image elements for each of image types i = 1 to n. For example, the eye image library 11a stores, for each image type, an image group including a plurality of eye images having different inclination and roundness image elements. This image element is also a measurement item of the feature amount extracted from the input image data.

As shown in FIG. 3, the rule library 12 includes a selection rule library 12a, a transformation rule library 12b, and an arrangement rule library 12c. The libraries 12a to 12c store a rule group including a plurality of rules for each face part for each of the image types i = 1 to n. For example, the selection rule library 12a
Is composed of a selection rule group for each image type. One selection rule group includes, for example, a selection rule for each of the image elements that specify each image in each of the image libraries 11a to 11g of the face part library 11, such as a rule for the inclination of the eyes and a rule for the roundness. Become.

Each rule can be a fuzzy inference membership function and a fuzzy rule. For example, with respect to the selection rule, the range in which the measurement result of the feature amount of each image element is included in the membership function is set as the antecedent label of the fuzzy rule, and each image is output as the consequent output of the fuzzy rule. Also, each rule can be configured by a table.

The image input means 4 is constituted by a camera for picking up a face, but may be constituted by a scanner for reading an image of a face photograph. The feature amount extraction means 5
The image processing is performed on the face image data input from the image input means 4, the position of the face part is specified in the face image data after the image processing, and the feature amount of the face part is extracted. For example, with respect to the eyes, measured values of inclination, roundness (aspect ratio) and size are extracted as feature amounts. The type input means 6 is constituted by a keyboard, a mouse, or the like, and receives a selection input of an image type such as style, facial expression, age, and gender. The image output unit 7 is a printer that outputs a synthesized image on a sheet.

FIG. 4 is a flowchart showing an image creation processing procedure in the image creation apparatus. Control means 2
Receives the selection input of the image type by the type input means 6 (s1), and when the image type is selected and input, captures the face image by the image input means 4 (s2). Next, the control unit 2 performs predetermined image processing on the face image data captured by the image input unit 4 (s3), specifies a face part in the face image data after the face image processing, and extracts the feature amount thereof ( s
4).

Thereafter, the control means 2 selects the selection rule library 12a of the storage means 3 based on the input image type.
From the selection of the face part image is read from (s
5) A face part image is selected from one of the image part libraries 11 based on the read selection rule and the extracted feature amount (s6). Further, based on the input image type, the transformation rule library 12b
From the face part image is read (s
7) The face part image is deformed based on the read deformation rule and the extracted feature amount (s8), and based on the input image type, an arrangement rule relating to the arrangement position of the face part image is read from the arrangement rule library 12c. (S9), the arrangement position of the face part image is determined based on the read arrangement rule and the extracted feature amount (s10).

The control means 2 executes the processing of s4 to s10 for each of the face parts (s11). When the selection, deformation, and determination of the arrangement position of the face part images are completed for all the face parts, the selected and deformed face part images are arranged at the determined arrangement positions, and the face images are synthesized (s1).
2) Output the synthesized face image via the image output means 7 (s13).

The control means 2 can be constituted by a microcomputer, and the storage means 3 can be constituted by a hard disk, for example. Control means 2
The processing contents described above and the storage contents of the storage means 3 can be externally supplied via a storage medium.

FIG. 5 is a diagram specifically showing processing relating to selection, deformation, and arrangement position determination of a face part image in the image creating apparatus. For example, in the case of selecting, deforming, and arranging the position of an eye image as a face part by the processing of s4 to s10 illustrated in FIG. The angle θ between the center line and the horizontal line, the eye width x, the eye height y, the distance d, and the distance h from the center line of the eye to the chin are measured (FIG. 5).
(A)).

Next, a selection rule group to be used is read out based on the type i selected and input in advance, and the angle θ and x / By applying each value of y, a label in a range including the measured values of the inclination and roundness of the eyes is determined (FIG. 5B). Further, using the labels determined for the inclination and roundness of the eyes, the corresponding eye images are selected from the group of eye images of the image type selected and input in the eye parts library 11a (FIG. 5).
(C)).

Thereafter, a group of deformation rules to be used is read out based on the type i previously selected and inputted, and the rule of the eye size included in the group of deformation rules included in the group of the eye width x or the eye height y is included. The values are applied to determine the magnification or reduction of the eye image. Further, a group of arrangement rules to be used is read out based on the type i selected and inputted in advance, and the eye arrangement rule included in the arrangement rule group is applied with the eye interval d and the distance h from the center line of the eye to the chin. Thus, the positions of the eyes within the outline of the face are determined.

The same processing as that described above is executed for other face parts, and all face parts are selected, deformed, and the arrangement positions are determined. However, the deformation processing is executed only for the face outline, eyes and mouth, and the deformation processing for the other face parts is not executed. In addition, about eyes and mouth,
By storing images having different sizes in the face part library 11, the images can be included in the selection processing.

In this way, the image of the face part and the rules relating to the selection, deformation and arrangement of the face part are stored for each image type, and a selection input of a desired image type is accepted, and the selected image type is input. The image of the corresponding facial part can be selected, deformed, and arranged according to a rule corresponding to the image type, and a portrait of the selected image type can be created. For example, in the case where the expression of “laugh”, “cry”, or “anger” can be selected as the image type, when the image data shown in FIG.
The portraits shown in FIGS. 6B to 6D are created according to the selection of the image type.

Further, by allowing the style of each painter and the style of the same painter to be selected as the image type, when the face image data shown in FIG. 7A is input, FIG. Caricature of the beauty of painter A shown in Fig. 7,
7C is a cartoon character-like caricature of painter A, FIG. 7D is an animal-like caricature of painter A, or FIG.
One of the realistic portraits of painter B shown in (E) is selectively created. Therefore, it is possible to selectively create a plurality of portraits having different styles and the like for the same person, and to repeatedly create a portrait by selecting a style different from the style created last time by the same person. The frequency of use and the operation efficiency are improved.

Further, as shown in FIGS. 8A and 8B, the face parts library 11 stores images replaced by animals such as horses and cats, and stores the images in the rule library 12.
First, select an image according to the feature amount extracted from the image data,
By storing the transformation and arrangement rules for each animal, a portrait that is synthesized with the animal selected as the image type can be created, as shown in FIGS. 8C and 8D.

Further, images different for each age and gender are stored as image types in the face part library 11, and images corresponding to features extracted from the image data are selected, deformed and arranged in the rule library 12. By storing the rules for each age and gender, a caricature corresponding to the age and gender input as the image type can be created.

In the above-described embodiment, an example of an image creating apparatus that stores face parts for creating a portrait of a human and selects face parts as appropriate based on feature amounts extracted from input image data. However, the present invention is not limited to creating human portraits, for example, agricultural products and industrial products,
Alternatively, the present invention can be applied to an apparatus for creating an image of an animal, a landscape, or the like. For example, in an image creating apparatus for creating an apple drawing as a crop, a plurality of pieces of image part information are stored as parts, for example, for each part such as the shape of an apple body or the shape of a core, and image data of an apple as a target object is stored. Is input, a feature quantity is extracted from this image data for each part such as the shape of the apple body and the shape of the core (a core shape bent to the right or a core shape bent to the left), The image parts information of each part is appropriately selected based on the extracted feature amounts, and an apple image is created. As described above, the present invention stores a plurality of parts of each part in advance with respect to an object, and when image data of the object is input, determines parts of each part based on a feature amount extracted from the image data. Select as appropriate and create an image of the thing.

[0036]

According to the first, sixth and eleventh aspects of the present invention, an image based on input image data is created by image component information corresponding to an image type selected and input, thereby achieving a single image. A plurality of types of images having different image types such as styles and expressions can be created from the image data.

According to the second, seventh and twelfth aspects of the present invention, by selecting an image part based on a different selection rule for each image type, it is possible to select an image part finely according to the image type. Thus, an image having high uniqueness can be created for each image type.

According to the third, eighth, and thirteenth aspects of the present invention, an external device for inputting image data, such as an image reading device, becomes unnecessary by providing an image pickup means for picking up an image. An image corresponding to the image type selected based on the image can be created.

According to the fourth, ninth and fourteenth aspects of the present invention, it is possible to create a portrait based on the input face image data based on the face part information corresponding to the selected and input image type. , A plurality of portraits having different image types such as styles and expressions can be created.

According to the fifth, tenth, and fifteenth aspects, a plurality of portraits having different styles, expressions, ages, or genders can be created from a single face image data.

[Brief description of the drawings]

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

FIG. 2 is a diagram showing storage contents of a face part library constituting a storage unit of the image creating apparatus.

FIG. 3 is a diagram showing storage contents of a rule library constituting a storage unit of the image creating apparatus.

FIG. 4 is a flowchart illustrating an image creation processing procedure in the image creation apparatus.

FIG. 5 is a diagram illustrating selection of a face part image in the image creating apparatus;
It is a figure which shows the process regarding a deformation | transformation and arrangement position determination concretely.

FIG. 6 is a diagram illustrating a creation state of a portrait in a case where expressions such as “laugh”, “cry”, and “anger” can be selected as image types in the image creation device.

FIG. 7 is a diagram showing a creation state of a portrait for each image type for the same person in a case where the style of each painter and the difference in style of the same artist can be selected as the image type as the image type in the image creating apparatus. is there.

FIG. 8 is a diagram showing a storage state of a face part library and a rule library and a creation state of a portrait in the image creating apparatus when an animal can be selected as an image type.

[Explanation of symbols]

 Reference Signs List 1-Image creation device 2-Control unit 3-Storage unit 4-Image input unit 5-Feature amount extraction unit 6-Type input unit 7-Image output unit 8-Part information selection unit 9-Part transformation unit 10-Part arrangement unit 11-Parts library 12-Rules library

Claims (15)

[Claims] A storage unit for storing a plurality of pieces of image component information having different feature amounts for each of a plurality of image types having different feature amount trends; an image data inputting unit for receiving input of image data; A type selection unit that receives any one of the selection inputs, and an image from the storage unit based on the feature amount of the image component extracted from the image data input by the image data input unit and the image type selected and input by the type selection unit. An image creation apparatus, comprising: control means for creating an image by selecting component information. 2. The image creating apparatus according to claim 1, wherein said image part information includes an image part selection rule. 3. The apparatus according to claim 1, wherein said image data input means includes an image pickup means for picking up an image. 4. A caricature based on face image data input from an image data input means, wherein said storage means is means for storing face part information.
An image creating apparatus according to claim 1. 5. The image creating apparatus according to claim 4, wherein said plurality of image types are classified by style of painting, facial expression, age, or gender. 6. A plurality of pieces of image component information having different feature amounts are stored for each of a plurality of image types having different feature amount trends, and image data is input and any one of the plurality of image types is selected and input. And receiving the selected image component information from the storage unit based on the feature amount of the image component extracted from the input image data and the selected and input image type to generate an image. 7. The image creating method according to claim 1, wherein the image part information includes a rule for selecting an image part. 8. The image creating method according to claim 6, wherein said image data is image data captured by an image capturing means. 9. The image creating method according to claim 6, wherein the image part information is face part information, and a portrait is created based on the input face image data. 10. The method according to claim 9, wherein the plurality of image types are classified according to style of painting, facial expression, age, or gender. 11. An image data input process for receiving an input of image data, a type selection process for receiving a selection input of one of a plurality of image types, and a process for selecting an image component extracted from the image data input by the image data input means. Based on the feature amount and the image type selected and input by the type selection unit, the image component information is stored from a storage unit storing a plurality of image component information having different feature amounts for each of the plurality of image types having different feature amount trends. An image creation program storage medium characterized by storing a program comprising: an image creation process for selecting and creating an image. 12. The storage medium according to claim 11, wherein said image part information includes a rule for selecting an image part. 13. An image creation program storage medium according to claim 11, wherein said image data input processing inputs an image taken by an image pickup means. 14. A caricature based on face image data input in image data input processing, wherein said storage means is means for storing face part information.
14. The image creation program storage medium according to 2 or 13. 15. The storage medium according to claim 14, wherein said plurality of image types are classified according to style, expression, age, or gender.