JP4877074B2 - Image processing apparatus, image processing method, and computer program - Google Patents

Description

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

  A method of outputting an image photographed by an imaging device such as a digital still camera (DSC) or a scanner with an image output device such as a printer is becoming widespread. In some cases, these image output apparatuses automatically perform image processing for determining the image type of an image to be output and adjusting the image quality. Examples of such image processing include processing (pixel value processing) for adjusting pixel values of pixels constituting an image, such as adjustment of contrast, brightness, and color balance. (For example, patent document 1).

  In addition, a process for transforming an image represented by image data (deformation process), for example, an image process for correcting a cheek line of a face image is known (Patent Document 2). With this technique, for example, an impression given to what the image sees can be adjusted.

WO2004-070657 JP 2004-318204 A

  However, the pixel value processing alone may not provide a sufficient image quality adjustment effect. Similarly, the deformation processing alone may not provide a sufficient image quality adjustment effect. Further, it is not easy to obtain a desired image quality adjustment effect by making full use of the pixel value adjustment process and the deformation process, and it is particularly difficult for general users who do not have sufficient knowledge about image processing. . Such a problem is common to image output in various modes including not only when printing but also displaying on a display or the like.

  The present invention can be realized as the following forms or application examples in order to solve at least a part of the above-described problems.

Application Example 1 An image processing apparatus, which is a first processing unit that performs a deformation process for deforming a region included in a target image, and a process associated with the deformation process, and is included in the target image And a second processing unit that performs pixel value processing for adjusting the pixel value of the pixel.

  According to the image processing apparatus in Application Example 1, since the pixel value processing and the deformation processing are associated with each other, it is possible to easily perform image quality adjustment that combines the pixel value processing and the deformation processing.

  In the image processing apparatus according to the application example 1, at least a part of the deformation processing and the pixel value processing that are associated with each other may be the same or similar among changes that are brought about in the target image. In this way, it is possible to easily perform image quality adjustment that combines pixel value processing and deformation processing that bring about the same or similar changes, and it is also possible to bring great changes to the target image.

  In the image processing apparatus according to the application example 1, the target image may include a face image, and the change that the deformation process and the pixel value process cause to the target image may include a change in the impression of the face image. In this way, it is possible to realize a change in the impression of the face image by adjusting the image quality by combining the pixel value processing and the deformation processing.

  In the image processing apparatus according to Application Example 1, the deformation process is a process of deforming the face image so as to bring a predetermined change in the impression of the face image, and the pixel value process is an impression of the face image. The pixel value may be adjusted so as to bring about a change that is the same as or similar to the predetermined change. In this way, it is possible to easily perform image quality adjustment of a face image by combining pixel value processing and deformation processing that bring about the same or similar impression change, and it is also possible to bring a big change to the face image.

  In the image processing apparatus according to Application Example 1, the deformation process and the pixel value process that are associated with each other may act so as to cancel out some of the changes that are brought about in the target image. In this way, it is possible to combine the pixel value processing and the deformation processing to bring a desired change to the target image and to prevent an undesired change from occurring in the target image.

  In the image processing apparatus according to the application example 1, the target image may include a face image, and the change that the deformation process and the pixel value process cause to the target image may include a change in the impression of the face image. In such a case, the deformation process is a process of deforming the face image so as to cause a predetermined change in the impression of the face image, and the pixel value processing is performed with the predetermined change in the impression of the face image. In this way, the process of adjusting the pixel values so as to bring about a contradictory change, it is possible to bring about other desired changes to the target image while suppressing changes in the impression of the face image.

  In the image processing apparatus according to the application example 1, the processing content including the type determination unit that determines an image type determined according to the feature of the image, the deformation process, and the pixel value process is determined for the target image. A processing content determination unit that determines the image content according to the image type, and the image quality adjustment processing of the determined processing content may be performed on the target image. In this way, since the processing content including the deformation processing and the pixel value processing associated with each other is determined according to the image type, effective image quality adjustment according to the image type can be easily realized.

  In the image processing device according to Application Example 1, the processing content determination unit selects processing content to be performed on the target image from among a plurality of types of candidate processing content each including the deformation processing and the pixel value processing. A selection screen generation unit that generates a selection screen for the purpose according to the determined image type may be included. In this way, preferable candidate processing contents can be presented to the user in accordance with the image type, so that the operation burden for adjusting the image quality of the user can be reduced.

  In the image processing apparatus according to the application example 1, the selection screen generation unit determines a priority order of the plurality of types of candidate processing contents according to the determined image type, and generates the selection screen according to the priority order. May be. In this way, since the selection screen is generated according to the priority order, the operation burden for the user to adjust the image quality can be further reduced.

  In the image processing apparatus according to Application Example 1, the selection screen generation unit specifies a part of the plurality of types of candidate process contents according to the determined image type, and the specified candidate process contents are determined. The selectable selection screen may be generated. In this way, the candidate processing content is narrowed down to a part and presented to the user, so that it is possible to further reduce the operation burden for the user to adjust the image quality.

  The image processing apparatus according to the application example 1 includes a selection learning unit that learns the selection performed via the selection screen, and the selection screen generation unit includes the learning result in addition to the determined image type. The selection screen may be generated using. In this way, since the selection screen can be generated in consideration of the user's selection tendency, it is possible to further reduce the operation burden for the user to adjust the image quality.

  In the image processing apparatus according to the application example 1, the selection screen generation unit sets each candidate process content to at least one of a plurality of types of the image types regardless of the determination result of the image type according to a user instruction. You may display corresponding to.

Application Example 2 This is an image processing method that performs a deformation process for deforming an area included in the target image, and is a process associated with the deformation process, and adjusts the pixel value of the pixel included in the target image. An image processing method for performing pixel value processing.

Application Example 3 A computer program for image processing, which is a first function for performing a deformation process for deforming an area included in a target image, and a process associated with the deformation process. A computer program that causes a computer to realize a second function of performing pixel value processing for adjusting pixel values of included pixels.

  The image processing method according to the application example 2 and the computer program according to the application example 3 can obtain the same effects as the image processing apparatus according to the application example 1. In addition, the image processing method according to the application example 2 and the computer program according to the application example 3 can be realized in various modes in the same manner as the image processing apparatus according to the application example 1.

  Furthermore, the present invention can be realized in the form of a recording medium that records the computer program according to Application Example 3, a data signal that includes the computer program and is embodied in a carrier wave, and the like.

Next, embodiments of the present invention will be described in the following order based on examples.
A. First embodiment:
-Configuration of the printer 100:
FIG. 1 is a block diagram showing a configuration of a printer 100 as an image processing apparatus according to the first embodiment of the present invention. The printer 100 of this embodiment is a color inkjet printer that supports so-called direct printing, in which an image is printed based on image data acquired from a memory card MC or the like. The printer 100 includes a CPU 110 that controls each unit of the printer 100, an internal memory 120 configured by, for example, a read only memory (ROM) and a random access memory (RAM), an operation unit 140 configured by buttons and a touch panel, a liquid crystal display, and the like. A display unit 150 configured by a display, a printer engine 160, and a card interface (card I / F) 170 are provided. The printer 100 may further include an interface for performing data communication with other devices (for example, a digital still camera). Each component of the printer 100 is connected to each other via a bus.

  The printer engine 160 is a printing mechanism that performs printing based on print data. The card interface 170 is an interface for exchanging data with the memory card MC inserted into the card slot 172. In this embodiment, the memory card MC stores RGB data as image data.

  The internal memory 120 stores an image data acquisition unit 210, an image quality adjustment unit 220, an image type determination unit 230, a processing content determination unit 240, a display processing unit 250, and a print processing unit 260 as functional units. Has been. Each of the functional units 210 to 260 is a computer program that realizes a predetermined function by being read from the internal memory 120 by the CPU 110 and executed. The image data acquisition unit 210, the image quality adjustment unit 220, the image type determination unit 230, and the processing content determination unit 240 execute image processing to be described later. The image quality adjustment unit 220 includes a deformation processing unit 222 and a pixel value processing unit 224 as submodules. The processing content determination unit 240 includes a selection screen generation unit 242 as a submodule. The display processing unit 250 is a display driver that controls the display unit 150 to display a processing menu and a message on the display unit 150. The print processing unit 260 is a computer program for generating print data from image data, controlling the printer engine 160, and printing an image based on the print data.

  The internal memory 120 further includes an image type database 310 and a processing content database 320. Furthermore, as indicated by a broken line in FIG. 3, the internal memory 120 may include a selection learning database 330, and the processing content determination unit 240 may include a selection learning unit 244 as a submodule. A configuration including the selection learning database 330 and the selection learning unit 244 will be described later as a modification.

  FIG. 2 is a diagram conceptually showing the contents of the image type database 310. The image type database 310 describes image types that are determined according to image characteristics. In this embodiment, an image type that is determined according to an image shooting scene is used. For example, image types such as “portrait”, “landscape”, “evening scene”, “night scene”, and “flower” are described (FIG. 2). The image type database 310 further describes one or a plurality of picture making types with priorities in association with the image types. The picture making type is a name of an image quality adjustment process performed on an image. In this embodiment, a word representing an impression brought about by an image quality adjustment process on an image is used as the name. Specifically, picture making types such as “easy”, “beautiful”, and “lively” are described (FIG. 2). In FIG. 2, m of “picture making type m (m is a natural number)” represents a priority level, and the smaller the value of m, the higher the priority level.

  FIG. 3 is a diagram conceptually showing the contents of the processing content database 320. The processing content database 320 describes specific processing content of image quality adjustment processing corresponding to the picture making type for each picture making type. Image quality adjustment processing corresponding to one picture making type includes pixel value processing and deformation processing. The pixel value process is a process for adjusting the pixel values of the pixels constituting the image. Pixel value processing is processing performed on pixels constituting a face image representing a human face in the present embodiment, in this embodiment, for example, processing for adjusting skin contrast, and coloring the cheek portion of the face. Includes processing. In addition, the pixel value processing includes processing performed on all pixels constituting the image, for example, processing for adjusting contrast and brightness. Further, the pixel value processing includes processing performed on some pixels constituting the image, for example, sharpness processing performed on the edge region and its neighboring pixels. The deformation process is a process of deforming an area included in the target image, and in the present embodiment, is a process of deforming the above-described face image.

  For example, as shown in FIG. 3, the image quality adjustment processing corresponding to the picture creation type “Genki” includes pixel value processing, processing for setting contrast to “hard”, processing for setting brightness to “normal”, and saturation. This includes a process of “increasing”, a process of increasing the color balance to “normal”, and a process of increasing sharpness (sharpness). The image processing corresponding to the picture-making type “Genki” is a pixel value processing for the face image. The processing is to “strengthen” the skin contrast, and the “horizontal yellow” color is applied to the cheek part of the face. Including the process of attaching. Further, the image processing corresponding to the picture making type “Genki” includes a process of “decreasing the height of a face” and a process of “enlarging it vertically” as a face image deformation process. The pixel value processing and the deformation processing corresponding to one picture making type are both processing for giving the same or similar impression to the target image. For example, each of the pixel value processing corresponding to the picture making type “Genki” and each deformation processing are processes that bring about a change that gives a “good” impression to the target image.

-Operation of the printer 100:
The printer 100 prints an image based on the image data stored in the memory card MC. When the memory card MC is inserted into the card slot 172, the display processing unit 250 displays a user interface including a list display of images stored in the memory card MC on the display unit 150. The image includes an image including the face image F and an image not including the face image F. FIG. 4 is an explanatory diagram illustrating an example of a user interface including a list display of images.

  The printer 100 according to the present embodiment performs normal printing in which when the user selects one (or a plurality of) images and selects a print button in the user interface shown in FIG. 4, the selected image is printed as it is. Execute the process. On the other hand, when one (or a plurality of) images are selected and a picture creation button is selected by the user in the user interface, the printer 100 performs predetermined image processing on the selected images. Then, a process (picture making process) for printing / saving the image after the image process is executed.

  FIG. 5 is a flowchart illustrating the flow of the picture making process performed by the printer 100 according to the first embodiment. When the picture making process is started, the image process is executed using the image selected in the above-described user interface as a target image (step S100).

  FIG. 6 is a flowchart showing the flow of image processing in the first embodiment. When the image processing is started, the image data acquisition unit 210 reads out and acquires the image data of the target image from the card slot 172 (step S110). The acquired image data is stored in a predetermined area of the internal memory 120.

  The image type determination unit 230 analyzes the acquired image data and determines the image type of the target image (step S120). In the present embodiment, as described above, the image type is determined according to the shooting scene such as “portrait”, “landscape”, “night view”, and the like. For this reason, in the present embodiment, the image type can be determined by the process of specifying the shooting scene of the target image by analyzing the image data (scene specifying process). Various known or well-known methods can be used for the scene specifying process. For example, it is possible to use a process for specifying a shooting scene using a hue (characteristic hue) that characterizes the target image and a frequency characteristic of a pixel region having the characteristic hue.

  Specifically, the image type determination unit 230 counts the number of pixels belonging to each hue of blue, green, skin color, and red for the target image, and calculates a ratio to the total number of pixels. If the pixel value (for example, HSB value or RGB value) has a value within a predetermined range, it is determined that the color has a predetermined hue. For example, the image type determination unit 230 determines a characteristic hue of the target image using a map prepared in advance. In the map, for example, the ratio of the number of pixels constituting each hue and the characteristic hue are described in association with each other.

  The image type determination unit 230 further specifies a pixel region that forms a characteristic hue, and performs frequency analysis on the specified pixel region. The pixel area constituting the characteristic hue is specified based on the hue and coordinate position information of each pixel included in the hue information. The frequency analysis for the identified pixel region is executed in the horizontal direction (lateral direction) and the vertical direction (vertical direction) of the image data using a two-dimensional Fourier transform formula. As a result, the frequency characteristic of the pixel region having a characteristic hue in the target image is calculated.

The image type determination unit 230 specifies the shooting scene of the target image using the characteristic hue and the frequency characteristics of the characteristic hue region. For example, the shooting scene is specified as follows. If the shooting scene is specified, the image type of the shot image can be determined as can be seen from FIG.
(1) When the characteristic hue is green and there are many high-frequency components as frequency characteristics, it is specified as “landscape” centering on green such as mountains and plains.
(2) When the characteristic hue is blue and there are many low frequencies as frequency characteristics, it is specified as “landscape” centering on the sky.
(3) When the characteristic hue is blue and the frequency characteristic has a high frequency, it is identified as a “landscape” centered on the sea.
(4) When the characteristic hue is skin color and there are many low frequencies as frequency characteristics, it is specified as a “portrait” centering on a person.
(5) When the characteristic hue is skin color and there are many high frequencies as frequency characteristics, it is specified as a beach or similar “landscape”.
(6) When the characteristic hue is gray and there are many low frequencies as frequency characteristics, it is specified as “night scene”.
(7) When the characteristic hue is red and there are many low frequencies as frequency characteristics, it is specified as “evening scene”.
(8) When a specific hue occupies most of the characteristic hues and the high frequency component is not so many as the frequency characteristics, it is determined that the image is macro photography (close-up photography). When the hue area is seen, it is specified that the scene is “flower” in macro photography.

  When the image type is determined by specifying the shooting scene, the selection screen generation unit 242 of the processing content determination unit 240 acquires a picture making type candidate (step S130). Specifically, the selection screen generation unit 242 searches the image type database 310 and acquires the picture making type associated with the image type specified in step S120 as a candidate together with the priority order. For example, when the image type is “portrait”, the acquired picture creation candidates are “easy”, “cute”, “beautiful”, “lively”, and “good” in descending order of priority.

  When a picture creation candidate is acquired, a selection screen for selecting a picture creation to be performed on the target image from a plurality of picture creation candidates is generated and displayed (step S140). FIG. 7 is a diagram illustrating an example of the selection screen. Specifically, as illustrated in FIG. 7, the selection screen generation unit 242 generates image data of a selection screen that displays the acquired names of picture creation candidates in order of priority. The display processing unit 250 displays a selection screen on the display unit 150 using the generated image data. The user operates the cursor CS by pressing the previous candidate button or the next candidate button, and selects a desired picture creation. An arrow AR1 in FIG. 7A indicates that there is another picture making candidate with a lower priority in addition to the displayed picture making candidate, and an arrow AR2 in FIG. 7B indicates the displayed picture. In addition to the creation candidates, there is another picture creation candidate with a high priority. The selection screen may include a list display button indicated by a broken line in FIG. The case of having a list display button will be described later as a modified example.

  The processing content determination unit 240 receives an input for selecting one picture making type from the user via the selection screen, and determines the picture making type (step S150). Thereby, the processing content of the image quality adjustment processing performed on the target image is determined (FIG. 3).

  When the picture making type is determined, the image quality adjustment unit 220 executes image quality adjustment processing for the target image (step S160). FIG. 8 is a flowchart showing the flow of image quality adjustment processing. When the image quality adjustment process is started, the image quality adjustment unit 220 detects the face area FA in the target image (step S161). Here, the face area FA means an area corresponding to a human face on the target image. The detection of the face area FA by the image quality adjustment unit 220 is executed using a known face detection method such as a pattern matching method using a template (see Japanese Patent Application Laid-Open No. 2004-318204).

  If the face area FA is not detected (step S162: NO), only pixel value processing is performed (step S165). When the face area FA is detected (step S162: YES), pixel value processing (step S163) and face image deformation processing (face deformation processing) (step S164) are performed.

  The pixel value processing unit 224 of the image quality adjustment unit 220 acquires the processing content of the pixel value processing corresponding to the picture making type determined in step S150 from the processing content database 320. The pixel value processing unit 224 performs pixel value processing according to the acquired processing content. For example, when the determined picture making type is “Genki”, the pixel value processing unit 224 performs a process of setting the contrast to “high contrast”, a process of setting the brightness to “normal”, and “higher” the saturation. Processing, processing for setting the color balance to “normal”, processing for increasing sharpness (sharpness processing) are executed. For example, a brightness target value Baim corresponding to the brightness “normal” is determined in advance. The process of setting the brightness to “normal” is executed by adjusting the brightness of each pixel using the tone curve shown below so that the average brightness Bave of all the pixels constituting the target image becomes the target value Baim. Is done.

  FIG. 9 is a first diagram illustrating an example of pixel value processing. FIG. 9A shows an example of a tone curve used for the process of adjusting the brightness. In FIG. 9A, the horizontal axis corresponds to the lightness input value, and the vertical axis corresponds to the lightness output value. As the brightness, for example, a value of B (Brightness) in the HSB color space is used. In the brightness adjustment, brightness conversion using such a tone curve is performed on all pixels of the target image. In this embodiment, the degree of brightness adjustment is determined by the amount of change in brightness value output when the reference brightness Bref is input. For example, as shown in FIG. 9A, if the amount of change is set to a positive value b +, the tone curve becomes a convex curve, and the larger the absolute value of b +, the brighter the image. Conversely, if the amount of change is set to a negative value b−, the tone curve becomes a downwardly convex curve, and the larger the absolute value of b−, the darker the image.

  FIG. 9B shows an example of a tone curve used for the process of adjusting the contrast. Similarly to FIG. 9A, in FIG. 9B, the horizontal axis corresponds to the lightness input value, and the vertical axis corresponds to the lightness output value. In contrast adjustment, lightness conversion using such a tone curve is performed on all pixels of the target image, as in lightness adjustment. In this embodiment, the degree of contrast adjustment is determined by the amount of change in the brightness value output when the reference brightness Bref is input. For example, as shown in FIG. 9B, when the amount of change is set to a positive value k +, the tone curve becomes an S-shaped curve, and the larger the absolute value of k +, the stronger the contrast of the image (in high contrast). Become. Conversely, if the amount of change is set to a negative value k−, the tone curve becomes an inverted S-shaped curve, and the contrast of the image becomes weaker (softer) as the absolute value of k− increases.

  For example, the saturation is adjusted by performing conversion using a tone curve similar to that shown in FIG. 9A on the saturation value (for example, the value of S (Saturation) in the HSB color space). .

  For the adjustment of the color balance, for example, a method of adjusting each color component so that an average value of pixel values (for example, RGB values) of all pixels constituting the image becomes a value representing a predetermined target color is used. For example, when the color balance is adjusted to “normal”, the target color is set to an achromatic color (white or gray). When the color balance is adjusted to “yellow”, the target color is set to a color obtained by adding a yellow color (component) to an achromatic color.

  For the sharpness processing, a method using an unsharp mask can be used. This method is a method in which data with no change in brightness value (unsharp) is prepared, and a difference value obtained by subtracting unsharp data from the original data is multiplied by a coefficient to add to the original data. Thereby, the change of the brightness value can be sensitized. Unsharp data can be obtained by averaging the brightness values of each pixel of the original data using the brightness values of surrounding pixels (smoothing process). For the smoothing process, for example, a method of calculating an average with a greater weight as the luminance value of the pixel closer to the target pixel can be used. As such a weight function, a two-dimensional Gaussian function centered on the target pixel can be used.

  The soft focus process can be performed by replacing the unsharp data described above with the original data. The sharpness process and the soft focus process do not need to be performed on all the pixels of the target image, and may be performed only on the edge region and its surrounding pixels, for example.

  The vignette process is a process for reducing the brightness of pixels near the four corners of the image. Vignette processing can give the image a retro-like impression.

  The noise process is a process for adding predetermined noise to the brightness value of each pixel constituting the image, for example. As such noise, noise by Gaussian distribution or noise by uniform distribution can be used. The image is given a graininess (roughness) by the noise processing. For example, when used together with the vignette processing, a nostalgic impression can be given to the image.

  When the face area FA is detected, the pixel value processing unit 224 further executes pixel value processing on the face image according to the acquired processing content. For example, when the determined picture making type is “Genki”, the pixel value processing unit 224 performs a process of “strengthening” the skin contrast and a process of coloring “horizontally yellow” on the cheek portion of the face image. (Cheek coloring process) is executed.

  The process for adjusting the skin contrast is a process for adjusting the contrast of the pixels corresponding to the skin of the face image. Specifically, the pixel value processing unit 224 uses the tone curve shown in FIG. 9B to contrast the pixels having a predetermined skin color hue among the pixels in the face area FA and in the vicinity thereof. Make adjustments.

  FIG. 10 is a diagram for explaining the cheek coloring process. As shown in FIG. 10A, the cheek coloring process of “horizontally long” is performed by adding a predetermined color (in this embodiment, red or red) to the pixel value of the pixel in the horizontally long region Ch1 below each eye. Yellow). As shown in FIG. 10B, the cheek coloring process for coloring “vertically long” is a process of adding a predetermined color to the pixel value of the pixel in the vertically long region Ch2 on the lower side of each eye. The areas Ch1 and Ch2 are determined from the positional relationship with these organs, for example, by further detecting organs such as eyes and mouth within the detected face area FA.

  When the face area FA is detected, when the pixel value processing ends, the deformation processing unit 222 of the image quality adjustment unit 220 performs face deformation processing (step S164). FIG. 11 is a flowchart showing the flow of the face deformation process. When the deformation processing unit 222 starts the face deformation processing, the deformation processing unit 222 sets a deformation area TA including part or all of the face image (step S1642).

  FIG. 12 is a diagram illustrating the setting of the deformation area. As shown in FIG. 12, in the present embodiment, the face area FA is detected as a face area FA including a rectangular area including the eyes, nose and mouth images of the face image on the target image. Note that the reference line RL shown in FIG. 12 is a line that defines the height direction (vertical direction) of the face area FA and the center in the width direction (horizontal direction) of the face area FA. That is, the reference line RL is a straight line that passes through the center of gravity of the rectangular face area FA and is parallel to the boundary line along the height direction (vertical direction) of the face area FA. The deformation area TA is an area on the target image and is a target of image deformation processing for face shape correction. As shown in FIG. 12, in this embodiment, the deformation area TA extends (or shortens) the face area FA in a direction (height direction) parallel to the reference line RL and a direction (width direction) perpendicular to the reference line RL. ). Specifically, assuming that the size in the height direction of the face area FA is Hf and the size in the width direction is Wf, the face area FA is extended by m1 · Hf upward and m2 · Hf downward, A region extended by m3 · Wf to the left and right is set as the deformation region TA. Note that m1, m2, and m3 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 FA, 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. 12, the deformation area TA is set as an area that generally includes an image from the jaw to the forehead in the height direction and includes images of the left and right cheeks in the width direction. That is, in the present embodiment, the above-described coefficients m1, m2, and m3 are set in advance based on the relationship with the size of the face area FA so that the deformation area TA is an area that includes an image in such a range. Yes.

  When the deformation area TA is set, the deformation processing unit 222 divides the deformation area TA into a plurality of small areas (step S1644). FIG. 13 is an explanatory diagram illustrating an example of a method of dividing the deformation area TA into small areas. The deformation processing unit 222 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 of the dividing points D (the number and position of the dividing points D) is performed in a pattern determined in advance according to the deformation mode of the face image. For example, a pattern table (not shown) in which an arrangement pattern is recorded in association with a deformation mode of a face image is facilitated in advance, and the deformation processing unit 222 refers to the pattern table and changes the pattern according to the deformation mode. Dividing points D are arranged. In the following, description will be given by taking as an example a case in which the deformation mode deforms the outline of the face image “smallly in the horizontal direction”.

  As shown in FIG. 13, the division points D are arranged at the intersections of the horizontal division line Lh and the vertical division line Lv and at the intersections of the horizontal division line Lh and the vertical division line Lv and the outer frame of the deformation area TA. . Here, the horizontal dividing line Lh and the vertical dividing line Lv are reference lines for arranging the dividing points D in the deformation area TA. As shown in FIG. 13, in the case of deforming the outline “smallly laterally”, three horizontal dividing lines Lh perpendicular to the reference line RL and four vertical dividing lines Lv parallel to the reference line RL are set. Is done. 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, and the horizontal dividing line Lh2 is arranged near the eye image. The horizontal dividing line Lh3 is arranged in the vicinity immediately above the eye image. The vertical dividing lines Lv1 and Lv4 are arranged outside the cheek line image, and the vertical dividing lines Lv2 and Lv3 are arranged outside the eye corner image. The horizontal dividing line Lh and the vertical dividing line Lv are arranged in 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 becomes the above-described positional relationship as a result. It is executed according to the correspondence with the size.

  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. 13, the division points D located on the horizontal division line Lhi (i = 1 or 2) are referred to as D0i, D1i, D2i, D3i, D4i, and 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.

  As shown in FIG. 13, the arrangement of the dividing points D in the present embodiment is symmetrical with respect to the reference line RL.

  The deformation processing unit 222 divides the deformation area TA into a plurality of small areas by a straight line connecting the arranged dividing points D (that is, the horizontal dividing line Lh and the vertical dividing line Lv). In the present embodiment, as shown in FIG. 13, the deformation area TA is divided into 20 rectangular small areas.

  The deformation processing unit 222 performs image deformation on the deformation area TA of the target image (step S1646). The image is deformed by moving the position of the dividing point D arranged in the deformation area TA and deforming the small area.

  The movement mode (movement direction and movement distance) of the position of each division point D for deformation is determined in advance according to the deformation mode. The deformation processing unit 222 moves the position of the dividing point D with a predetermined moving direction and moving distance.

  FIG. 14 is an explanatory diagram illustrating an example of movement of the position of the dividing point D. As illustrated in FIG. FIG. 15 is a first explanatory diagram illustrating an example of a predetermined moving direction and moving distance. FIG. 15 shows a moving direction and a moving distance when the contour in the face image is deformed “sideways small”. FIG. 15 shows the amount of movement of each division point D along the direction perpendicular to the reference line RL (H direction) and the direction parallel to the reference line RL (V direction). If such data is stored in the internal memory 120 in advance in the form of a table, for example, the deformation processing unit 222 can easily perform various modifications. The unit of the movement amount shown in FIG. 15 is the pixel pitch PP of the target image. For the H direction, the amount of movement to the right side is represented as a positive value, the amount of movement to the left side is represented as a negative value, and for the V direction, the amount of movement upward is positive. It is expressed as a value, and the downward movement amount is expressed as a negative value. For example, the dividing point D11 is moved to the right along the H direction by a distance of 7 times the pixel pitch PP, and is not moved along the V direction (0 times the pixel pitch PP). For example, the division point D22 is not moved because the movement amount is zero in both the H direction and the V direction.

  In this embodiment, the division points D (for example, the division points D10 shown in FIG. 13) located on the outer frame of the deformation area TA are set so that the boundary between the inner and outer images of the deformation area TA does not become unnatural. The position is not moved. Therefore, in FIG. 15, the movement mode for the dividing point D located on the outer frame of the deformation area TA is not defined.

  In FIG. 14, the division point D before the movement is indicated by a white circle, and the division point D after the movement or the division point D without the movement of the position is indicated by a black circle. Further, the divided point D after the movement is referred to as a divided point D ′. For example, the position of the dividing point D11 is moved rightward in FIG. 14 to become a dividing point D′ 11.

  In the present embodiment, all combinations of two division points D (for example, combinations of division points D11 and D41) that are in a symmetric positional relationship with respect to the reference line RL are the same after the movement of the division point D. The movement mode is determined so as to maintain a symmetrical positional relationship with respect to the line RL.

  For each small area constituting the deformation area TA, the deformation processing unit 222 determines that the small area image in the state before the position movement of the dividing point D is the image of the small area newly defined by the position movement of the dividing point D. In this way, an image deformation process is performed. For example, in FIG. 14, an image of a small region (small region indicated by hatching) having vertices at the division points D11, D21, D22, and D12 is divided into points D′ 11, D′ 21, D22, and D′ 12. Is transformed into an image of a small area with the vertex at.

  FIG. 16 is an explanatory diagram showing the concept of the image deformation method. In FIG. 16, the dividing point D is indicated by a black circle. In FIG. 16, for simplification of description, regarding 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. 16, 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 this 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 the figure, 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. 17 is an explanatory diagram showing the concept of an image deformation processing method in a triangular area. In the example of FIG. 17, 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. 17, the position of the pixel of interest p ′ in the image of the triangular area s′t′u ′ after deformation 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. The deformation processing unit 222 performs a deformation process by defining a triangular area as described above for each small area constituting the deformation area TA shown in FIG. 13 and deforms an image in the deformation area TA.

  As described above, the face deformation process has been described by taking the case where the contour of the face image is “smallly laterally” deformed as a specific example. However, for other deformation modes, the movement direction and the movement distance shown in FIG. By changing it accordingly, it can be executed easily. FIG. 18 is a second explanatory diagram illustrating an example of a predetermined moving direction and moving distance. FIG. 18 shows the movement direction when the contour of the face image is “smallly vertically” deformed, when the eyes of the face image are “largely vertically” deformed, and when the eyes of the face image are “largely vertically and horizontally” deformed. And the moving distance are shown respectively.

  When the image quality adjustment process is completed, the image quality adjustment unit 220 instructs the display processing unit 250 to display the target image after the image quality adjustment on the display unit 150. FIG. 19 is an explanatory diagram illustrating an example of the display unit 150 on which a target image after image quality adjustment is displayed. The display unit 150 on which the target image after the image quality adjustment is displayed allows the user to confirm the result of the image quality adjustment according to the selected picture making type. When the user is satisfied with the image quality adjustment result and selects the “save” button (FIG. 5: step S200), the image data representing the target image after image quality adjustment is saved accordingly (step S200). S400). For example, the target image (bitmap data) after image quality adjustment is compressed into a predetermined format such as JPEG and stored as an image file according to a predetermined file format such as EXIF. Such an image file may be stored in, for example, the inserted memory card MC. In such a case, the image file of the target image after image quality adjustment may be overwritten on the image file of the target image before image quality adjustment, or may be stored as a different image file.

  When the user is satisfied with the image quality adjustment result and selects the “print” button (FIG. 5: step S200), the print processing unit 260 executes a print process of the target image after the image quality adjustment (step S300). FIG. 20 is a flowchart showing the flow of the printing process. The print processing unit 260 converts the resolution of the image data of the target image after the image quality adjustment to a resolution suitable for the printing process by the printer engine 160 (step S310), and prints the image data after the resolution conversion in the printer engine 160. Is converted into ink color image data expressed in gradation with a plurality of ink colors used in step S320. In this embodiment, it is assumed that the plurality of ink colors used for printing in the printer engine 160 are four colors of cyan (C), magenta (M), yellow (Y), and black (K). Furthermore, the print processing unit 260 generates dot data indicating the ink dot formation state for each print pixel by executing halftone processing based on the gradation value of each ink color in the ink color image data (step S330), dot data is arranged to generate print data (step S340). The print processing unit 260 supplies the generated print data to the printer engine 160, and causes the printer engine 160 to print the target image (step S350). Thereby, the printing of the target image after the image quality adjustment is completed.

  If the user is not satisfied with the result and selects the “Return” button, for example, the display unit 150 displays the picture creation type selection screen shown in FIG. 7, and the user selects the picture creation type again. (Not shown).

  According to the first embodiment described above, since the deformation process for deforming the face image and the pixel value process for adjusting the pixel value are associated as one image quality adjustment process, the user selects the image quality adjustment process. Therefore, image quality adjustment that combines pixel value processing and deformation processing can be easily used.

  Further, in the present embodiment, one image quality adjustment process including a combination of a deformation process for deforming a face image and a pixel value process for adjusting a pixel value includes the image quality adjustments such as “cute”, “easy”, and “lively”. It is associated with a picture making type having a name representing the impression that the process brings to the target image. As a result, the user can sensuously use a preferable combination of the deformation process and the pixel value process. For example, in order to give a “cute” impression to a face image, it is effective to combine a pixel value process that weakens skin contrast and a face deformation process that thins the face outline vertically. However, it is not easy for a user who does not have sufficient knowledge of image processing or camera to appropriately use such a combination and perform image quality adjustment processing on a target image so as to have a desired impression. According to the present embodiment, a set of a plurality of processes that bring the same or similar impression to the target image is provided as one image quality adjustment process. Therefore, the user can easily use the image quality adjustment process to perform a desired process. An image having an impression can be obtained.

  Furthermore, in this embodiment, the image type of the target image is automatically determined, and several image quality adjustment processes suitable for the image type are specified from among a number of image quality adjustment processes that can be performed. A selection screen for displaying the adjustment process (the corresponding picture making type) according to the priority order is provided as a user interface (FIG. 7). Thereby, it is possible to reduce a burden of the user selecting an image quality adjustment process suitable for the target image. The image processing apparatus is desired to be able to execute a wide variety of image quality adjustment processes. On the other hand, if the available image quality adjustment processes increase, there is a disadvantage that the operation burden on the user increases. Such inconvenience can be reduced.

B. Modification of the first embodiment:
First modification of the first embodiment:
In the first embodiment, the selection screen is generated with reference to the image type database 310. However, instead of this, the selection made through the selection screen is learned, and the learning result is obtained. May be used to generate a selection screen.

  In addition to the configuration of the printer 100 according to the first embodiment, the printer according to this modification includes a selection learning unit 244 and a selection learning database 330 as indicated by a broken line in FIG. Since the other configuration of the printer according to the present modification is the same as that of the printer 100 according to the first embodiment, the same components are denoted by the same reference numerals as those of the printer 100 according to the first embodiment (FIG. 1). ), And the description thereof is omitted.

  FIG. 21 is a diagram illustrating an example of the contents of the selection learning database. In the selection learning database 330, the selection result of the picture making type by the user is recorded in association with the image type of the target image in the form of the number of selections. For example, in the example shown in FIG. 21, it is recorded that the picture making type “easy” is selected 5 times and “Genki” is selected once for the target image whose image type is “landscape”.

  FIG. 22 is a flowchart showing the flow of the picture making process in this modification. Steps S100 to S400 of the picture making process in the present modification are the same as steps S100 to S400 of the picture making process in the first embodiment shown in FIG.

  In the picture making process in the present modification, when the printing process (step S300) or storage (step S400) of the target image ends, the selection learning unit 244 of the processing content determination unit 240 learns the picture making selection result (steps). S500). Specifically, the selection learning unit 244 records the picture creation type applied to the target image selected by the user and finally stored or printed together with the image type of the target image in the selection learning database 330.

  When learning the picture creation selection result, the processing content determination unit 240 updates the image type database 310 as necessary in accordance with the change of the selection learning database 330 (step S600). For example, when there is a picture making type selected five or more times for a certain image type in the selection learning database 330, the processing content determination unit 240 sets the picture making type as the image type in the image type database 310. Record as the highest priority painting type associated. When there are a plurality of picture making types selected five or more times, the processing content determination unit 240 determines the priority order in descending order of the number of selections and records it in the image type database 310. The picture creation type recorded by default in the image type database 310 is recorded with a lower priority following the picture creation type selected five or more times.

  By updating the image type database 310 in accordance with the change of the selection learning database 330, a selection screen is generated with reference to the updated image type database 310 in the next picture making process. As a result, the selection screen generation unit 242 can generate a selection screen that takes into account the user's selection results. Therefore, according to this modification, it is possible to further reduce the user's operation burden for selecting the image quality adjustment process.

  The above-described aspect of the selection learning database 330 is an example, and various modifications may be made to the aspect for learning the user's selection result or the algorithm for reflecting the learning result recorded in the selection learning database 330 in the generation of the selection screen. Is possible. For example, the selection learning database 330 may record the picture making type selected by the user for each person represented in the face image. Specifically, the selection learning database 330 includes person characteristics (e.g., represented by vectors representing positions, sizes, and directions of components such as eyes, mouths, and contours of face images) and person identifiers. Are recorded in association with each other. In the selection learning database 330, the picture making type selected for the target image including the face image specified by the person identifier is recorded in the form of the number of selections in association with the person identifier. When the face area FA is detected in the target image, the selection learning unit 244 further detects components such as eyes, mouths, and contours of the face image corresponding to the face area FA, and calculates the characteristics of the person. The selection learning unit 244 compares the calculated feature of the person with the feature of the person whose identifier is recorded in the selection learning database 330. If the same person is already recorded in the selection learning database 330, the picture creation type selection result is recorded in association with the identifier of the person. When the same person is not recorded in the selection learning database 330, the feature of the person is newly recorded together with the identifier, and the picture making type selected by the user is recorded in association with the identifier. The selection screen generation unit 242 calculates the characteristics of the person in the face image included in the target image, identifies the person in the face image, and refers to the selection learning database 330 to determine the tendency of selection of the picture making type. The selection screen can be generated in consideration of each person represented in the face image included in the image.

Second modification of the first embodiment:
A list display button may be provided on the selection screen in the above embodiment as indicated by a broken line in FIG. The list display button is a user interface for accepting an instruction to display possible picture creation type candidates regardless of the image type determination result. When the user selects such a list display button, a selection screen shown in FIG.

  FIG. 23 is a first diagram illustrating another example of the selection screen. In the selection screen shown in FIG. 23, candidates for picture making types that can be selected by the user are displayed in a list in association with image types. In the example of FIG. 23, the candidates for the picture making type associated with the image types “portrait” and “landscape” are displayed. On this selection screen, when the user selects the next candidate button, the selection screen is operated such that the image creation type candidates associated with the image types “evening scene” and “night scene” are displayed. Thus, the user can select all picture making types recorded in the image type database 310. By making such a selection screen displayable in accordance with a user instruction, for example, the picture making type desired by the user is not included in the picture making type candidates narrowed down according to the image type (FIG. 7). Can respond.

-Third modification of the first embodiment:
Instead of the image processing according to the first embodiment shown in the flowchart of FIG. 6, the image processing shown in the flowchart of FIG. 24 may be performed.

  FIG. 24 is a flowchart illustrating the flow of image processing according to the third modification of the first embodiment. In FIG. 24, the processing of steps S110, S120, S130, and S160 ending with “0” is the same as the processing of the step having the same name and the same sign shown in FIG.

  In the image processing according to this modification, when a picture making type candidate is acquired (step S130), the processing content determination unit 240 selects pictures to be adopted in descending order of priority from the acquired picture making type candidates. The making type is determined (step S155). For example, when the image type is “portrait”, the acquired picture creation candidates are “friendly”, “cute”, “beautiful”, “lively”, and “good” in descending order of priority (FIG. 2). Therefore, first, “friendly” is determined as a picture making type to be adopted.

  When the picture creation type is determined, the image quality adjustment unit 220 performs image quality corresponding to the determined picture creation type for the target image, as in the image quality adjustment process (FIG. 6: step S160) in the first embodiment. Adjustment processing is executed (step S160).

  When the image quality adjustment process is completed, a selection screen for the user to select a picture making type is displayed together with the target image after the image quality adjustment (step S175). Specifically, the selection screen generation unit 242 generates a selection screen including the target image after the image quality adjustment, and the display processing unit 250 displays the generated selection screen.

  FIG. 25 is a second diagram illustrating another example of the selection screen. When the user selects the determination button on the selection screen shown in FIG. 25, the image processing in the present modification is terminated, and the process proceeds to saving or printing (FIG. 5). On the other hand, when the user selects the next candidate button on the selection screen shown in FIG. 25, the process returns to step S155 to select a picture making type candidate with the next highest priority from the picture making type determined in the previous step S155. It is newly decided as a picture making type to be adopted. Thereafter, the processes in steps S155 to S185 are repeated until the user selects the determination button on the selection screen.

  According to the present modification described above, the target image subjected to the image quality adjustment process corresponding to the picture creation type candidate is displayed on the selection screen according to the priority order determined according to the image type. Therefore, there is a high possibility that the target image on which the image quality adjustment process desired by the user has been performed is displayed on the selection screen at an early stage, and the user can efficiently select the desired image quality adjustment process. Further, the user can select an image quality adjustment process to be finally applied to the target image while sequentially viewing the target images that have been subjected to the image quality adjustment process as candidates.

  In the selection screen shown in FIG. 25, the target image after the image quality adjustment is displayed one by one. For example, the target image that has been subjected to an arbitrary number of different image quality adjustment processes depending on the size of the display unit 150 May be displayed.

-4th modification of 1st Example:
In the above embodiment, the image data representing the target image is analyzed to determine the image type of the target image, but instead, it can be determined by various methods. For example, information attached to the image data of the target image may be used. FIG. 26 is an explanatory diagram conceptually illustrating an example of an image file including image data and attached information associated with the image data. The image file 500 includes an image data storage area 501 for storing image data and an attached information storage area 502 for storing attached information. The attached information is stored so that various parameters as attached information can be specified using a tag in accordance with, for example, a TIFF (Tagged Image File Format) format. The attached information shown enlarged in FIG. 26 is information (EXIF information) defined by the EXIF (Exchangeable Image File Format) standard. The EXIF information is information relating to an image when image data is generated (at the time of shooting) in an image data generation device such as a digital camera. Such EXIF information may include shooting scene type information indicating the type of shooting scene, as shown in FIG. In the shooting scene type information, “person”, “landscape”, “night view”, and the like are described.

  When shooting scene type information is associated with the image data of the target image as attached information, the image type determination unit 230 acquires the shooting scene information and recognizes the shooting scene of the target image. The image type may be determined.

  The attached information used for determining the image type is not limited to EXIF information. For example, the attached information storage area 502 may store control information of an image output device such as a printer, specifically, printer control information that specifies a correction level of image quality adjustment processing such as sharpness and contrast. . Such control information of the image output apparatus is stored in, for example, a MakerNote data storage area set in the attached information storage area 502. The MakerNote data storage area is an undefined area that is open to manufacturers such as an image data generation apparatus or an image output apparatus. Such image output device control information may be used alone or in combination with image data analysis or EXIF information for image type determination.

C. Second embodiment:
·Constitution:
FIG. 27 is a block diagram showing a configuration of a printer 100a as an image processing apparatus in the second embodiment of the present invention. Since the hardware configuration of the printer 100a of the second embodiment is the same as that of the printer 100 (FIG. 1) of the first embodiment, the same reference numerals as those in FIG. The description is omitted.

  The printer 100a of the second embodiment is different from the printer 100 of the first embodiment in the configuration of functional units (computer programs) provided in the internal memory 120. In the internal memory 120 of the printer 100a, an image data acquisition unit 210, an image quality adjustment unit 220, an image type determination unit 230, a processing content determination unit 240a, a display processing unit 250, and a print processing unit 260 are stored. ing. Among these, the image data acquisition unit 210, the image quality adjustment unit 220, the image type determination unit 230, and the display processing represented by the same reference numerals as the functional units stored in the internal memory 120 of the printer 100 of the first embodiment. Since the unit 250 and the print processing unit 260 are the same as the functional units having the same reference numerals in the first embodiment, the description thereof is omitted.

  The processing content determination unit 240a in the second embodiment includes an image quality adjustment UI generation unit 248 instead of the selection screen generation unit 242 in the first embodiment. As will be described later, the image quality adjustment UI generation unit 248 provides a user interface (image quality adjustment UI) for the user to operate image quality adjustment processing for dynamically adjusting contrast and brightness.

Operation As in the printer 100 of the first embodiment, when the memory card MC is inserted into the card slot 172, the printer 100a of the second embodiment displays the image stored in the memory card MC by the display processing unit 250. A user interface (FIG. 7) including a list display is displayed on the display unit 150. In the user interface, when one (or a plurality) of images are selected by the user and a picture creation button is selected, the printer 100a of the second embodiment performs a predetermined image on the selected image. Processing is performed, and processing (picture making processing) for printing and saving the image after image processing is executed.

  FIG. 28 is a flowchart illustrating a flow of a picture making process performed by the printer 100a according to the second embodiment. When the picture making process is started, an image quality adjustment UI is displayed (step S1000). Specifically, the image quality adjustment UI generation unit 248 of the processing content determination unit 240 a generates an image quality adjustment UI, and the display processing unit 250 displays the generated image quality adjustment UI on the display unit 150.

  FIG. 29 is an explanatory diagram illustrating an example of an image quality adjustment UI according to the second embodiment. As shown in FIG. 29, the image quality adjustment UI shown in FIG. 29 includes a first level bar LB1 that is an interface for accepting an instruction of a contrast adjustment level from a user together with a target image, and an instruction of an adjustment level of brightness. Includes a second level bar LB2 that is an interface for receiving from the user. The image quality adjustment UI further includes a first check box CB1 that is an interface for receiving an instruction to maintain the impression of the target image from the user.

  Next, the processing content determination unit 240a determines whether or not an instruction from the user has been received via the image quality adjustment UI (step S1010). When the user selects the determination button on the image quality adjustment UI, the processing content determination unit 240a performs a process of printing and saving the image data of the target image currently displayed on the image quality adjustment UI (step S1050), The picture making process ends.

  On the other hand, when the user receives an instruction to change the brightness or contrast adjustment level from the user via the image quality adjustment UI, the processing content determination unit 240a determines whether the brightness or the Then, the pixel value processing unit 224 of the image quality adjustment unit 220 executes pixel value processing for adjusting the contrast (step S1020). Specifically, when the change of the brightness adjustment level is received, the processing content determination unit 240a has a value b + or b− indicating the amount of change shown in FIG. 9A according to the change of the adjustment level. To decide. In addition, when the change of the contrast adjustment level is received, the processing content determination unit 240a determines a value k + or k− indicating the change amount illustrated in FIG. 9B according to the change of the adjustment level. The pixel value processing unit 224 determines the shape of the tone curve using the determined value b + or b− or the value k + or k−, and the original image data of the target image (image data that has not undergone image quality adjustment). The pixel value processing for adjusting the brightness or contrast is executed for all the pixel values.

  When the pixel value processing is performed, the processing content determination unit 240a determines whether or not an impression maintenance instruction has been issued by detecting whether or not the first check box CB1 on the image quality adjustment UI is checked. (Step S1030). When the first check box CB1 is not checked, that is, when the impression maintenance is not instructed (step S1030: NO), the processing content determination unit 240a returns the processing to step S1000.

  On the other hand, when the first check box CB1 is not checked, that is, when the impression maintenance is not instructed (step S1030: YES), the face image is deformed so as to maintain the impression the face image gives to the viewer. The face deformation process is executed (step S1040).

  FIG. 30 is a diagram for explaining the relationship between brightness and contrast and the impression of a face image. FIG. 31 is a first diagram illustrating face deformation processing for maintaining an impression. FIG. 32 is a second diagram illustrating face deformation processing for maintaining an impression.

  It is empirically understood that when the brightness is changed without deformation in the face image, the face image looks thinner as it becomes darker and the face image appears thicker as it becomes brighter, as conceptually shown by arrows in FIG. ing. Further, when the contrast is changed without being deformed, the face image looks finer as the contrast is harder (stronger), and the face image becomes softer (weaker) as conceptually indicated by the arrows in FIG. Experience has shown that it looks thick.

  In the first map shown in FIG. 31, a line CL1 is a face impression maintaining line related to contrast. When the first combination of the deformation amount of the face width and the adjustment level of the contrast and the second combination are on the same face impression maintenance line CL1, the image quality adjustment processing of the first combination is performed. The face image and the face image that has been subjected to the image quality adjustment processing of the second combination appear to have the same impression regarding the thickness of the face (different from the thickness on the actual image). When the amount of deformation of the face width is a positive value, the face image is deformed thickly. When the amount of deformation is negative, the face image is deformed thinly. In the second map shown in FIG. 32, a line CL2 is a face impression maintenance line related to brightness. When the first combination of the deformation amount of the face width and the adjustment level of the brightness and the second combination are on the same face impression maintenance line CL2, the image quality adjustment processing of the first combination is performed. The face image that has been subjected to the image quality adjustment processing of the second combination appears to have the same impression regarding the thickness of the face (different from the thickness on the actual image).

  In the face deformation process in the second embodiment, the face is changed so as to bring a change in the face image opposite to the brightness change by the pixel value process in step S1020 or the change in the impression of the face image caused by the change in contrast (FIG. 30). Deform. Specifically, the processing content determination unit 240a stores a first map shown in FIG. 31 and a second map shown in FIG. A case where the contrast of the target image is changed from the adjustment level k1 to the adjustment level k2 in the pixel value processing in step S1020 will be described as a specific example (FIG. 31). The processing content determination unit 240a has a point P1 on the first map (FIG. 31) determined by the contrast adjustment level k1 and the current face deformation amount (0 in the example of FIG. 31), and the contrast adjustment level k2. And the face deformation amount n1 after the face deformation process so that the point P2 on the first map determined by the face deformation amount n1 after the face deformation process is positioned on the same face impression maintenance line CL1. Is calculated.

  When the deformation amount n1 is determined, the deformation processing unit 222 of the image quality adjustment unit 220 uses the deformation amount n1 to deform the face image that has been subjected to the pixel value processing in step S1020. A specific method of deforming the face image is as described with reference to FIGS. 11 to 18 in the first embodiment. It can be seen that the width of the face image can be deformed to a predetermined level by changing the moving direction and moving distance of the dividing points shown in FIG. 15 according to the determined deformation amount n1.

  Next, a case where the brightness of the target image is changed from the adjustment level b1 to the adjustment level b2 in the pixel value processing in step S1020 will be described as a specific example (FIG. 32). The processing content determination unit 240a adjusts the brightness of the point P3 on the second map (FIG. 32) determined by the brightness adjustment level b1 and the current face deformation amount (n3 in the example of FIG. 32). Deformation of the face after the face deformation process so that the point P4 on the second map determined by the level b2 and the deformation amount n2 of the face after the face deformation process is located on the same face impression maintenance line CL2 The quantity n4 is calculated. When the deformation amount n4 is determined, the deformation processing unit 222 deforms the face image that has been subjected to the pixel value processing in step S1020, using the determined deformation amount n4.

  As understood from the above description, the face deformation process (face width) and the pixel value process (brightness, contrast) in this embodiment are the impressions of the thickness of the face image (appearance) among the changes that each brings to the target image. Act to cancel each other's changes. For example, when pixel value processing for brightening an image is performed, the face image appears to be thick, and thus face deformation processing is performed to make the face image thinner. Further, when the pixel value process for increasing the contrast of the image is performed, the face image appears to be thinned, so that the face deformation process is performed so that the face image is thickened.

  When the face transformation process ends, the process returns to step S1000, and the image quality adjustment UI updated to display the target image after the image quality adjustment is displayed on the display unit 150 in step S1000. In this manner, the user's instruction regarding image quality adjustment received via the image quality adjustment UI is dynamically reflected in the target image.

  According to the second embodiment described above, the user can easily use image processing that combines face deformation processing and pixel value processing. For example, in the past, when a user wants to slightly brighten a favorite portrait image (an image of a person's face being a main subject) and simply instructs an image quality adjustment process to increase the brightness, the impression of the portrait face image May change and the user may feel uncomfortable. In such a case, the user can recognize that the impression of the face image has changed because the face image looks thicker due to the brightening of the image, and can perform deformation processing to narrow the face. However, there are cases where it is difficult for a user who has insufficient knowledge of image processing to recognize that the face image looks thick. Even if it is recognized that the face image appears to be thick, it is not easy to determine how much the face image should be deformed. According to the present embodiment, the pixel value processing and the face deformation processing are associated in advance so as to maintain the impression regarding the thickness of the face image (FIG. 31: first map, FIG. 32: second). Map), if the first check box CB1 is checked and pixel value processing (in this embodiment, adjustment of brightness or contrast) is performed, the face deformation processing and pixel value processing are combined, The impression of the face image can be easily maintained.

D. Modification of the second embodiment:
First modification of the second embodiment:
In the second embodiment, the pixel value process and the face deformation process are associated with each other so that the change in impression that the pixel value process brings to the target image and the change in impression that the face deformation process brings to the object cancel each other. However, it is not limited to this. For example, the pixel value process and the face deformation process may be associated with each other so that the change in the impression that the pixel value process brings to the target image and the change in the impression that the face deformation process brings to the object are the same or similar to each other. . Such an example will be described below as a first modification of the second embodiment.

  FIG. 33 is a flowchart showing the flow of the picture making process according to the first modification of the second embodiment. FIG. 34 is an explanatory diagram illustrating an example of an image quality adjustment UI according to the first modification of the second embodiment. FIG. 35 is a diagram for explaining the relationship between the deformation amount and contrast of a face image and the impression of the face image.

  Since the configuration of the printer according to this modification is the same as that of the printer 100a (FIG. 27) in the second embodiment described above, description thereof will be omitted and only the picture making process will be described.

  When the picture making process in this modification is started, an image quality adjustment UI shown in FIG. 31 is displayed (step S2010). As shown in FIG. 31, the image quality adjustment UI shown in FIG. 31 instructs the adjustment level of the image quality adjustment process (impression application process) to give a “beautiful” impression to the face image of the target image together with the target image from the user. A third level bar LB3 which is an interface for receiving is included. The image quality adjustment UI shown in FIG. 1. Maintain contrast. 2. Maintain face width. Radio buttons RB <b> 1 to RB <b> 3, which are interfaces for accepting any one of the instructions exclusively from the user without any limitation, are included.

  Next, the processing content determination unit 240a determines whether or not an instruction from the user has been received via the image quality adjustment UI (step S2020). When the user selects the determination button on the image quality adjustment UI, the processing content determination unit 240a performs a process of printing / saving the image data of the target image currently displayed on the image quality adjustment UI (step S2080), The picture making process ends.

  On the other hand, when the user receives an instruction to change the adjustment level of the impression imparting process from the user via the image quality adjustment UI, the processing content determination unit 240a determines whether the radio buttons RB1 to RB3 on the image quality adjustment UI are selected. Is detected to determine whether or not the image quality adjustment processing is limited (step S2030).

  When the radio button RB1 is selected, that is, when the maintenance of the contrast is instructed, the processing content determination unit 240a executes the impression imparting process by the face deformation process to the deformation processing unit 222 of the image quality adjustment unit 220. (Step S2040). When the radio button RB2 is selected, that is, when the maintenance of the face width is instructed, the processing content determination unit 240a causes the pixel value processing unit 224 to execute the impression imparting processing by the pixel value processing (Step S1). S2070). When the radio button RB3 is selected, that is, when there is no limitation, the processing content determination unit 240a gives an impression that combines the facial deformation processing and the pixel value processing in the deformation processing unit 222 and the pixel value processing unit 224. The process is executed (steps S2050 and S2060).

  As conceptually shown by the broken-line arrows in FIG. 35, when the contrast of the face image is hardened (intensified) within a predetermined range, a “beautiful” impression can be given to the face image, and the face image It has been empirically understood that a “beautiful” impression can be given to a face image by making it thin within a range of (making the deformation amount a negative value).

  In the impression imparting process only by the face deformation process (step S2040), as shown by an arrow BE1 in FIG. 35, the face image deformation amount is set to a negative value according to the designated adjustment level, and the face image is thinned. This is done by deforming and the contrast is maintained. The impression imparting process (step S2070) based only on the pixel value process is executed by increasing (intensifying) the contrast according to the instructed adjustment level as shown by the arrow BE2 in FIG. 35, and the face width is maintained. Is done.

  Then, in the impression imparting process (steps S2050 and S2060) that combines the face deformation process and the pixel value process, as shown by an arrow BE3 in FIG. The value is set to a value, and the face image is deformed finely, and the contrast is hardened (strengthened) according to the instructed adjustment level.

  When the impression imparting process ends, the process returns to step S2010. In step S2010, the image quality adjustment UI updated to display the target image after the impression imparting process is displayed on the display unit 150. In this way, the user's instruction regarding impression processing received through the image quality adjustment UI is dynamically reflected in the target image.

  Also according to this modification described above, the user can easily use image processing that combines face deformation processing and pixel value processing. In addition, since the face deformation process and the pixel value process that cause the same or similar change (in this modification example, the impression of “beautiful”) is associated, either the face deformation process or the pixel value process With only one of them, a larger change can be applied to the target image in a desired direction than when image quality adjustment is performed. For example, when a user wants to give a “beautiful” impression to a face image, a great effect can be obtained by combining a process of making contrast high and a process of reducing the width of the face image. It is difficult for a user with insufficient processing knowledge to correctly determine such a combination. If a pixel value process that gives a “beautiful” impression to a face image is mistakenly combined with a face deformation process that gives a “cute” impression to the face image, a desired effect cannot be obtained. According to the present embodiment, since the pixel value processing and the face deformation process are associated in advance as the impression imparting process for imparting a “beautiful” impression, the face deformation process and the pixel value process are combined. , You can easily change the impression of the face image.

-Second modification of the second embodiment:
The combination of the face deformation process and the pixel value process in the second embodiment and the first modification of the second embodiment is an example, and various other combinations can be used. For example, a pixel value process that reduces the contrast of the face image and a face deformation process that reduces the face image vertically and reduces the face image vertically reduces the impression of the face image. It is good also as performing the impression provision process.

E. Other variations:
In the above-described embodiment and its modifications, the processing content is shown by a flowchart, but this is only an example, and the order of each step may be changed or execution of some steps may be omitted. For example, in the picture making process in the second embodiment shown in FIG. 28, before or after the pixel value process (FIG. 28: step S1020), it is determined whether or not the impression maintenance check box is checked (FIG. 28: step S1030). Pixel value processing may be performed after performing face deformation processing (FIG. 28: step S1040). In such a case, after the face deformation process is performed, the pixel value process that causes a conflicting impression change is performed so as to cancel the change that the face deformation process causes to the image deformation.

  The association between the pixel value processing and the face deformation processing may be associated with one as the main and the other as the subordinate, or may be associated with each other on an equal basis. For example, in the first modification of the first embodiment and the second embodiment, the pixel value process and the face deformation process are associated with each other in order to give an impression such as “cute” or “beautiful” to the target image. You might be able to think that In the second embodiment, when pixel value processing is performed in order to obtain a desired change (such as brightening an image), an undesired change (face appears to be thick) that is incidentally introduced into the target image. Since the face deformation process is performed so as to cancel out (), it may be considered that the pixel value process is the main and the face deformation process is the sub.

  Also, resolution conversion and color conversion (steps S310 and S320 in FIG. 20) in the printing process may be executed before the picture making process. In the picture making process in the second embodiment shown in FIG. 33, the pixel value process (step S2050) and the face deformation process (step S2060) may be interchanged.

  In the above-described embodiment, the detection of the face area FA is executed. However, instead of the detection of the face area FA, for example, acquisition of information on the face area FA through user designation may be performed.

  In the above-described embodiment and its modifications, the picture making process by the printers 100 and 100a as the image processing apparatus has been described. However, part or all of the picture making process is, for example, image data such as a digital camera except for the printing process. It may be executed by a control computer or an image processing chip of the generation device, or may be executed by a personal computer. The printers 100 and 100a are not limited to ink jet printers, and may be other types of printers such as laser printers and sublimation printers.

  In the above embodiment, a part of the configuration realized by hardware may be replaced by software, and conversely, a part of the configuration realized by software may be replaced by hardware.

  As mentioned above, although the Example and modification of this invention were demonstrated, this invention is not limited to these Example and modification at all, and implementation in a various aspect is possible within the range which does not deviate from the summary. It is.

By the way, the embodiment described with reference to the above-described embodiments and modification examples, particularly, reduces the burden on the user for selecting an application process to be applied to the target image from among a plurality of types of image quality adjustment processes. If it is expressed abstractly from the viewpoint, for example, it can be expressed as follows.
An image processing apparatus,
An image quality adjustment unit capable of executing multiple types of image quality adjustment processing;
About the target image, a type determination unit that determines an image type determined according to image characteristics;
A selection screen generating unit for generating a selection screen for selecting an application process to be applied to the target image from among the plurality of types of image quality adjustment processes, according to the determined image type;
An image processing apparatus comprising:

1 is a block diagram illustrating a configuration of a printer 100 as an image processing apparatus according to a first embodiment. The figure which shows the content of an image type database notionally. The figure which shows the content of the process content database notionally. Explanatory drawing which shows an example of the user interface containing the list display of an image. 3 is a flowchart showing a flow of picture making processing by the printer of the first embodiment. 3 is a flowchart showing a flow of image processing according to the first embodiment. The figure which shows an example of the selection screen of 1st Example. 6 is a flowchart illustrating a flow of image quality adjustment processing according to the first embodiment. The 1st figure explaining an example of pixel value processing. The figure for demonstrating a cheek coloring process. The flowchart which shows the flow of the face deformation process of 1st Example. The figure explaining the setting of a deformation | transformation area | region. Explanatory drawing which shows an example of the division | segmentation method into a small area | region of a deformation | transformation area | region. Explanatory drawing which shows an example of the movement of the position of a dividing point. The 1st explanatory view showing an example of a predetermined moving direction and moving distance. Explanatory drawing which shows the concept of the deformation | transformation method of an image. Explanatory drawing which shows the concept of the deformation | transformation processing method of the image in a triangular area | region. The 2nd explanatory view which shows an example of a predetermined moving direction and moving distance. Explanatory drawing which shows an example of the display part on which the target image after image quality adjustment was displayed. 6 is a flowchart showing a flow of printing processing. The figure which shows an example of the content of the selection learning database. The flowchart which shows the flow of the picture making process in the 1st modification of 1st Example. The 1st figure which shows the other example of a selection screen. 10 is a flowchart showing a flow of image processing according to a third modification of the first embodiment. The 2nd figure which shows the other example of a selection screen. Explanatory drawing which shows notionally an example of the image file containing the attached information linked | related with image data with image data. FIG. 9 is a block diagram illustrating a configuration of a printer as an image processing apparatus according to a second embodiment. 10 is a flowchart showing a flow of picture making processing by the printer of the second embodiment. It is explanatory drawing which shows an example of the image quality adjustment UI in 2nd Example. The figure for demonstrating the relationship between brightness and contrast, and the impression of a face image. The 1st figure explaining the face deformation process for impression maintenance. The 2nd figure explaining the face deformation | transformation process for impression maintenance. The flowchart which shows the flow of the picture making process of the 1st modification of 2nd Example. Explanatory drawing which shows an example of the image quality adjustment UI in the 1st modification of 2nd Example. The figure for demonstrating the relationship between the deformation amount and contrast of a face image, and the impression of a face image.

Explanation of symbols

100, 100a ... Printer 110 ... CPU
DESCRIPTION OF SYMBOLS 120 ... Internal memory 140 ... Operation part 150 ... Display part 160 ... Printer engine 170 ... Card interface 172 ... Card slot 210 ... Image data acquisition part 220 ... Image quality adjustment part 222 ... Deformation processing part 224 ... Pixel value processing part 230 ... Image type Determination unit 240, 240a ... Processing content determination unit 242 ... Selection screen generation unit 244 ... Selection learning unit 248 ... Image quality adjustment UI generation unit 250 ... Display processing unit 260 ... Print processing unit 310 ... Image type database 320 ... Processing content database 330 ... Selective learning database 500 ... Image file 501 ... Image data storage area 502 ... Attached information storage area MC ... Memory card

Claims (6)

An image processing apparatus,
A first processing unit that performs a deformation process for deforming an area included in the target image;
A second processing unit that performs a pixel value process for adjusting a pixel value of a pixel included in the target image;
About the target image, a type determination unit that determines an image type determined according to image characteristics;
A processing content determination unit that determines processing content including the deformation processing and the pixel value processing according to the determined image type ;
The deformation process and the pixel value process are associated with each other as one image quality adjustment process,
The deformation processing and the pixel value processing performed as the one image quality adjustment processing are image quality adjustment processing of the processing content determined by the processing content determination unit, and are respectively the same as at least a part of the target image. An image processing apparatus that is an image quality adjustment process that gives an impression. The image processing apparatus according to claim 1.
The target image includes a face image,
The deformation processing and the pixel value processing is a processing that result same impression to each of the facial image, the image processing apparatus. The image processing apparatus according to claim 1 or 2 ,
The processing content determination unit determines the selection screen for selecting a processing content to be performed on the target image from a plurality of types of candidate processing content each including the deformation processing and the pixel value processing. An image processing apparatus including a selection screen generation unit that generates according to an image type. The image processing apparatus according to claim 3 .
The selection screen generating unit determines an order of priority of the plurality of types of candidate processing contents according to the determined image type, and generates the selection screen according to the priority order. An image processing method comprising:
A deformation process step of performing a deformation process to deform an area included in the target image;
A pixel value processing step for performing pixel value processing for adjusting a pixel value of a pixel included in the target image;
For the target image, a determination step of determining an image type determined according to image characteristics;
Determining a process content including the deformation process and the pixel value process according to the determined image type ,
The deformation process and the pixel value process are associated with each other as one image quality adjustment process,
The deformation processing and the pixel value processing performed as the one image quality adjustment processing are image quality adjustment processing of processing contents determined by the determination step, and each has the same impression on at least a part of the target image. An image processing method that is image quality adjustment processing. A computer program for image processing,
A first function for performing deformation processing for deforming an area included in the target image;
A second function of performing a pixel value process for adjusting a pixel value of a pixel included in the target image;
A third function for determining an image type determined in accordance with an image characteristic for the target image; and a processing content including the deformation process and the pixel value process according to the determined image type. 4 is a computer program for causing a computer to realize the functions of
The deformation process by the first function and the pixel value process by the second function are associated with each other as one image quality adjustment process,
The deformation process and the pixel value process performed as the one image quality adjustment process are image quality adjustment processes whose contents are determined by the fourth function, and are identical to at least a part of the target image. A computer program that is an image quality adjustment process that gives an impression.

Images