JP2010170219A - Apparatus, method and program for processing image, and printer - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve such the problem that since the aspect ratio of a face is also greatly changed in deforming an image including a person, a bad-looking image is produced. <P>SOLUTION: An image processor includes: a region setting part for setting a compression region and an enlargement region in an object image including a face image; an image deformation part for enlarging the enlargement region in a specific direction by a prescribed enlargement rate; and a face deformation part for, when at least a portion of the face image is included in the enlargement region, deforming the face image by compression quantity determined according to the enlargement rate so that the face image included in the enlargement region is compressed in the specific direction. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus, an image processing method, an image processing program, and a printing apparatus.

  An image processing technique for deforming an image for a digital image is known (see Patent Document 1). In Patent Document 1, a partial area (an area representing a cheek image) on a face image is set as a correction area, the correction area is divided into a plurality of small areas according to a predetermined pattern, and set for each small area. Image processing for deforming the shape of a face by enlarging or reducing the image at a specified magnification is disclosed.

JP 2004-318204 A

  In addition, when a person including a face is captured in an image, the user may desire to obtain an image in which the figure of the person is transformed into a favorite figure (for example, a slim figure). As a deformation process that meets such demands, a specific area is set in an image and uniform compression processing is performed on the specific area, and at the same time, uniform enlargement processing is performed on an area outside the specific area. There is. However, when the uniform deformation (compression and enlargement) processing is performed, the face of the person included in the specific area or outside the specific area is also affected by the deformation, and as a result, an image in which the aspect ratio of the face is greatly changed is obtained. End up. In this way, an image of a person whose face aspect ratio has changed significantly (for example, an image in which the face is extremely long) gives the user a sense of discomfort.

  The present invention has been made in view of the above problems, and provides an image processing apparatus, an image processing method, an image processing program, and a printing apparatus capable of easily obtaining a better-looking deformation result for an image including a person. The purpose is to do.

  In order to achieve the above object, the image processing apparatus according to the present invention includes a region setting unit that sets a compression region and an enlargement region in a target image in a target image including a face image, and a predetermined enlargement ratio. When an image deforming unit that enlarges an area in a specific direction and at least a part of the face image are included in the enlarged area, the face image included in the enlarged area is compressed in the specific direction. And a face deformation unit that deforms the face image by a compression amount determined according to the enlargement ratio. According to the present invention, the face deforming unit deforms the face image included in the enlarged area so as to be compressed in a specific direction by the compression amount determined according to the enlargement ratio of the enlarged area. Therefore, even if the enlargement area is enlarged by the image deformation unit, the aspect ratio of the face does not collapse greatly as a result. Therefore, an image that does not give the user a sense of incongruity can be obtained. Note that the order of processing by the image deformation unit and processing by the face deformation unit may be first.

  The image deformation unit compresses the compression region in the specific direction at a predetermined compression rate, and the face deformation unit is configured to compress the compression region when at least a part of the face image is included in the compression region. The face image may be deformed by an enlargement amount determined according to the compression rate so that the face image included in the image is enlarged in the specific direction. According to this configuration, in addition to the effect that the face image included in the enlarged region is compressed so as to cancel the enlargement effect in the enlarged region to some extent, the face image included in the compressed region cancels the compression effect in the compressed region to some extent. There is also an effect that it is enlarged. For a face image that exists at a position straddling the compression area and the enlargement area, the range included in the compression area is expanded in a specific direction, and the range included in the expansion area is compressed in a specific direction.

  The face deformation unit may perform the deformation of the face image when an angle formed by the vertical direction of the face image and the specific direction is larger than a predetermined reference angle. According to this configuration, the face image whose vertical direction is substantially parallel to the specific direction is excluded from the deformation target, and the enlarged image (compressed region) of the face image whose vertical direction stands to some extent (substantially perpendicular) with respect to the specific direction. ) In accordance with the enlargement ratio (compression ratio).

  The face deforming unit may perform deformation on a face image excluding face images at least partially overlapping each other when a plurality of face images exist in the target image. According to this configuration, it is possible to prevent the inconvenience that the images collapse on the contrary by individually deforming the face images that overlap each other.

  The face deforming unit may determine the compression amount based on a predetermined ratio of the numerical values indicated by the enlargement ratio. For example, if the enlargement ratio is 20%, a numerical value that is a percentage of the numerical value of 20% is used as the compression amount. Thus, instead of applying a compression amount that completely cancels the enlargement effect on the enlargement region to the face image, the compression amount of the face image is determined based on a numerical value of a predetermined ratio of the numerical values indicated by the enlargement rate. Thus, after both the processing by the image deforming unit and the processing by the face deforming unit are finished, an image in which the balance between the face and the part other than the face in the enlarged region is optimal can be obtained.

  So far, the technical idea of the present invention has been described as an image processing apparatus. However, the invention of the image processing method including each process corresponding to each means included in the above-described image processing apparatus and the above-described image processing apparatus are included. It is also possible to grasp the invention of an image processing program that causes a computer to execute each function corresponding to each means. Further, the image processing device, the image processing method, and the image processing program may be specifically realized by hardware such as a personal computer or a server, or a digital still camera or scanner as an image input device, or It can be realized by various products such as a printer (printing device) as an image output device, a projector, and a photo viewer.

FIG. 2 is an explanatory diagram schematically illustrating a configuration of a printer as an image processing apparatus. It is the flowchart which showed an example of the image correction process. It is explanatory drawing which showed an example of UI. It is explanatory drawing which showed a mode that the face area | region was detected from the target image. It is explanatory drawing which showed a mode that the organ area | region was detected from the face area | region. It is the flowchart which showed the detail of the face deformation process. It is explanatory drawing which showed a mode that the deformation | transformation area | region was set with respect to the face area | region. It is explanatory drawing which showed an example of the division | segmentation method to a small area | region of a deformation | transformation area | region. It is the figure which showed an example of the movement amount for every division | segmentation point. It is the figure which showed an example of a mode that the image in a deformation | transformation area | region is deform | transformed by face deformation processing. It is explanatory drawing which shows the deformation | transformation process of a small area image notionally. It is explanatory drawing which shows the concept of the deformation | transformation processing method of the image in a triangular area | region. It is the figure which showed an example of a mode that each area | region of a target image was deform | transformed by a one-way deformation | transformation process. It is the flowchart which showed the detail of the unidirectional deformation process. It is explanatory drawing which showed the one-way deformation | transformation process typically. It is the figure which showed a mode that the face area | region overlapped in the object area | region. It is the figure which showed the other example of the movement amount for every division | segmentation point. It is the figure which showed the other example of a mode that the image in a deformation | transformation area | region is deform | transformed by face deformation processing. It is the figure which showed a mode that the deformation | transformation area | region straddled the compression area | region and the expansion area | region.

The embodiments of the present invention will be described in the following order.
1. 1. Schematic configuration of image processing apparatus 2. Image correction processing Summary

1. Schematic Configuration of Image Processing Device FIG. 1 is an explanatory diagram schematically showing the configuration of a printer 100 as an example of an image processing device according to the present invention. The printer 100 is a color inkjet printer that supports so-called direct printing, in which an image is printed based on image data acquired from a recording medium such as a memory card MC. The printer 100 includes an internal memory 120, a CPU 110, an operation unit 140, a display unit 150, a printer engine 160, a card interface (card I / F) 170, and a card slot 172.

  The internal memory 120 includes a ROM and a RAM, and includes an image correction processing unit 200, a display processing unit 310, and a print processing unit 320 as functional blocks. The image correction processing unit 200 is a computer program for executing image correction processing to be described later under a predetermined operating system. The image correction processing unit 200 includes a face area detection unit 210, a deformation direction setting unit 220, and a unidirectional deformation unit 230 as program modules. The unidirectional deformation unit 230 executes a unidirectional deformation process as a kind of image correction process by using a buffer area that is a temporary storage area provided in the RAM and a corresponding pixel number table 410. The unidirectional deformation unit 230 also serves as an area setting unit and an image deformation unit in the claims. Further, the image correction processing unit 200 includes a face deformation unit 240 as a program module. The face deforming unit 240 uses the dividing point arrangement pattern table 420 to perform face deforming processing as a kind of image correction processing. The functions of these units will be described later.

  The display processing unit 310 is a display driver that controls the display unit 150 to display processing menus, messages, images, and the like on the display unit 150. The print processing unit 320 generates print data that defines the ink amount for each pixel by performing predetermined color conversion processing and halftone processing on the image data, and controls the printer engine 160 based on the print data. This is a computer program for executing image printing. For example, image data representing an image after the image correction processing is executed by the image correction processing unit 200 corresponds to the image data to be processed by the color conversion processing and the halftone processing by the print processing unit 320. The CPU 110 implements the functions of these units by reading these programs from the internal memory 120 and executing them.

The operation unit 140 includes buttons and a touch panel, and accepts input such as instructions from the user. The display unit 150 is configured by a liquid crystal display, for example. The printer engine 160 is a printing mechanism that performs printing based on print data transmitted from the print processing unit 320. The card I / F 170 is an interface for exchanging data with the memory card MC inserted into the card slot 172. In addition to the card I / F 170, the printer 100 may include an interface for performing data communication with other devices (for example, a digital still camera or a personal computer). The above components are connected to each other via a bus.
The printer 100 can perform a face deformation process and a one-way deformation process on an image including a human image, thereby deforming the human image as a whole thinly or thickly, and at the same time, the balance of the person's face (face Aspect ratio) can be optimized.

2. Image Correction Process FIG. 2 is a flowchart showing the image correction process executed by the printer 100.
In step S (hereinafter, step notation is omitted) 100, the image correction processing unit 200 sets (acquires) a target image to be processed. For example, when the memory card MC is inserted into the card slot 172, the display processing unit 310 causes the display unit 150 to display a user interface (UI) including display of an image stored in the memory card MC. Then, the image correction processing unit 200 sets a target image according to the input from the UI.

  FIG. 3 shows an example of a UI displayed on the display unit 150. For example, the UI includes an image display field IA, two image switching buttons B1 and B2, a normal print button B3, a correction print button B4, and a cancel button B5. The user can set the target image by operating the image switching buttons B1 and B2 while selecting the target image while viewing the image display field IA, and pressing either the normal print button B3 or the corrected print button B4. In the example of FIG. 3, the image TI in which the persons P1 and P2 are captured is selected as the target image. In this state, when the user presses either the normal print button B3 or the corrected print button B4, image correction processing is performed. The unit 200 sets the image TI as a target image. The UI may be configured to display a list of a plurality of images in the memory card MC.

  When the user presses the correction print button B4, the image correction processing unit 200 performs face deformation processing and unidirectional deformation processing on the target image as described later. After the flowchart is completed, the printer 100 prints the image on which the correction process has been executed. However, when the user presses the normal print button B3, the printer 100 prints the target image as usual without performing the face deformation process and the one-way deformation process.

  In S200, the image correction processing unit 200 determines whether or not execution of “correction printing” is instructed by the user's operation on the UI button. If “correction printing” is instructed, the processing from S300 is performed. If “normal printing” is instructed, the flowchart ends. In the following, the description will be continued on the assumption that the user has pressed the correction print button B4 and instructed execution of “correction printing” in S100.

  In S300, the face area detection unit 210 reads image data representing the target image from the memory card MC to the internal memory 120 and detects the face area in the target image. The face area is an area including at least a part of the face image in the target image, and is an area assumed to include at least a predetermined facial organ (eyes, nose, mouth). The face area detection unit 210 analyzes image data representing the target image and detects a rectangular area that is assumed to include the face organ as a face area. The face area is detected using a known detection method such as a pattern matching method using a template (see Japanese Patent Application Laid-Open No. 2006-279460). The face area detection unit 210 can employ any technique for the pattern matching as long as it can detect the face area. For example, the face area detection unit 210 inputs various pieces of image information (for example, luminance information, edge amount, contrast, etc.) in units of rectangular areas (detection target areas) set in the target image, and the detection target area is the face. A face area may be detected by using a pre-learned neural network that outputs information indicating whether or not the area corresponds, or a face area for each detection target area using a support vector machine It may be determined whether or not.

  FIG. 4 is an explanatory diagram showing an example of a face area detection result in S300. In the example of FIG. 4, since the images of two persons P1 and P2 are included in the target image TI, face areas Fd (Fd1 and Fd2) corresponding to the face images of the persons P1 and P2 are detected. That is, when there are a plurality of face images in the target image, the face area detection unit 210 detects the face area Fd related to each face image. The face area Fd is a rectangular area that includes all the eyes, nose, and mouth images of the corresponding face. The face area detection unit 210 identifies the face area Fd based on the coordinates of the four vertices of the area. However, when the detection result of the face area Fd in the target image (information for specifying the position of the face area in the image) already exists as attached information in the image data representing the target image stored in the memory card MC. There is also. For example, when the face region Fd is already detected from the target image by the function of the digital still camera used for capturing the target image, and information indicating the detection result is recorded on the memory card MC together with the image data. . In such a case, the face area detection unit 210 does not need to detect the face area Fd from the target image, and specifies the face area Fd in the target image based on the attached information.

  In S400, the deformation direction setting unit 220 sets a deformation direction for the unidirectional deformation process. Hereinafter, the term “deformation direction” means a deformation direction for unidirectional deformation processing. The deformation direction corresponds to a specific direction in the claims. The deformation direction is either the horizontal direction or the vertical direction of the target image. In the present embodiment, the long side direction of the target image is treated as the horizontal direction, and the short side direction of the target image is treated as the vertical direction. The deformation direction setting unit 220 can set the deformation direction according to an external user input, or can set the deformation direction based on the analysis result of the target image.

  When the deformation direction is set according to a user input, the deformation direction setting unit 220 instructs the display processing unit 310 to execute a process of displaying a deformation direction setting UI, and the display processing unit 310 In response to the instruction, the display unit 150 displays a deformation direction setting UI. The user inputs whether to select “horizontal direction” or “vertical direction” as the deformation direction via the deformation direction setting UI. The deformation direction setting unit 220 sets “horizontal direction” or “vertical direction” selected by the user's input as the deformation direction. In addition, while visually recognizing the target image displayed on the display unit 150, the user basically determines the left-right direction (face width direction) of the face in the target image among the horizontal direction and the vertical direction of the target image. A direction with a small angle is selected as the deformation direction.

  When the deformation direction is set according to the analysis result of the target image, the deformation direction setting unit 220 sets either the horizontal direction or the vertical direction as the deformation direction according to the inclination of the face in the target image. For example, the deformation direction setting unit 220 detects a region including the right eye image (right eye region) and a region including the left eye (left eye region) in the face region Fd detected or specified by the face region detection unit 210 in S300. . The detection of the organ region (right eye region, left eye region) can be performed using a known detection method such as a pattern matching method using a template, as in the detection of the face region.

  FIG. 5 is an explanatory diagram showing an example of the detection result of the organ region. In the example of FIG. 5, the right eye area ER and the left eye area EL are detected in the face area Fd1. The deformation direction setting unit 220 can specify the detected right eye region ER and left eye region EL by the coordinates of the four vertices of each region. The deformation direction setting unit 220 sets a line segment L2 perpendicular to the line segment L1 connecting the center point CR of the right eye region ER and the center point CL of the left eye region EL in the target image TI (up and down direction of the face) The height direction is defined as a line segment, and the inclination of the line segment L2 is defined as the face inclination. For example, when the inclination of the line segment L2 with respect to the vertical direction of the target image TI is smaller than 45 °, the deformation direction setting unit 220 sets the deformation direction to “horizontal direction”. On the other hand, when the inclination of the line segment L2 with respect to the vertical direction of the target image TI is greater than 45 °, the deformation direction is set to “vertical direction”. When the inclination of the line segment L2 is 45 °, the deformation direction is set to a predetermined standard direction (for example, the horizontal direction).

  When the target image includes a plurality of faces, the deformation direction setting unit 220 may set the deformation direction according to a larger face inclination. Alternatively, when the target image includes a plurality of faces, the deformation direction may be set according to the tilt of the face with the smallest tilt with respect to the vertical or horizontal direction of the target image, or the tilt of the plurality of faces The deformation direction may be set according to the average. Hereinafter, the description will be continued assuming that the horizontal direction is set as the deformation direction.

  In S500, the face deforming unit 240 determines whether or not the tilt in the height direction of a certain face region Fd in the target image is a tilt that can be a target of the face deforming process described later. Specifically, it is determined whether or not the angle formed by the deformation direction set in S400 and the height direction of the face is larger than the reference angle. If the angle is larger than the reference angle (Yes), S600 (face deformation processing). If the angle is equal to or smaller than the reference angle (No), S600 is skipped and the process proceeds to S700. For example, 45 ° corresponds to the reference angle used here. As described above, in S400, a deformation direction that is basically determined as “Yes” in S500 is set in consideration of the inclination of the face in the target image, but there are a user's setting mistake and a plurality of faces. In some cases, for some faces, the height direction of the face is lying with respect to the deformation direction (the angle between the deformation direction and the height direction of the face is within 45 °). Therefore, it is necessary to perform the determination of S500.

In order to perform the determination of S500, the image correction processing unit 200 sets the direction of the organ region of the line segment L2 that defines the height direction of the face even when the deformation direction is set according to the user input in S400. Identification based on detection is performed for each face.
In S700, the face deforming unit 240 determines whether or not the determination in S500 for all the face areas Fd detected in the target image has been completed one by one, and the determination in S500 is completed for all the face areas Fd. If YES in step S800, the process advances to step S800. If not completed (NO), the process returns to step S500 and the process is repeated for the undetermined face area Fd.

As shown in FIG. 16, a plurality of face regions Fd detected in the target image TI may overlap each other. In this way, when face regions Fd that overlap each other are subjected to face deformation processing, the result of deformation of one face may adversely affect the other face, and the image may be broken. Therefore, in the present embodiment, when a plurality of face areas Fd are detected from the target image TI, the face deforming unit 240 performs face deformation processing on the face area Fd that partially overlaps the other face area Fd. Not targeted. That is, in S500, the face area Fd whose angle between the deformation direction and the face height direction is equal to or larger than the reference angle and does not overlap with the other face area Fd is determined as “Yes”.
In S600, the face deformation unit 240 performs face deformation processing on each face image in the target image.

FIG. 6 is a flowchart showing details of the face deformation process in S600.
In S610, the face deforming unit 240 sets a deformed area based on the face area Fd (the face area Fd to be determined in the latest S500). The deformation area means an area that includes the face area Fd in the target image and is a target of face deformation processing. The deformation area is a rectangular area that covers the entire face image, and the deformation area may be interpreted as a face image. In the above description, the face regions Fd that overlap each other are excluded from the target of the face deformation process, but each face that overlaps the deformed regions may be excluded from the target of the face deformation process.

  FIG. 7 is an explanatory diagram illustrating an example of a method for setting a deformation area. In FIG. 7, a solid-line rectangle TA indicates a deformation area TA set for the face area Fd. The reference line RL is a line that defines the height direction (vertical direction) of the face area Fd and indicates the center in the width direction (horizontal direction) of the face area Fd. The reference line RL is a straight line that passes through the center of gravity of the rectangular face area Fd and is parallel to the boundary line along the height direction of the face area Fd. It can be said that the reference line RL is a line substantially parallel to the line segment L2. Therefore, in the determination of S500, instead of examining the angle between the deformation direction and the line segment L2, the angle between the deformation direction and the reference line RL may be examined. The deformation area TA is set as an area obtained by extending the face area Fd in a direction parallel to the reference line RL (height direction) and a direction orthogonal to the reference line RL (width direction). Specifically, when the length in the height direction of the face region Fd1 is H1 and the size in the width direction is W1, the face region Fd is extended by k1 · H1 upward and k2 · H1 downward, A region extended by k3 · W1 to the left and right is set as the deformation region TA. k1, k2, and k3 are predetermined coefficients. When the deformation area TA is set in this way, the reference line RL, which is a straight line parallel to the contour line in the height direction of the face area Fd, becomes a straight line parallel to the contour line in the height direction of the deformation area TA. . The reference line RL is a straight line that divides the width of the deformation area TA in half.

As shown in FIG. 7, the deformation area TA is set as an area that generally includes an image from the jaw to the top of the head in the height direction and includes images of the left and right cheeks in the width direction. In other words, in the present embodiment, the above-described coefficients k1, k2, and k3 are set in advance through experiments so that the deformation area TA is an area that includes an image in such a range.
In S620, the face deforming unit 240 divides the deformation area set in S610 into a plurality of small areas.

  FIG. 8 is an explanatory diagram showing an example of a method of dividing the deformation area into small areas. FIG. 8 shows the deformation area TA. The face deformation unit 240 arranges a plurality of division points D in the deformation area TA and divides the deformation area TA into a plurality of small areas using a straight line connecting the division points D. The arrangement mode of the dividing points D (the number and position of the dividing points D) is defined by the dividing point arrangement pattern table 420. The face deforming unit 240 arranges the dividing points D with reference to the dividing point arrangement pattern table 420. In the example of FIG. 8, the dividing points D are arranged at the intersections of the horizontal dividing line Lh and the vertical dividing line Lv and at the intersections of the horizontal dividing line Lh and the vertical dividing line Lv and the outer frame of the deformation area TA. The horizontal dividing line Lh and the vertical dividing line Lv are reference lines for arranging the dividing point D in the deformation area TA. As shown in FIG. 8, in the arrangement of the dividing points D in the present embodiment, three horizontal dividing lines Lh orthogonal to the reference line RL and four vertical dividing lines Lv parallel to the reference line RL are set. The The three horizontal dividing lines Lh are referred to as Lh1, Lh2, and Lh3 in order from the bottom of the deformation area TA. The four vertical dividing lines Lv are referred to as Lv1, Lv2, Lv3, and Lv4 in order from the left of the deformation area TA.

  The horizontal dividing line Lh1 is arranged below the chin image in the deformation area TA, the horizontal dividing line Lh2 is arranged near the bottom of the eye image, and the horizontal dividing line Lh3 is near the top of the eye image or the forehead. Around the image. The vertical division lines Lv1 and Lv4 are arranged outside the cheek line image, and the vertical division lines Lv2 and Lv3 are arranged outside the corner image. The horizontal dividing line Lh and the vertical dividing line Lv are arranged in accordance with the size of the deformation area TA set in advance so that the positional relationship between the horizontal dividing line Lh and the vertical dividing line Lv and the image is the above-described positional relationship. It is executed according to the correspondence relationship.

  According to the arrangement of the horizontal dividing line Lh and the vertical dividing line Lv described above, the intersection of the horizontal dividing line Lh and the vertical dividing line Lv, and the intersection of the horizontal dividing line Lh and the vertical dividing line Lv and the outer frame of the deformation area TA In addition, the dividing point D is arranged. As shown in FIG. 8, the division points D located on the horizontal division line Lhi (i = 1, 2, 3) are called D0i, D1i, D2i, D3i, D4i, D5i in order from the left. For example, the dividing points D located on the horizontal dividing line Lh1 are called D01, D11, D21, D31, D41, D51. Similarly, the dividing points D located on the vertical dividing line Lvj (j = 1, 2, 3, 4) are called Dj0, Dj1, Dj2, Dj3 in order from the bottom. For example, the division points D located on the vertical division line Lv1 are called D10, D11, D12, and D13. The arrangement of the dividing points D in the present embodiment is symmetrical with respect to the reference line RL. The face deformation unit 240 divides the deformation area TA into a plurality of small areas by a straight line (horizontal division line Lh and vertical division line Lv) connecting the arranged division points D. In the example of FIG. 8, the deformation area TA is divided into 20 rectangular small areas.

  In S630, the face deformation unit 240 determines the movement amount for the predetermined division point D according to the compression rate or the enlargement rate used for the one-way deformation process. Here, in the unidirectional deformation process (S800) described below, the compression area is compressed at a predetermined compression rate and the expansion area is compressed at a predetermined expansion rate under the condition that the compression area and the expansion area are set in the target image. Expanding. The unidirectional deformation unit 230 sets the compression area and the enlargement area. Specifically, the unidirectional deformation unit 230 divides the target image by a dividing line perpendicular to the deformation direction (a dividing line different from the horizontal dividing line Lh and the vertical dividing line Lv), so that a compression region at a substantially central position. And an enlarged region positioned on the left and right of the compression region.

  There are various ways of dividing the compression area and the expansion area by the dividing line perpendicular to the deformation direction by the unidirectional deformation unit 230. For example, the compression area and the expansion area set in the internal memory 120 as a fixed value in advance. May be divided according to the area ratio, or may be divided according to the position of the dividing line designated on the target image by the user via the operation unit 140 and the display unit 150, or may be positioned at the center of the target image. An area including the entire deformation area may be set as a compression area, and areas on the left and right of the set compression area may be set as an enlargement area. In the following, simply referring to “compressed area” means a compressed area set in the target area for unidirectional deformation processing, and simply saying “enlarged area” means unidirectional deformation processing. Therefore, it means an enlarged area set in the target area.

  In the present embodiment, the unidirectional deformation unit 230 performs the setting of the compression region and the enlargement region in the target image as described above at least before the face deformation unit 240 starts the process of S630. In S630, the face deforming unit 240 assumes that the target image is divided into a compressed area and an enlarged area, and the deformed area set in S610 is included in either the compressed area or the enlarged area. If it is included in the compression area, the amount of movement is determined in accordance with the compression rate used in the one-way deformation process in the compression area. The amount of movement is determined according to the enlargement factor used in the one-way deformation process for the region. Hereinafter, when simply expressed as “compression rate”, it means the compression rate applied to the compression area during the one-way deformation process, and when simply expressed as “enlargement rate”, the one-way deformation process. It means the enlargement rate applied to the enlargement area.

  The compression rate and the enlargement rate may be stored in advance as fixed values in the internal memory 120 or the like, or numerical values input by the user via the operation unit 140 or the like. Alternatively, the printer 100 allows the user to input only one of the compression rate and the enlargement rate via the UI in order to prevent the size of the target image after the unidirectional deformation process from changing too much, and the input compression Depending on one value of the rate or the enlargement rate, a value of the compression rate or enlargement rate that is not input may be determined.

The face deforming unit 240 acquires the compression rate and enlargement rate stored in the internal memory 120 in advance as described above, or the compression rate and enlargement rate input by the user (or determined according to the user input). Can do.
Here, first, a case will be described in which the face deforming unit 240 determines that the deformation area is included in the compression area and acquires a value of “30%” as the compression rate applied to the compression area. In other words, the compression rate of 30% is a magnification for making the length in the deformation direction of the compression region before the unidirectional deformation process 0.7 times longer after the unidirectional deformation process.

  When the face deformation unit 240 determines that the deformation area is included in the compression area, the reference line for the predetermined division point D is enlarged so that at least a part of the face image applied to the deformation area is enlarged in the deformation direction. The amount of movement in the direction away from the RL is set according to the compression rate. In the present embodiment, the face deforming unit 240 has divided points D11, D12, D13, D21, D22, D23, D31, D32, D33, D41, which are present inside the frame of the deformed area TA among the divided points D. The amount of movement for D42 and D43 is determined. As shown in FIG. 8, the direction orthogonal to the reference line RL is called the H direction, and the direction parallel to the reference line RL is called the V direction. For the H direction, the rightward movement amount is represented as a positive value (plus), the leftward movement amount is represented as a negative value (minus), and for the V direction, the upward movement amount is represented. Expressed as a positive value (plus), and the amount of downward movement as a negative value (minus).

  Here, it can be said that the angle formed by the deformation direction and the H direction is smaller than the angle formed by the deformation direction and the V direction. Therefore, if a moving amount in a direction away from the reference line RL is set for a predetermined dividing point D based on the compression rate, and the dividing point D is moved according to the set moving amount, at least a part of the face image is deformed. It is also expanded in the direction. As an example, the face deformation unit 240 sets the movement amount to the minus side (left side) for the division points D11, D21, D12, D22, D13, and D23 on the left side of the reference line RL as the movement amount in the H direction. For the division points D31, D41, D32, D42, D33, and D43 on the right side of the reference line RL, the amount of movement to the plus side (right side) is set.

  Further, the face deformation unit 240 sets the movement amount to the plus side (upper side) for the dividing points D11, D21, D31, and D41 on the horizontal dividing line Lh1 as the moving amount in the V direction, and on the horizontal dividing line Lh3. For the division points D13, D23, D33, and D43, a moving amount to the minus side (downside) is set. In this way, if the movement amount is set for the predetermined division point D on the horizontal division line Lh1 and the predetermined division point D on the horizontal division line Lh3, and the division point D is moved according to the set movement amount, A part is also compressed at least in the direction perpendicular to the deformation direction.

  More specifically, when the face deformation unit 240 sets the movement amount of each division point D, the face deformation unit 240 first calculates the numerical value (30%) indicated by the compression rate in the deformation amount (enlargement amount) of the image in the deformation region in the H direction. ) And the amount of deformation (compression amount) in the V direction. As an example, the face deformation unit 240 assigns 70% (21%) of the numerical value (30%) indicated by the compression rate to the deformation amount (enlargement amount) in the H direction, and the above value is obtained from the numerical value (30%) indicated by the compression rate. The remainder (9%) obtained by subtracting the deformation amount (enlargement amount) in the H direction is assigned to the deformation amount (compression amount) in the V direction.

  The face deformation unit 240 further distributes the deformation amount assigned to the H direction and the V direction as a movement amount to each division point D. As an example, the face deforming unit 240 calculates a numerical value (10.5%) corresponding to 50% of the deformation amount (21%) assigned in the H direction to each dividing point D11, D12, D13, D21, D22, D23, D31. , D32, D33, D41, D42, D43 are set as movement amounts in the H direction (movement amounts away from the reference line RL), and are numerical values corresponding to 30% of the deformation amount (9%) assigned in the V direction ( 2.7%) is set as the movement amount of each dividing point D11, D21, D31, D41 on the horizontal dividing line Lh1 to the plus side in the V direction, and 70% of the deformation amount (9%) assigned in the V direction. Is set as the amount of movement of each division point D13, D23, D33, D43 on the horizontal division line Lh3 toward the minus side in the V direction. As a result, for the division point D11, for example, a numerical value of 10.5% is set as the moving amount in the H direction minus side, and a numerical value of 2.7% is set as the moving amount in the V direction plus side. For the division point D43, a numerical value of 10.5% is set as the movement amount in the H direction plus side, and a numerical value of 6.3% is set as the movement amount in the V direction minus side. The amount of movement of the dividing point D set in this way in the H direction and V direction means a ratio to the length (number of pixels) of the deformation area TA in the H direction and V direction.

  As described above, the ratio (distribution ratio) when the numerical value indicated by the compression ratio is distributed to the deformation amount in the H direction and the V direction, the deformation amount in the H direction, and the deformation amount in the V direction are distributed to each division point D. The ratio when doing this is not limited. Further, the face deforming unit 240 may add further changes for each division point D with respect to the movement amount of the division point D in the H direction and the V direction. However, in principle, the movement mode of each division point D is made to be bilaterally symmetric with respect to the reference line RL, and in the face deformation process when the deformation area is included in the compression area in this way. Means that the dividing points D13, D23, D33, D43 on the horizontal dividing line Lh3 are minus in the V direction rather than the amount by which the dividing points D11, D21, D31, D41 on the horizontal dividing line Lh1 are moved to the plus side in the V direction. Increase the amount moved to the side. This is to prevent the deformed neck image from becoming long by largely moving the dividing points D11, D21, D31, D41 on the horizontal dividing line Lh1 to the plus side in the V direction.

In FIG. 9, the face deforming unit 240 distributes the numerical value indicated by the compression ratio to the deformation amounts in the H direction and the V direction as described above, and further distributes the deformation amounts in the H direction and the V direction to each division point D. An example of the movement amount determined in this way is shown in the table. However, FIG. 9 shows the movement amount after the movement amount of each division point D determined according to the compression ratio as described above is further changed according to the position of the division point D. In FIG. 9, the movement amount of each division point D is not represented by n% as described above, but by a value converted to a pixel pitch. For example, for the dividing point D13, a movement amount of 19 times the pixel pitch is set on the left side along the H direction, and a movement amount of a distance of 7 times the pixel pitch is set downward along the V direction. Yes. Furthermore, in the example of FIG. 9, not only the dividing points D11, D21, D31, D41 on the horizontal dividing line Lh1 and the dividing points D13, D23, D33, D43 on the horizontal dividing line Lh3, but also the horizontal dividing line Lh2 An example in which the movement amount in the V direction is also set for the upper division points D12, D22, D32, and D42 is shown.
In S640, the face deformation unit 240 deforms the image in the deformation area TA by moving each division point D according to the movement amount for each division point D determined in S630 and deforming the small area in the deformation area TA. Let

  FIG. 10 shows a specific mode when the image in the deformation area TA is deformed by moving the position of each division point D according to the movement amount for each division point D illustrated in FIG. For each small area constituting the deformation area TA, the face deforming unit 240 changes the image of the small area in the state before the position of the dividing point D is moved to an image of a newly defined small area by the position movement of the dividing point D. As described above, an image deformation process is performed. In FIG. 10, for the convenience of comparison, the contour of the face of the person P1 before deformation is indicated by a chain line, and the outline of the face of the person P1 after deformation is indicated by a solid line. In FIG. 10, “′” is attached to the code of the dividing point D after the movement, and parentheses are attached to the code of the dividing point D (white circle) before the movement. For example, an image of a small region (small region indicated by hatching) having vertices at the division points D11, D21, D22, and D12 is a vertex at the division points D′ 11, D′ 21, D′ 22, and D′ 12. Is transformed into an image of a small area. Details of the deformation process of the small area image will be described later.

  As shown in FIG. 10, as a result of the movement of the dividing point D in S640, the positions of the dividing points D11, D21, D31, D41 arranged on the horizontal dividing line Lh1 with respect to the direction (V direction) parallel to the reference line RL. Is moved upward, while the positions of the dividing points D12, D22, D32, D42, D13, D23, D33, D43 arranged on the horizontal dividing lines Lh2, Lh3 are moved downward. Therefore, an image located between the horizontal dividing line Lh1 and the horizontal dividing line Lh3 is compressed in the V direction, and among them, an image located between the horizontal dividing line Lh1 and the horizontal dividing line Lh2 is strongly compressed in the V direction. Is done.

  With respect to the direction (H direction) orthogonal to the reference line RL, the positions of the dividing points D11, D12, D13 arranged on the vertical dividing line Lv1 are moved to the left, and the dividing points arranged on the vertical dividing line Lv4 The positions of D41, D42, and D43 are moved rightward. The positions of the dividing points D21, D22, D23 arranged on the vertical dividing line Lv2 are moved in the left direction, and the positions of the dividing points D31, D32, D33 arranged on the vertical dividing line Lv3 are moved in the right direction. . Accordingly, an image located on the left side of the vertical dividing line Lv1 is compressed to the left side in the H direction, and an image located on the right side of the vertical dividing line Lv4 is compressed to the right side. An image located between the vertical division line Lv1 and the vertical division line Lv2 is enlarged while moving to the left in the H direction, and an image located between the vertical division line Lv3 and the vertical division line Lv4 is H Enlarged while moving to the right with respect to direction. Further, the image located between the vertical dividing line Lv2 and the vertical dividing line Lv3 is enlarged with respect to the H direction around the reference line RL.

  As described above, the horizontal dividing line Lh1 is arranged below the chin image, the horizontal dividing line Lh3 is arranged above the top image, and the vertical dividing lines Lv1 and Lv4 are outside the cheek line image. The vertical dividing lines Lv2 and Lv3 are arranged outside the image of the corner of the eye. Therefore, in the face deformation process when the deformation area is included in the compression area in this way, the image of the face image from the chin to the top of the head is reduced in the V direction, and the left and right cheeks and cheeks are also reduced. Is enlarged in the H direction as a whole. By combining the deformation modes in the H direction and the V direction, the face shape of the person P1 included in the deformation area TA is crushed to some extent in the vertical direction and deformed into a thick shape in the width direction by the face deformation process. .

  In step S630, the face deforming unit 240 further multiplies each movement amount determined by finally allocating the numerical value indicated by the compression ratio to each division point D by a predetermined correction coefficient, and multiplies the correction coefficient. Each value obtained in this way may be the amount of movement of each division point D. The correction coefficient here is a numerical value of 0 or more and less than 1, for example, and indicates the degree of enlargement in the face width direction (H direction) and the degree of compression in the face height direction (V direction) by face deformation processing. It is a numerical value for suppressing. The specific value of the correction coefficient may be stored in advance in the internal memory 120 or may be set as a user input. The suppression of the degree of deformation by such a correction coefficient is performed when, for example, the amount of movement allocated to each division point D based on the compression ratio is applied to each division point D and the deformation process is performed. This is performed when the amount is too large and the image may be broken.

  FIG. 11 is an explanatory diagram conceptually showing the small area image deformation process executed in S640. In FIG. 11, the dividing point D is indicated by a black circle. In order to simplify the description, for the four small regions, the state before the position movement of the dividing point D is shown on the left side, and the state after the position movement of the dividing point D is shown on the right side. In the example of FIG. 11, the central division point Da is moved to the position of the division point Da ′, and the positions of the other division points D are not moved. Thereby, for example, an image of a rectangular small area (hereinafter also referred to as “pre-deformation noticeable small area BSA”) having the vertices at the division points Da, Db, Dc, Dd before the movement of the division point D is obtained from the division point Da ′. , Db, Dc, and Dd are transformed into an image of a rectangular small area (hereinafter also referred to as “the noticed small area ASA after deformation”).

  In the present embodiment, a rectangular small region is divided into four triangular regions using the center of gravity CG of the small region, and image deformation processing is performed in units of triangular regions. In the example of FIG. 11, the pre-deformation attention small area BSA is divided into four triangular areas having the centroid CG of the pre-deformation attention small area BSA as one vertex. Similarly, the post-deformation attention small area ASA is divided into four triangular areas having the centroid CG ′ of the post-deformation attention small area ASA as one vertex. Then, image deformation processing is performed for each corresponding triangular area in each state before and after the movement of the dividing point Da. For example, an image of a triangular area having vertices at the division points Da and Dd and the center of gravity CG in the attention small area BSA before deformation has a vertex at the division points Da ′ and Dd and the center of gravity CG ′ in the attention small area ASA after deformation. It is transformed into an image of a triangular area.

  FIG. 12 is an explanatory diagram showing the concept of an image deformation processing method in a triangular area. In the example of FIG. 12, the image of the triangular area stu with the points s, t, u as vertices is transformed into the image of the triangular area s′t′u ′ with the points s ′, t ′, u ′ as vertices. . For the deformation of the image, the position of a certain pixel in the image of the triangular area s't'u 'after the deformation corresponds to the position in the image of the triangular area stu before the deformation, and the calculated position This is performed by using the pixel value in the image before deformation in step S4 as the pixel value of the image after deformation.

  For example, in FIG. 12, the position of the pixel of interest p ′ in the image of the deformed triangular area s′t′u ′ corresponds to the position p in the image of the triangular area stu before deformation. The position p is calculated as follows. First, coefficients m1 and m2 for expressing the position of the target pixel p ′ by the sum of the vector s′t ′ and the vector s′u ′ as shown in the following equation (1) are calculated.

  Next, by using the calculated coefficients m1 and m2, the position p is obtained by calculating the sum of the vector st and the vector su in the triangular area stu before deformation by the following equation (2).

  When the position p in the triangular area stu before deformation coincides with the pixel center position of the image before deformation, the pixel value of the pixel is set as the pixel value of the image after deformation. On the other hand, when the position p in the triangular area stu before deformation is shifted from the pixel center position of the image before deformation, an interpolation operation such as bicubic using the pixel values of the pixels around the position p. Thus, the pixel value at the position p is calculated, and the calculated pixel value is set as the pixel value of the image after deformation.

  Image deformation from the image of the triangular area stu to the image of the triangular area s't'u 'by calculating the pixel value for each pixel in the image of the triangular area s't'u' after the deformation as described above Processing can be performed. In this way, the face deformation unit 240 performs a deformation process by defining a triangular area as described above for each small area constituting the deformation area TA.

  Next, a case will be described in which the face deforming unit 240 determines that the deformation area is included in the enlargement area and acquires an enlargement ratio applied to the enlargement area. When the face deforming unit 240 determines that the deformed area is included in the enlarged area, the face deforming unit 240 uses the reference for the predetermined division point D so that at least a part of the face image in the deformed area is compressed in the deforming direction. The amount of movement in the direction approaching the line RL is set according to the enlargement ratio. In this case, as in the case where the deformation area is included in the compression area, the face deformation unit 240 has the division points D11, D12, D13, D21 existing inside the frame of the deformation area TA among the division points D. , D22, D23, D31, D32, D33, D41, D42, and D43 are determined. With respect to these predetermined division points D, a movement amount in a direction approaching the reference line RL is set based on the enlargement ratio, and if the division point D is moved according to the set movement amount, at least a part of the face image is deformed. Also compressed.

  Further, when the face deforming unit 240 determines that the deformed area is included in the enlarged area, as the amount of movement in the V direction, the dividing points D11, D21, D31, and D41 on the horizontal dividing line Lh1 are on the minus side (lower A movement amount to the positive side (upper side) may be set for the dividing points D13, D23, D33, and D43 on the horizontal dividing line Lh3. In this way, if the movement amount is set for the predetermined division point D on the horizontal division line Lh1 and the predetermined division point D on the horizontal division line Lh3, and the division point D is moved according to the set movement amount, A part is enlarged also at least in the direction orthogonal to the deformation direction.

  Note that the face deformation unit 240 indicates the enlargement ratio in the movement amount setting of each division point D when the deformation area is included in the enlargement area, as in the case where the deformation area is included in the compression area. A numerical value of a predetermined ratio (for example, 70%) of the numerical values is assigned to the deformation amount (compression amount) in the H direction, and the remainder obtained by subtracting the deformation amount (compression amount) in the H direction from the numerical value indicated by the enlargement ratio (for example, 3 Is assigned to the deformation amount (enlargement amount) in the V direction. Further, the face deformation unit 240 uses the deformation amount assigned to the H direction and the V direction as described above when the deformation area is included in the enlarged area, as in the case where the deformation area is included in the compression area. In addition, the division points D11, D12, D13, D21, D22, D23, D31, D32, D33, D41, D42, and D43 are distributed and set at a predetermined ratio.

  In FIG. 17, the face deformation unit 240 distributes the numerical value indicated by the enlargement ratio as described above to the deformation amounts in the H direction and the V direction, and further distributes the deformation amounts in the H direction and the V direction to the respective division points D. An example of the movement amount determined in this way is shown in the table. However, FIG. 17 shows the movement amount after the movement amount of each division point D determined according to the enlargement ratio as described above is further changed according to the position of the division point D. Further, in FIG. 17, similarly to FIG. 9, the amount of movement of each division point D is indicated by a value converted into a pixel pitch. In the example of FIG. 17, not only on the dividing points D11, D21, D31, D41 on the horizontal dividing line Lh1 and the dividing points D13, D23, D33, D43 on the horizontal dividing line Lh3, but on the horizontal dividing line Lh2. An example in which the movement amount in the V direction is also set for the dividing points D12, D22, D32, and D42 is shown.

  FIG. 18 shows a specific mode when the face deformation unit 240 moves each division point D in S640 and deforms the image in the deformation area TA according to the movement amount for each division point D illustrated in FIG. Yes. In FIG. 18, as in FIG. 10, the contour of the face of the person P <b> 2 before the deformation is indicated by a chain line and the outline of the face of the person P <b> 2 after the deformation is indicated by a solid line for convenience of comparison. Also in FIG. 18, “′” is added to the code of the dividing point D after the movement, and parentheses are added to the code of the dividing point D (white circle) before the movement.

  As shown in FIG. 18, as a result of the movement of the dividing point D in S640, the positions of the dividing points D11, D21, D31, and D41 arranged on the horizontal dividing line Lh1 are moved downward with respect to the V direction. The positions of the dividing points D12, D22, D32, D42, D13, D23, D33, D43 arranged on the dividing lines Lh2, Lh3 are moved upward. Therefore, an image located between the horizontal dividing line Lh1 and the horizontal dividing line Lh3 is enlarged in the V direction, and among them, an image located between the horizontal dividing line Lh1 and the horizontal dividing line Lh2 is strongly enlarged in the V direction. Is done.

  In FIG. 18, with respect to the H direction, the positions of the dividing points D11, D12, D13, D21, D22, and D23 arranged on the vertical dividing lines Lv1 and Lv2 are moved to the right and on the vertical dividing lines Lv3 and Lv4. The positions of the division points D31, D32, D33, D41, D42, and D43 arranged at are moved to the left. Therefore, the image located on the left side of the vertical dividing line Lv1 is enlarged on the right side in the H direction, and the image located on the right side of the vertical dividing line Lv4 is enlarged on the left side. An image located between the vertical division line Lv1 and the vertical division line Lv2 is compressed while moving to the right in the H direction, and an image located between the vertical division line Lv3 and the vertical division line Lv4 is H Compressed while moving to the left with respect to direction. Furthermore, the image located between the vertical division line Lv2 and the vertical division line Lv3 is compressed in the H direction around the reference line RL.

  As described above, the horizontal dividing line Lh1 is arranged below the chin image, the horizontal dividing line Lh3 is arranged above the top image, and the vertical dividing lines Lv1 and Lv4 are outside the cheek line image. The vertical dividing lines Lv2 and Lv3 are arranged outside the image of the corner of the eye. Therefore, in the face deformation process when the deformation area is included in the enlargement area in this way, the image of the face image from the chin to the top of the head is enlarged in the V direction, and the left and right cheeks and cheeks Are generally compressed in the H direction. That is, in the face deformation process when the deformation area is included in the enlarged area, the shape of the face of the person P2 included in the deformation area TA is elongated to some extent in the vertical direction and deformed into a narrow shape in the width direction. The face deforming unit 240 further multiplies each movement amount determined by finally allocating the numerical value indicated by the enlargement ratio to each division point D in S630 by a predetermined correction coefficient, and obtained by this multiplication. Each value may be the amount of movement of each division point D. The correction coefficient in this case is a numerical value of 0 or more and less than 1, for example, and indicates the degree of compression in the face width direction (H direction) and the degree of enlargement in the face height direction (V direction) by face deformation processing. It is a numerical value for suppressing.

  In S800, the unidirectional deformation unit 230 performs a unidirectional deformation process on the target image. As described above, the unidirectional deformation unit 230 divides the target image into the compression region and the enlargement region by the dividing line orthogonal to the deformation direction when performing the unidirectional deformation process.

  FIG. 13A illustrates a state in which the target image TI is divided into a compressed area AC and an enlarged area AE. FIG. 13A shows an example in which a compression area AC is set in an area including the center of the target image TI, and enlarged areas AE and AE having the same area are set on both the left and right sides of the compression area AC. The person P1 is included in the enlarged area AE on the left side of the person P1.

  FIG. 13B illustrates an image (referred to as a modified image TI ′) after the one-direction deformation process is performed on the target image TI. That is, the unidirectional deformation unit 230 performs the unidirectional deformation process to transform the compression area AC into a compression area AC ′ whose length in the deformation direction is shortened as shown in FIG. Is transformed into an enlarged region AE ′ having an extended length in the deformation direction.

FIG. 14 is a flowchart showing the unidirectional deformation process executed in S800.
FIG. 15 is an explanatory diagram schematically showing the unidirectional deformation process when the deformation direction is the horizontal direction. FIG. 15A shows an arrangement of pixels in the target image before the one-way deformation process is performed. FIG. 15B shows an example of the corresponding pixel number table 410. FIG. 15C illustrates an arrangement of pixels of an image (deformed image) that has been subjected to the unidirectional deformation process.

  In S810, the unidirectional deformation unit 230 determines whether the deformation direction set by the deformation direction setting unit 220 in S400 is the horizontal direction or the vertical direction. If the deformation direction is the horizontal direction, the process proceeds to S820. On the other hand, if the deformation direction is the vertical direction, the process proceeds to S850. As described above, in this embodiment, since the horizontal direction is the deformation direction, the process proceeds to S820.

  In S820, the unidirectional deformation unit 230 generates the corresponding pixel number table 410. The corresponding pixel number table 410 is a table representing the number of pixels of the deformed image corresponding to each pixel in the deformation direction of the target image. The unidirectional deformation unit 230 determines the number of pixels (corresponding number of pixels) of the deformed image based on the magnification (compression rate and enlargement rate) already set for each of the compression region and the enlargement region. Then, by storing the determined corresponding pixel number in the corresponding pixel number table 410, the corresponding pixel number table 410 is generated.

  In generating the corresponding pixel number table 410, the unidirectional deformation unit 230 converts the compression rate and the enlargement rate into a magnification. For example, when the numerical value “30%” is set as the compression rate as described above, the compression rate is converted to a numerical value (magnification) of 0.7 times. For example, when a numerical value of 30% is set as the enlargement ratio, this enlargement ratio is converted to a numerical value (magnification) of 1.3 times. For example, the unidirectional deformation unit 230 performs binarization by halftone processing on the fractional part of such a magnification to determine an array pattern of 0 and 1, and an integer of the magnification to the value of 0 or 1 of the array pattern By adding a portion, the number of corresponding pixels for each pixel of the target image can be determined. In generating the corresponding pixel number table 410, the unidirectional deformation unit 230 can use a known method such as dithering or error diffusion as the halftone process. Alternatively, an array pattern stored in advance for each fractional part of the magnification may be used. In S820, a corresponding pixel number table created in advance may be used instead of generating the corresponding pixel number table 410.

  In FIG. 15A, for the sake of simplicity, there are regions 1, 2, and 3 each consisting of 5 pixels in the horizontal direction of the image, region 1 and region 3 are enlarged regions, and region 2 is a compressed region. The description will be made assuming a certain case. Here, it is assumed that the magnification of region 1 is 1.2 times, the magnification of region 2 is 0.6 times, and the magnification of region 3 is 1.2 times. Therefore, in the corresponding pixel number table (FIG. 15B), among the five pixels Px1 to Px5 in the region 1, the corresponding pixel number is set to 1 for four pixels Px1, Px2, Px3, and Px5, and the remaining one pixel For Px4, the number of corresponding pixels is set to two. Of the five pixels Px6 to Px10 in the region 2, the corresponding number of pixels is set to 1 for the three pixels Px6, Px8, and Px10, and the corresponding number of pixels is set to 0 for the remaining two pixels Px7 and Px9. Has been. Of the five pixels Px11 to Px15 in the region 3, the number of corresponding pixels is set to 1 for four pixels Px11, Px12, Px13, and Px15, and the number of corresponding pixels is set to 2 for the remaining one pixel Px14. Has been.

  In S830, the unidirectional deformation unit 230 refers to the corresponding pixel number table and rearranges pixels for one line of the target image using the buffer area in the internal memory 120. Here, a line is a processing unit in the unidirectional deformation process, and refers to an image area whose length is the number of all pixels in the horizontal direction of the target image and whose width is one pixel. In the example of FIG. 15, as shown in FIG. 15C, pixels Px1, Px2, and Px3 having a corresponding pixel number of 1 are sequentially arranged one by one as the pixels constituting the region 1, and then the corresponding pixel number of 2 Two pixels Px4 are arranged, and then one pixel Px5 having a corresponding number of pixels of one is arranged. Next, the pixels Px6, Px8, and Px10 having a corresponding pixel number of 1 are sequentially arranged as the pixels that configure the region 2, and then the pixels Px11, Px12 and Px13 are arranged one by one, two pixels Px14 with the corresponding number of pixels 2 are arranged, and one pixel Px15 with the number of corresponding pixels 1 is arranged. By performing such rearrangement of pixels for one line for all lines, the enlargement area of the target image is enlarged 1.2 times, and the compression area is compressed 0.6 times.

  In S840, the unidirectional deformation process execution unit 230 determines whether or not pixel rearrangement has been completed for all lines of the target image. When the pixel rearrangement has been completed for all lines, the unidirectional deformation process is terminated, and as a result, the flowchart of FIG. 2 is terminated. On the other hand, when the pixel rearrangement is not completed, the process returns to S830, and S830 and S840 are repeatedly executed until the pixel rearrangement is completed for all lines.

  In S850, the unidirectional deformation unit 230 generates the corresponding pixel number table 410 by using the respective magnifications of the compression area and the enlargement area as in S820. When the deformation direction is the vertical direction, a corresponding pixel number table 410 that defines the number of corresponding pixels for each pixel arranged in the vertical direction of the target image is generated. Since the method for determining the number of corresponding pixels is the same as that in S820, description thereof is omitted.

  In S860, the one-way deformation unit 230 refers to the corresponding pixel number table and arranges the line of the target image in the storage area of the deformed image provided in the buffer area. When the deformation direction is the horizontal direction, rearrangement is performed according to the number of corresponding pixels (0, 1, 2 or the like) corresponding to the pixel in units of pixels, but when the deformation direction is the vertical direction, Arrangement is performed in line units according to the number of corresponding pixels corresponding to the line. Specifically, one line of the target image stored in the buffer area is added to the storage area of the deformed image in the buffer area as a line corresponding to the number of corresponding pixels corresponding to the one line.

  In S870, the unidirectional deformation unit 230 determines whether or not the process of S860 has been completed for all the lines of the target image, and if complete, ends the unidirectional deformation process, and as a result, The flowchart of FIG. 2 ends. On the other hand, if it is not completed, the process returns to S860, and S860 and S870 are repeatedly executed until S860 is performed for all the lines of the target image.

3. Summary As described above, the compression area set in the target image is compressed in the deformation direction and the enlargement area is expanded in the deformation direction by the one-way deformation process in S800. Therefore, as shown in FIG. 13B, the person P1 in the transformed image TI ′ is generally thinner (slimmed) than the person P1 in the target image TI before transformation, and the person P1 in the transformed image TI ′ The person P2 is generally thicker than the person P2 in the target image TI before deformation. As described above, the face shape included in the compressed region is crushed in the vertical direction and thickened in the width direction by the face deformation process in S600, and the face shape included in the enlarged region is It is elongated in the vertical direction and thinned in the width direction. Therefore, in the target image that has undergone the face deformation process and the unidirectional deformation process, the human image included in the compressed area is deformed into a slim body as a whole and is included in either the compressed area or the enlarged area. The face of the person image that has been displayed also has no sense of incongruity between the vertical and horizontal balance. The face of the human body is a part that attracts particular attention to the user. If the aspect ratio of the face is significantly deformed by the image correction process, the user will feel a great sense of discomfort. According to the present embodiment, since the aspect ratio of the face is suppressed from being significantly changed as compared to before processing, the user can obtain an image that does not feel strange to the eye.

  In the above description, the case where the unidirectional deformation process (S800) is executed after the face deformation process (S600) has been described as an example. However, the unidirectional deformation process is performed regardless of the order of the processes when these two processes are performed. The face deformation process may be performed after (for example, S800 is performed between S400 and S500 in the flowchart of FIG. 2).

  In the present embodiment, various measures are taken to obtain an image with a good overall balance while preventing the aspect ratio of the face in the target image from changing too much. As described above, in the face deformation process, the numerical value indicated by the compression ratio or enlargement ratio in the one-way deformation process is not applied as the deformation amount in the H direction of the image of the deformation area, but indicates the compression ratio or enlargement ratio. A numerical value corresponding to a predetermined ratio is applied. In other words, if the face deformation process is performed to enlarge enough to cancel almost all the compression in the compression area or almost all enlargement in the enlarged area, the balance between the face and the body other than the face is very poor. A person image may be obtained. For this reason, the deformation in the width direction of the face in the face deformation process is performed to such an extent that the effect of the deformation by the one-way deformation process is better to some extent.

  In the face deformation process described above, two cases will be described: the case where the entire deformation area is included in the compression area (person P1) and the case where the entire deformation area is included in the enlargement area (person P2). I did it. However, depending on the position of the person image in the target image and the setting mode of the compression area and the enlargement area, one deformation area may be set at a position straddling the boundary between the compression image and the enlargement image.

  FIG. 19A illustrates a case where the deformation area TA for a face image of a person is set at a position straddling the boundary (chain line) between the compressed image and the enlarged image in the target image. In such a case, in S630, the face deformation unit 240 determines, based on the compression ratio of the compression area, for the division points D belonging to the compression area among the division points D arranged as described above in the deformation area TA. The movement amount calculated as described above is set (assuming that the entire deformation area TA is included in the compression area). On the other hand, among the division points D of the deformation area TA, the division points D belonging to the expansion area are based on the enlargement ratio of the expansion area (assuming that the entire deformation area TA is included in the expansion area). The movement amount calculated as described above is set.

  After setting the movement amount of each division point D in this way, in S640, the face deformation unit 240 converts the deformation area TA into a deformation area TA1 belonging to the compression area and a deformation area TA2 belonging to the enlargement area, as shown in FIG. 19B. The image in the deformation area TA1 is deformed according to the amount of movement set at the dividing point D in the deformation area TA1, and the image in the deformation area TA2 is moved at the division point D in the deformation area TA2. Perform deformation according to the amount. As a result of such face deformation processing, of the faces in the deformation area TA, the part belonging to the compression area is enlarged in the deformation direction, and the part belonging to the expansion area is compressed in the deformation direction.

DESCRIPTION OF SYMBOLS 100 ... Printer, 110 ... CPU, 120 ... Internal memory, 140 ... Operation part, 150 ... Display part, 160 ... Printer engine, 170 ... Card I / F, 172 ... Card slot, 200 ... Image correction process part, 210 ... Face Area detection unit, 220 ... Deformation direction setting unit, 230 ... Unidirectional deformation unit, 240 ... Face deformation unit, 310 ... Display processing unit, 320 ... Print processing unit, 410 ... Corresponding pixel number table, 420 ... Division point arrangement pattern table

Claims (8)

In a target image including a face image, an area setting unit that sets a compression area and an enlargement area in the target image;
An image deformation unit that enlarges the enlargement area in a specific direction with a predetermined enlargement ratio;
When at least a part of the face image is included in the enlargement area, the compression amount determined according to the enlargement ratio so that the face image included in the enlargement area is compressed in the specific direction. An image processing apparatus comprising: a face deforming unit that deforms the face image. The image transformation unit compresses the compression area in the specific direction by a predetermined compression rate,
The face deforming unit adjusts the compression rate so that the face image included in the compression area is enlarged in the specific direction when at least a part of the face image is included in the compression area. The image processing apparatus according to claim 1, wherein the face image is deformed by an enlargement amount determined accordingly.   3. The face deformation unit, wherein the face image is deformed when an angle formed by the vertical direction of the face image and the specific direction is larger than a predetermined reference angle. An image processing apparatus according to 1.   The face deformation unit performs deformation on a face image excluding face images at least partially overlapping each other when a plurality of face images exist in the target image. The image processing apparatus according to claim 1.   The image processing apparatus according to claim 1, wherein the face deforming unit determines the compression amount based on a numerical value of a predetermined ratio among the numerical values indicated by the enlargement ratio. In a target image including a face image, an area setting step for setting a compression area and an enlarged area in the target image;
An image transformation step of enlarging the enlargement area in a specific direction with a predetermined enlargement ratio;
When at least a part of the face image is included in the enlargement area, the compression amount determined according to the enlargement ratio so that the face image included in the enlargement area is compressed in the specific direction. And a face deformation step for deforming the face image. An area setting function for setting a compression area and an enlargement area in the target image in the target image including the face image;
An image transformation function for enlarging the enlargement area in a specific direction with a predetermined enlargement ratio;
When at least a part of the face image is included in the enlargement area, the compression amount determined according to the enlargement ratio so that the face image included in the enlargement area is compressed in the specific direction. An image processing program for causing a computer to execute a face deformation function for deforming the face image. In a target image including a face image, an area setting unit that sets a compression area and an enlargement area in the target image;
An image deformation unit that enlarges the enlargement area in a specific direction with a predetermined enlargement ratio;
When at least a part of the face image is included in the enlargement area, the compression amount determined according to the enlargement ratio so that the face image included in the enlargement area is compressed in the specific direction. A printing apparatus comprising: a face deformation unit that deforms the face image.

Images