JP2009152718A - Unit and method for image processing, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enable easy selection of a desired portion from an image. <P>SOLUTION: The face of a person imaged in an image is detected through image data analysis. Based on the detection result, a position (target position) which becomes a target when setting a selection area is set in the image. Next, the set position of the selection area is determined so that a reference point of the selection area comes to the set target position. Then, by modification of the size of the selection area while the reference point of the selection area is maintained to the target position, the final selection area is set in the image. In general, a user tends to set such a composition as to arrange the face of the person to a suitable position, and therefore, by the above setting of the selection area based on the face of the person, the composition roughly matching the desire of the user is obtained. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

The present invention relates to a technique for analyzing image data and setting a selected region in a part of the image based on the analysis result.

In recent years, images can be easily handled in the form of digital data. For example, if a digital camera captures an image, records the image data, and supplies the recorded image data to a printing apparatus such as an inkjet printer, a high-quality printed image can be easily obtained. Moreover, since the image content is recorded as digital data in the image data, it is easy to analyze the image content and process the image. In view of this, there has been proposed a printing apparatus that uses this feature to perform a so-called trimming process to extract only a portion that a user wants to print from image data and print only that portion (Patent Document 1).

Japanese Patent Laid-Open No. 2005-80070

However, even if the trimming process is performed with the proposed printing apparatus, there is actually a problem that it cannot be easily executed. That is, every time trimming is performed,
A troublesome operation using the operation buttons for setting the position and size of the frame (trimming frame) that specifies the location to be printed is necessary, so it is not possible to easily select and output the portion to be printed was there.

The present invention has been made to solve the above-described problems of conventional techniques, and an object of the present invention is to provide a technique that allows a user to easily select a portion to be output without performing troublesome operations.

In order to solve at least a part of the problems described above, the image processing apparatus of the present invention employs the following configuration. That is,
An image processing apparatus that sets a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
A face area detecting means for detecting a face area that is an area in which a person's face is captured in the image by analyzing the image data;
Target position determining means for determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
Selection region position determining means for determining the position of the selection region in the image;
Selection area setting means for setting the selection area in the image by changing the size of the selection area while keeping the reference point of the selection area coincident with the target position in the image. The gist.

The image processing method of the present invention corresponding to the above image processing apparatus is
An image processing method for setting a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
Detecting a face area, which is an area in which the face of a person appears in the image, by analyzing the image data;
Determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
Determining the position of the selected region in the image;
And a step of setting the selection area in the image by changing the size of the selection area while keeping the reference point of the selection area coincident with the target position in the image. .

In the image processing apparatus and the image processing method of the present invention, when image data is read, the image data is analyzed to detect an area (face area) where a human face is drawn in the image. Next, a target position (target position) for setting the selected area in the image is set in the image based on the detection result of the face area. And so that the reference point in the selected area is at this target position,
The setting position of the selection area is determined. Next, the selection area to be finally set in the image is determined by changing the size of the selection area while keeping the reference point of the selection area at the target position.
Here, as a reference point of the selection area, a position that divides the selection area vertically and horizontally at a predetermined ratio (for example, a position of an intersection of a straight line that equally divides the selection area left and right and a straight line that equally divides the selection area vertically) Can be used as a reference point.

In general, a user tends to determine the composition of an image so that a person's face is placed at an appropriate position. Therefore, if the position of the selection area is set based on the face of the person shown in the image,
The selection area can be set at a position that is almost similar to the composition set by the user. Therefore, the user can set a desired selection region without performing a complicated operation such as adjusting the position of the selection region by operating the operation button many times. In addition, when changing the size of the selection area set in this way, the size of the selection area is changed every time the size of the selection area is changed in order to change the size of the selection area while keeping the reference point coincident with the target position. There is no need to readjust the position. Therefore, the user can easily change the selection area to a desired size. In this way, the user can easily set a selection area having a desired size at a desired position.

In addition, when changing the size of the selection area, it may be changed to the size specified by the user, or the size of the selection area is determined based on the result of analyzing the image data. The size may be changed. Of course, it may be changed to a predetermined size. In addition, the vertical and horizontal lengths of the selected region may be changed separately, or the size may be changed by similar enlargement or reduction while maintaining the vertical / horizontal length ratio at a predetermined ratio. It is good.

In the above-described image processing apparatus of the present invention, the eyes of a person may be further detected from the detected face area, and the target position may be set based on the detected eye position.

In general, when a user views an image, there is a tendency to pay attention to “eyes” in the face of a person. Therefore, a composition in which the eyes are appropriately arranged is preferred. Therefore, if the target position is set based on the detected eye position, it is possible to set a selection region where a more appropriate composition can be obtained.

Further, when the image processing apparatus of the present invention described above sets the selection area, the size of the selection area is determined according to the size of the detected face area, and the selection area having the determined size is set in the image. It is good as well.

In this way, the size of the selected area can be set so that the face area occupies an appropriate ratio with respect to the entire selected area, so that a suitable composition in which a human face is drawn with an appropriate size is obtained. As described above, it is possible to set the selection area.

In the above-described image processing apparatus of the present invention, the size of the selected region may be determined by considering how many face regions are detected in addition to the size of the detected face region. .

In general, it is empirically known that the optimal ratio between the face area and the entire selected area is slightly different depending on the number of people in the image. For example, in an image in which one person is photographed, it is preferable to enlarge the selection area and add a part other than the face to the composition to some extent. However, if the number of images increases, the opposite is true. It has been empirically found that a better composition is obtained when the selected region is not made too large. From this, it is possible to set a selection area that can provide a more suitable composition if the size of the selection area is determined in consideration of not only the size of the face area but also the number of detected face areas. It becomes.

In the above-described image processing apparatus of the present invention, the vertical / horizontal length ratio of the selected region may be determined based on the vertical / horizontal length ratio of the image represented by the read image data. Then, when changing the size of the selected region, the size of the selected region may be changed while maintaining the ratio of the vertical and horizontal lengths at the determined ratio.

Usually, the ratio of the vertical and horizontal lengths (aspect ratio) of an image is a ratio suitable for viewing an image. Therefore, if the ratio of the vertical and horizontal lengths of the selection area is determined based on the aspect ratio of the image, it is possible to set the selection area having an aspect ratio suitable for viewing the image.

In the image processing apparatus of the present invention described above, at least one face area may be selected from a plurality of detected face areas, and the target position may be determined based on the selected face area.
Here, when selecting a face area, the user may select a desired face area from among a plurality of face areas, or by analyzing image data, It is also possible to detect a face of a specific person from and select the face area.

In this way, since the selection area can be set based on the face area of the desired person, the user can easily set the selection area for the desired person even in the case of an image showing the faces of a plurality of persons. Is possible.

Furthermore, the present invention can be realized using a computer by causing a computer to read a program for realizing the above-described image processing method and executing a predetermined function. Therefore, the present invention also includes the following aspects as a program. That is, the program of the present invention corresponding to the image processing method described above is
A program for realizing, using a computer, an image processing method for setting a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
A function of detecting a face area that is an area in which a person's face is captured in the image by analyzing the image data;
A function for determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
A function for determining the position of the selected region in the image;
The function of setting the selection area in the image is realized by a computer by changing the size of the selection area while keeping the reference point of the selection area coincident with the target position in the image. The gist.

If this program is read into a computer and each of the above functions is realized, it is possible to easily select a desired portion without causing the user to perform troublesome operations.

Hereinafter, in order to clarify the contents of the present invention described above, examples will be described in the following order.
A. Device configuration:
B. Trimming frame setting process:
B-1. First embodiment:
B-2. Second embodiment:
C. Variations:

A. Device configuration :
FIG. 1 is a perspective view showing a printing apparatus 10 equipped with the image processing apparatus of this embodiment. As illustrated, the printing apparatus 10 includes a scanner unit 100, a printer unit 200, a control unit 300 that controls operations of the scanner unit 100 and the printer unit 200, and the like.
The scanner unit 100 has a scanner function of reading a printed image and generating image data, and the printer unit 200 has a printer function of receiving image data and printing an image on a print medium. . Further, the image read by the scanner unit 100 is transferred to the printer unit 20.
If the output starts from 0, the copy function can be realized. That is, the printing apparatus 10 according to the present embodiment is a so-called scanner / printer / copy combined apparatus that can independently realize a scanner function, a printer function, and a copy function.

The control unit 300 includes a CPU, a ROM, a RAM, and the like.
The image data read in step 1 and the image data read from a recording medium such as a memory card can be subjected to predetermined image processing and printed using the printer unit 200. For example,
Processing to extract part of an image from image data according to user instructions (trimming processing)
By performing the above, it is possible to extract and print only the portion of the image to be printed. When performing such a trimming process, the user cannot easily perform the trimming process if the user has to operate the operation button a number of times in order to designate a portion to be extracted. In view of these points, the printing apparatus 10 according to the present exemplary embodiment is equipped with the image processing apparatus according to the present exemplary embodiment that allows a user to easily specify a portion to be printed without forcing the user to perform troublesome operations.

FIG. 1 conceptually shows a state in which the image processing apparatus of this embodiment is mounted on the printing apparatus 10. As illustrated, the image processing apparatus includes a CPU mounted on the control unit 300.
And various types of processing are realized using functions of the CPU and RAM. When receiving the image data, the image processing apparatus according to the present embodiment analyzes the image data and performs a process of predicting a trimming frame in which a suitable composition can be obtained. Then, the predicted trimming frame is displayed on the monitor screen 320 while being superimposed on the image. As a result, the user can check the trimming frame on the monitor screen 320. After the user confirms the trimming frame on the monitor screen 320 and corrects it as necessary, when the user presses the OK button on the operation panel 310, the control unit 300 receives the image and the original image in the trimming frame is received. An image in the trimming frame is printed by extracting from the image data and supplying the extracted data to the printer unit 200. Accordingly, the user can easily obtain a suitable print image that has been subjected to the trimming process, without performing a complicated operation such as setting the trimming frame by operating the operation panel 310 many times. Hereinafter, such processing performed by the control unit 300 will be described in detail with reference to a flowchart.

B. Trimming frame setting process:
B-1. First Example:
FIG. 2 is a flowchart showing the flow of “trimming frame setting processing” in the first embodiment. This process is a process executed to determine a trimming frame for an image when the user designates image data to be trimmed by operating the operation panel 310.
As shown in the flowchart of FIG. 2, when processing is started, first, processing for reading image data designated by the user is performed (step S100). Here, the image data to be read may be recorded on a recording medium inserted in the printing apparatus 10 or recorded on a computer or the like connected to the printing apparatus 10. Also good.

After the image data is read, the read image data is analyzed, and a process of detecting a person's face shown in the image is performed (step S102). The human face is detected for the following reason. That is, in general, users tend to place importance on a person's face in an image. For example, when photographing an image, the composition is usually determined so that the face of a person is at an appropriate position in the frame. Similarly, when trimming an image, there is a tendency to perform the trimming process so that the person's face is at an appropriate position. Therefore, in the trimming frame setting processing of the present embodiment, the face of the person shown in the image is detected, and the trimming frame is set based on the detected face position, so that the trimming becomes a composition that matches the user's intention. The frame is set.

Here, as a method of detecting a person's face from image data, for example, various methods have been proposed, including a method of detecting a skin-colored region in an image, but in this embodiment, It shall be detected by the following method. That is, first, from the image data,
Extract the contour of the object. When extracting the contour, use a two-dimensional filter such as a median filter to remove noise, enhance the contrast and edges, and then binarize, and use the resulting binarized image for the boundary of the object. Extract as Next, the extracted contours that are apparently not human faces are excluded. For example, an object having a large proportion of straight lines in the extracted contour is highly likely to be a so-called artifact. in this way,
Objects that can be clearly judged not to be human faces are excluded, and for the remaining objects, suspected objects such as “eyes”, “mouth”, and “nasal muscles” are extracted from the contour shape. If these objects are really “eyes”, “mouth”, “nose muscles”, etc., they should be in a predetermined positional relationship with each other. For example, when an object that seems to be “mouth” is extracted, an object that seems to be “eyes” or “nasal muscles” (or an object that can be clearly determined to be “eyes” or “nasal muscles”) exists above For example, it can be determined that the extracted object is a “mouth”. Similarly, regarding an object that seems to be an “eye”, if it is really an “eye”, an object that seems to be an “eye” in the same direction is likely to exist in the vicinity. In this way, "eye", "mouth", "nose" from the contour
It is possible to identify “eyes”, “mouth”, “nasal muscles” and the like by extracting an object that seems to be, etc. and considering the positional relationship among the extracted objects. And "eyes", "mouth"
If the “nose muscles” and the like can be specified, the area surrounding them can be detected as a face area (face area). When the face area is detected from the image data in this way, a process for setting a trimming frame is then performed based on the position of the detected face area (step S104).
.

FIG. 3 is an explanatory diagram showing how a trimming frame is set based on the detected position of the face area. In FIG. 3, the rectangle drawn on the face portion of the person indicates the face area detected in the previous step S102. When detecting the face area, it is also possible to detect the shape of the face outline, but here, for simplicity, it is assumed that a rectangular area is detected as the face area as shown in the figure. explain. Several methods can be used to set the trimming frame based on the position of the detected face area. For example, simply, the trimming frame may be arranged so that the center of the trimming frame comes to the center of the face area. But,
If a so-called three-divided frame method is used, the trimming frame can be set more suitably. In this embodiment, the description will be made assuming that the trimming frame is set using the three-divided frame method.

As shown in FIG. 3, in the method of the three-divided frame, two dividing lines are drawn so that the vertical side of the trimming frame is divided into three equal parts, and the horizontal side is drawn so as to be divided into two equal parts. The trimming frame is set based on the upper intersection (indicated as “reference intersection” in the figure) among the intersections with one dividing line. That is, as shown in FIG. 3, the trimming frame is arranged so that the center of the face area detected earlier and the reference intersection of the trimming frame coincide. Generally, in photographic images, it is empirically known that a good composition can be obtained by placing a subject at the position of the reference intersection of the three-divided frame. By arranging the trimming frame so that the face comes, it is possible to obtain a suitable composition in which the human face is appropriately arranged.

When the position of the trimming frame is determined, the trimming frame may be set based on the position of the “eyes” of the person, not the center of the face area. For example, both eyes of a person are detected from the image data, and the trimming frame is set so that the middle position between the eyes matches the reference intersection of the trimming frame. In this way, it is possible to obtain a composition in which human eyes are suitably arranged. In particular, in the case of a composition with a large human face such as a portrait photograph, the user tends to place importance on the “eyes” in the face. By doing so, it becomes possible to obtain a good composition that more closely matches the user's preference.

Note that in this step (step S104 in FIG. 2), the position of the trimming frame is determined, but the size of the trimming frame is not determined. That is,
The size of the trimming frame shown in FIG. 3 is not the final size used when actually performing the trimming process, but only the provisional size temporarily set for the convenience of the process.
This is because in the trimming frame setting process of this embodiment, the size of the trimming frame can be changed according to the user's preference, and the trimming process is performed according to the size finally determined by the user. It is. The process for determining the size of the trimming frame will be described in detail later. When the trimming frame size is tentatively set, a predetermined size set in advance may be used, or the size of a predetermined ratio with respect to the read image data (for example, the original size). The size of the image may be a quarter of the image size. In this embodiment, as the provisional size of the trimming frame, a size obtained by halving the length and width of the read image data is used.

When the position and provisional size of the trimming frame are set in this way, the trimming frame is displayed on the monitor screen 320, thereby allowing the user to confirm the trimming frame (step S106). In response to this, the user confirms the position of the trimming frame on the monitor screen 320 and performs an operation of setting the final size of the trimming frame using the operation panel 310 (step S108).

FIG. 4 is an explanatory diagram showing how the user sets the trimming frame size while checking the monitor screen 320. As shown in the figure, a trimming frame is displayed on the monitor screen 320 in a state of being superimposed on the image, so that the user can easily grasp which part of the image is extracted by the trimming process. It is possible. Therefore, the user operates the operation panel 310 while confirming the monitor screen 320 so that the trimming frame has a desired size.

When the user operates the operation panel 310 to change the size of the trimming frame, the control unit 300 resets the trimming frame and displays the trimming frame on the monitor screen 320 again. Here, when changing the size of the trimming frame, only the size is changed without moving the position of the trimming frame. That is, the size of the trimming frame is changed by enlarging or reducing the size of the trimming frame while keeping the reference intersection of the trimming frame at the center position of the face area.

FIG. 5 conceptually shows how the size of the trimming frame is changed without moving the position of the trimming frame. The trimming frame indicated by “a” in the drawing is a provisional size trimming frame set in the previous step S104. On the other hand, the trimming frame indicated by “c” in the figure is obtained by enlarging the trimming frame of “a” in a similar shape with the reference intersection as the origin. As shown in the figure, the reference intersection point is located at the center of the face area even in the enlarged trimming frame “c”. Also, the trimming frame indicated by “b” in the figure is obtained by reducing the trimming frame of “a” to a similar shape. Again, the reference intersection is located at the center of the face area. In this way, if only the size is changed without changing the position of the reference intersection, the person's face is arranged at a suitable position even in the enlarged trimming frame or the reduced trimming frame. For this reason, the user does not need to perform complicated operations such as adjusting the position of the trimming frame again each time the size of the trimming frame is changed, and can easily set a trimming frame having a suitable composition. .

When the trimming frame size is adjusted while viewing the monitor screen 320 in this way and the desired trimming frame can be set, the user presses the enter button on the operation panel 310 to determine the final size of the trimming frame. In response to this, the control unit 300 stores the position and final size of the trimming frame on the RAM, and ends the trimming frame setting process of FIG. Then, the image data in the trimming frame is extracted from the original image data according to the stored position and size of the trimming frame, and the extracted image data is supplied to the printing unit 200 to print the image in the trimming frame.

FIG. 6 is an explanatory diagram illustrating an image printed in this way. FIG. 6A is an image obtained by printing image data extracted according to the trimming frame indicated by “a” in FIG. FIG. 6B is a print of the image data extracted in accordance with the trimming frame indicated by “b” in FIG. 5. Similarly, FIG. 6C is “c” in FIG. The image data extracted according to the indicated trimming frame is printed. As described above, in any of these trimming frames, the person's face is arranged at an appropriate position. Therefore, as shown in FIG. It is an image of a suitable composition arranged at the position.

As described above, in the printing apparatus 10 according to the present embodiment, the face of a person is detected and the position of the trimming frame is determined based on the position. For this reason, the user does not need to perform complicated operations such as adjusting the position of the trimming frame by operating the operation panel many times, and can easily set the trimming frame. Of course, as described above, the user needs to operate the operation panel 310 in order to determine the size of the trimming frame. In this case, it is only necessary to operate the buttons for enlarging and reducing the trimming frame. Therefore (see FIG. 4), the operation is very simple. Since the trimming frame set in this way is arranged based on the position of the person's face, it has a suitable composition in which the person's face is arranged at an appropriate position. Thus, the user can print an image trimmed to a suitable composition very easily.

In the above description, the trimming frame is set to be horizontally long when setting the trimming frame (see FIG. 3). However, the trimming frame may be set to be vertically long instead of horizontally long. FIG. 7 shows a state in which the trimming frame is set to be vertically long. Even when the trimming frame is set to be vertically long, similarly to the case where the trimming frame is set to be horizontally long as described above, the trimming frame may be arranged so that the reference intersection of the trimming frame is at the center of the face area. Thereby, it is possible to obtain a good composition in which a person's face is arranged at an appropriate position.

The orientation of the trimming frame in the landscape or portrait orientation may be determined by the user by operating the operation panel 310, but the number of persons photographed in the image (that is, the detected face area) is determined. It may be determined based on (number). For example, when only one face area is detected, the trimming frame may be arranged vertically. On the other hand, when a plurality of face areas are detected, the trimming frame may be arranged horizontally. . This way
When only one person is shown, it is possible to obtain an image with a good composition such as a portrait photograph by vertically enclosing the upper body of the person (see FIG. 7). On the other hand, in the case of an image in which a plurality of persons are shown, it is preferable to arrange the trimming frame horizontally so that a plurality of people arranged side by side can be accommodated in the trimming frame.

In the above description, the ratio between the vertical length and the horizontal length of the trimming frame (aspect ratio).
Has been described as not changing even if the user changes the size of the trimming frame (see FIG. 5). However, the user may be able to change the vertical length and the horizontal length of the trimming frame separately. FIG. 8 shows how the user individually sets the vertical size and horizontal size of the trimming frame. As shown in the figure, by operating a button on the operation panel 310, the user can enlarge or reduce the vertical size and the horizontal size, respectively. In this way, the user can print an image with his / her desired aspect ratio. For example, if a trimming frame is set in accordance with the aspect ratio of a photo frame such as a resume, an image that fits in the photo frame can be printed. And
In this way, even when the vertical size and horizontal size of the trimming frame are individually changed, the trimming frame is arranged so that the reference intersection point is at the center of the face area, so that a suitable composition can be obtained. It has become. Therefore, the user does not need to perform a complicated operation such as adjusting the position of the trimming frame each time the size is changed, and can easily obtain an image having a suitable composition with a desired aspect ratio. .

In the above description, an example of an image in which only one person is captured has been described (see FIG. 3). However, a trimming frame can be suitably set for an image in which a plurality of persons are captured. It is. FIG. 9 is an explanatory diagram showing a state in which a trimming frame is set on an image in which two persons are photographed. As shown in the drawing, in an image in which two persons are photographed, the trimming frame is arranged so that the average height of the two detected face areas matches the height of the reference intersection of the trimming frame, In addition, the trimming frame is arranged so that the reference intersection is located in the middle between the face area and the face area. In this way, the faces of the two people are placed at a suitable height,
Since the faces of the two people are arranged symmetrically and in a balanced manner, an image with a suitable composition can be obtained. Of course, even in such a case, the user does not need to perform complicated operations such as adjusting the position of the trimming frame by operating the operation panel 310 many times, so that a suitable image can be easily obtained. .

B-2. Second embodiment:
In the first embodiment described above, after the position of the trimming frame is determined based on the detected face area, the user sets the size of the trimming frame. However, not only the position of the trimming frame but also the size of the trimming frame can be determined based on the detected face area.

FIG. 10 is a flowchart showing the flow of the trimming frame setting process of the second embodiment for determining the position and size of the trimming frame based on the face area. Similar to the trimming frame setting process of the first embodiment, this process is a process performed to set a trimming frame for image data when the user selects image data to be trimmed. Also, FIG.
The trimming frame setting process of the second embodiment shown in FIG. 2 determines the size of the frame before displaying the trimming frame on the monitor screen 320 in contrast to the trimming frame setting process of the first embodiment shown in FIG. Although the points are greatly different, the other processes are almost the same. Hereinafter, the trimming frame setting process of the second embodiment will be described focusing on such differences.

In the trimming frame setting process of the second embodiment, when the process is started, first, as in the first embodiment, image data is read (step S200), the read image data is analyzed, and the person captured in the image is analyzed. A face is detected (step S202). Then, the position of the trimming frame is determined based on the detected position of the face area (step S204). When determining the position of the trimming frame, as in the first embodiment, the trimming frame is arranged so that the reference intersection of the trimming frame comes to the center of the detected face area (see FIG. 11). Of course, instead of the center of the face area, the reference intersection of the trimming frame may be made to coincide with the midpoint of the two eyes. When the position of the trimming frame is determined based on the detected face area position, processing for determining the size of the trimming frame is performed (step S206 in FIG. 10).

FIG. 11 is an explanatory diagram showing how the trimming frame size is determined in the second embodiment. As shown in the drawing, in the second embodiment, the horizontal size of the trimming frame is set to a length three times the horizontal width of the detected face area (indicated as “r” in the figure) (in the figure). "3r" is displayed). The horizontal size of the trimming frame is set in this way based on the concept of a three-divided frame. That is, it is empirically known that a photograph with a suitable composition can be taken by placing a subject in the center of the image and taking a picture with a space substantially the same as the width of the subject on both sides. So, if you adjust the horizontal size of the trimming frame to 3 times the width of the face area,
A trimming frame that captures a person's face with a suitable composition can be set.

If the horizontal size of the trimming frame is thus determined, the vertical size of the trimming frame is determined next time. The vertical size of the trimming frame can be set by various methods. For example, the ratio (aspect ratio) between the horizontal size and the vertical size of the original image is acquired from the image data, and trimming is performed so that the aspect ratio of the original image matches the aspect ratio of the trimming frame. What is necessary is just to determine the vertical size of a frame. Normally, the aspect ratio of image data shot with a digital camera or the like is set to a ratio that humans feel desirable, so if the aspect ratio of the trimming frame matches the aspect ratio of the original image data in this way, Thus, it becomes possible to easily set a trimming frame having a suitable aspect ratio. Of course, the aspect ratio of the trimming frame may be determined in advance. For example, if the aspect ratio of the trimming frame is set to a so-called golden ratio (1: 1.61), a suitable trimming frame having a golden ratio can be set.

When the position and size of the trimming frame are determined in this way, the trimming frame is displayed on the monitor screen 320 to allow the user to confirm the trimming frame (step S208 in FIG. 10).
. When the user confirms that the trimming frame is set to a suitable size, the user confirms the size of the trimming frame by pressing the enter button on the operation panel 310 (see FIG. 4). Of course, when the user wants to adjust the size of the trimming frame, the size may be adjusted by operating the operation panel 310. When the trimming frame is set in this way, the trimming frame setting process in FIG. 10 ends. Then, by extracting the image data in the set trimming frame from the original image data, and supplying the extracted image data to the printing unit 200,
Print the image in the trimming frame. Thereby, it is possible to obtain a good print image in which a person is extracted with a suitable composition.

As described above, in the trimming frame setting process of the second embodiment, the size of the trimming frame is determined based on the detected lateral width of the face area. In this way, the user does not need to operate the operation panel 310 in order to determine the size of the trimming frame, so that the trimming frame can be set more easily. And since the set trimming frame is set based on the position of the face area, the face area of the person is arranged at a suitable position,
In addition, since the width of the trimming frame is set based on the width of the face area, it is possible to trim a human face with a suitable size. As a result, the user can obtain an image with a suitable composition very easily. Of course, some users may want to change the position and size of the trimming frame. But even then,
Since the trimming frame is generally set to an appropriate position and size, the user can set a trimming frame of a desired size at a desired position only by finely adjusting the set trimming frame.

In the above description, an example in which only one person is captured has been described, but the position and size of the trimming frame can be appropriately set for an image in which two or more persons are captured. Is possible. FIG. 12 is an explanatory diagram showing how the position and size of the trimming frame are determined for an image in which two persons are captured. In order to determine the position of the trimming frame, as described in the first embodiment, the reference intersection of the trimming frame is located at the average height of the face area, and the face area and the face area The trimming frame may be arranged so that the reference intersection is located in the middle.

On the other hand, the size of the trimming frame may be determined as follows. That is, as shown in the drawing, the width from one face area of the two detected face areas to the other face area ("r"
”) And half the width (r / 2) is added to the outside of the two face regions. Then, the length from end to end of the width thus obtained (indicated as 2r in the figure) is the horizontal size of the trimming frame.When shooting two persons, about half the distance between the persons It has been empirically known that a good composition can be obtained if both spaces are taken on both sides, so if the size of the trimming frame is determined as shown in the figure, the two persons can be placed in appropriate positions. It is possible to obtain a suitable composition arranged in an appropriate size.

As described above, the vertical size of the trimming frame may be set so that the aspect ratio of the original image and the aspect ratio of the trimming frame coincide with each other, or the aspect ratio of the trimming frame is golden. You may set so that it may become ratio. This makes it possible to set a trimming frame having an appropriate aspect ratio. In this way, it is possible to set a suitable trimming frame for an image in which two persons are copied.

Further, the image is not limited to an image in which one person is photographed or an image in which two persons are photographed. An image in which three or more persons are photographed is also used to determine the position of the trimming frame based on the detected face area. The size can be suitably set. That is, it is possible to set a suitable trimming frame having a size suitable for each number of people by setting the trimming frame in consideration of the number of persons, regardless of the number of persons photographed in the image.

FIG. 13 is an explanatory diagram conceptually showing a method for setting a trimming frame of an appropriate size according to the number of people photographed in an image. In FIG. 13A, an image showing three persons is shown as an example, but the image is not limited to an image of three persons, and may be an arbitrary number of persons. For such an image, first, the position of the trimming frame is determined based on the detected position of the face area. That is, as shown in FIG. 13A, the trimming frame is arranged so that the average height of the detected face area coincides with the height of the reference intersection of the trimming frame, and the average of the face area The trimming frame is arranged so that the reference intersection is located at the position of. In this way, if the position of the trimming frame is determined based on the average height and the average position of the face area, the position of the trimming frame can be determined even when a plurality of persons are captured in the image. It is possible to decide appropriately. Of course, in the case of an image in which one person is photographed, the reference intersection of the trimming frame may be set at the center of the face area of the person (see FIG. 11).
If the position of the trimming frame is thus determined, the size of the trimming frame is determined next time.

To determine the size of the trimming frame, first select the leftmost face area and the rightmost face area from the detected face areas, and then select the rightmost face area from the leftmost face area. The width to the face area (displayed as “r” in the figure) is calculated. In FIG. 13A, an image in which three persons are copied is shown as an example, but not only an image in which a plurality of persons are copied in this way,
It is possible to calculate “r” even for an image in which only a person is captured. That is, since only one face area is detected in an image showing only one person, the width of the face area may be set to “r” (see FIG. 11). Thus, after calculating the width from the face area to the face area (in the case of one person, the width of the face area) “r”, this “r” and the number of persons captured in the image (the number of detected face areas) are calculated. The horizontal size of the trimming frame (indicated as “W” in the figure) is determined based on the number. That is, the ratio (r / W) between the value of “r” and the horizontal size “W” of the trimming frame
However, the value of the horizontal size “W” of the trimming frame is determined so as to coincide with a predetermined ratio predetermined for each number of persons.

Thus, the ratio (r) determined according to the width “r” from the face area to the face area and the number of persons (
The size of the trimming frame is determined using r / W) based on the following idea. That is, if the width “r” from the face area to the face area is calculated, and the value obtained by enlarging the width “r” at a predetermined ratio is the horizontal size of the trimming frame, the horizontal size of the trimming frame is larger than “r”. Therefore, it is possible to fit all the face areas inside the trimming frame. Furthermore, if the ratio (r / W) is set appropriately, the person can be arranged in a well-balanced manner in the trimming frame, so that a good composition can be obtained. Here, it can be considered that the ratio (r / W) at which such a good composition is obtained varies depending on the number of persons photographed in the image. For example, in the case of an image showing two persons (see FIG. 12), as described above, r / W =
It is empirically known that a good composition can be obtained when the ratio is set to 1/2. On the other hand, in the case of an image showing one person (see FIG. 11), it is known that a good composition can be obtained when r / W = 1/3 as described above. . Furthermore, similarly, it can be considered that an appropriate ratio (r / W) exists for each number of persons in an image in which three or more persons are captured. Thus, if the horizontal size of the trimming frame is set so that the value of “r / W” becomes an appropriate value, a suitable composition can be obtained, and the ratio (r /
W) differs depending on the number of persons. For this reason, the horizontal size (W) of the trimming frame is determined in consideration of not only “r” but also the number of persons photographed in the image.

FIG. 13B shows the ratio “r / W” for determining the value of the size “W” next to the trimming frame.
It is explanatory drawing which illustrated. As shown in the drawing, the ratio “r / W” is set to a different value depending on the number of persons photographed in the image. These values can be determined empirically. For example, in the case of an image in which a single person is captured (see FIG. 11), as described above, if the width of the face area is set to exactly one third of the trimming frame, a suitable composition may be obtained. Since it is known from experience, “1/3” can be set as the value of “r / W”. Further, in the case of an image in which two persons are captured (see FIG. 12), it is known that a suitable composition can be obtained by setting the horizontal size of the trimming frame to twice the width from the face area to the face area. Therefore, “1/2” can be set as the value of “r / W”. Similarly, it is possible to set a ratio based on experience for an image in which three persons are copied and an image in which four persons are copied. If the horizontal size “W” of the trimming frame is determined so as to match the value set in this way, a suitable composition can be obtained by appropriately placing the person inside the trimming frame. It becomes.

As shown in FIG. 13B, the ratio (r / W) of “r” to the size “W” next to the trimming frame increases as the number of persons photographed in the image increases. Become. This is due to the following reason. That is, as the number of persons increases, the value of “r” tends to increase as the number of persons increases. If the size “W” next to the trimming frame is increased accordingly, the size of the trimming frame is increased. On the other hand, the individual face area becomes small, and a suitable composition cannot be obtained. That is, even when the number of people increases and the value of “r” increases, it is preferable that the trimming frame size “W” be as small as possible (ie, the value of “r / W”). As a better value). For this reason,
In FIG. 13B, “r” with respect to the trimming frame size “W” as the number of people increases.
The ratio (r / W) is set to be large.

Also, as shown in FIG. 13 (b), different ratios are set depending on whether the trimming frame is set to be vertically long (vertical layout) or to be horizontally long (horizontal layout). It is good to keep it. Since the ratio (r / W) for achieving a suitable composition is slightly different between the vertical layout and the horizontal layout, if different values are set for the vertical layout and the horizontal layout in this way, It is possible to obtain a more suitable composition in this layout.

As described above, in the trimming frame setting process according to the present embodiment, an image having one person or a plurality of persons can be appropriately sized according to the number of persons. It is possible to set a trimming frame. For this reason, in order to select only the images that can be trimmed, the user does not need to perform an operation of confirming the number of persons photographed in the images, and simply selects an image that the user wants to print. Of course, when performing the trimming process, it is not necessary to perform complicated operations such as operating the operation panel 310 many times to install the trimming frame. For this reason, the user can easily perform the trimming process, and as a result, a printed image trimmed to a suitable composition can be obtained very easily.

C. Modification:
In the first and second embodiments described above, in the case of an image in which a plurality of persons are captured, it has been described that the trimming frame is set based on all detected face regions (see FIG. 13). However, the face area of a specific person may be searched from the detected face areas, and the trimming frame may be set using only the face area of the person. In order to detect the face area of a specific person from the detected face areas, the following process may be performed. That is, the shape of “eyes”, “mouth”, “nose”, etc. extracted from the image data, and the positional relationship between them are compared with the face data of a specific person stored in advance. To see if they match. For example, the extracted “eye” outline may be compared with the stored outline of a specific person's eye to determine whether or not they match. Or make a triangle with the extracted eyes and nose at the top,
Find the three angles of the triangle. Then, a triangle is similarly created for the stored face of a specific person, and three angles are obtained, and it is determined whether or not they match the three angles of the previous triangle. If they match, the face can be determined to be the face of a specific person. Thus, when a face of a specific person is detected, a trimming frame is set using only the face area of the person.

FIG. 14 is an explanatory diagram illustrating a state in which a trimming frame is set based only on a face area of a specific person. As shown in the figure, the face areas of three persons are detected in this image, and a trimming frame is set for the face area of one of these persons. In order to set the trimming frame in this way, the same processing as that for setting a trimming frame on an image in which only one person is captured may be performed. That is, the trimming frame may be arranged so that the center of the face area of the person coincides with the reference intersection of the trimming frame (see FIG. 3). Of course, instead of the center of the face area, the trimming frame may be arranged so that the midpoint of the two eyes coincides with the reference intersection of the trimming frame. In this way, if the trimming frame is set based on the face area of a specific person, even if the image shows a plurality of persons, the user can extract and print only the desired person with a suitable composition. Is possible. For example, if you store your face as face data of a specific person, even if it is an image of multiple persons, the trimming frame is set based on your face area, so you Can be extracted and printed with a suitable composition. In such a case, since the trimming frame is appropriately arranged, the user can easily extract and print only himself without performing troublesome operations such as operating the operation panel 310 many times. ing.

Alternatively, the user can designate one (or more) faces from an image in which a plurality of persons are captured, and the trimming frame is set by performing the above-described processing on the faces. Also good. Even in this case, it is possible to set an appropriate trimming frame so as to cut out the designated person simply by designating the person, and it is possible to easily print a desired image.

The image processing apparatus according to the present embodiment has been described above. However, the present invention is not limited to all the embodiments described above, and can be implemented in various modes without departing from the spirit of the present invention.

For example, in the above-described embodiment, the case where the image processing apparatus of this embodiment is mounted on a printing apparatus has been described. However, the image processing apparatus of this embodiment can also be mounted on a digital camera.
When the digital camera is mounted, a trimming frame is displayed on the monitor screen of the digital camera by the image processing apparatus according to the present embodiment immediately after the user captures an image. In this way, the user can know the optimal composition for shooting the scene, so it is easy to shoot an image with a better composition by taking another shot with reference to this composition. Is possible.

Of course, the image processing apparatus of the present embodiment is not limited to a digital camera or a printing apparatus, and can be mounted on various apparatuses. For example, it can be mounted on an image display device such as a liquid crystal display or a CRT display, or can be mounted on a portable display device such as a photo viewer or a mobile phone terminal. Further, it can be mounted on an unmanned photo printing terminal placed on a street corner or in a public place.

It is explanatory drawing which shows the printing apparatus carrying the image processing apparatus of a present Example. It is the flowchart which showed the flow of the trimming frame setting process of a present Example. It is explanatory drawing which showed a mode that a trimming frame was set based on the position of the detected face area. It is explanatory drawing which illustrated a mode that the user sets the size of a trimming frame, confirming a monitor screen. It is explanatory drawing which showed a mode that a trimming frame was expanded and reduced in the state which has arrange | positioned the reference | standard intersection of a trimming frame to the center of a face area. It is explanatory drawing which illustrated the print image output based on the image data extracted by the trimming frame. It is explanatory drawing which showed a mode that a trimming frame is arrange | positioned vertically long. It is explanatory drawing which showed a mode that the vertical length and horizontal length of a trimming frame were each set separately. It is explanatory drawing which showed a mode that a trimming frame was set to the image in which two persons were copied. It is the flowchart which showed the flow of the trimming frame setting process of 2nd Example. It is explanatory drawing which showed a mode that the size of a trimming frame was determined in 2nd Example. It is explanatory drawing which showed a mode that the position and size of a trimming frame were determined with respect to the image in which two persons were copied. It is explanatory drawing which showed notionally the method of determining the size of a trimming frame according to the number of persons. It is explanatory drawing which showed a mode that the trimming frame was set only based on the face area of the specific person.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Printing apparatus 100 ... Scanner part 200 ... Printer part 300 ... Control part 310 ... Operation panel 320 ... Monitor screen

Claims (8)

An image processing apparatus that sets a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
A face area detecting means for detecting a face area that is an area in which a person's face is captured in the image by analyzing the image data;
Target position determining means for determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
Selection region position determining means for determining the position of the selection region in the image;
Image processing comprising: selection region setting means for setting the selection region in the image by changing the size of the selection region while keeping the reference point of the selection region coincident with the target position in the image apparatus. The image processing apparatus according to claim 1,
The target position determining means is an image processing apparatus which detects the person's eyes from the detected face area and determines the target position based on a position where the eyes of the person are detected. The image processing apparatus according to claim 1 or 2,
A selection area size determining means for determining the size of the selection area according to the size of the detected face area;
The image processing apparatus, wherein the selection area setting means is a means for setting the selected area of the determined size in the image. The image processing apparatus according to claim 3,
The selection area size determining means is an image processing apparatus that determines the size of the selection area in consideration of the number of detected face areas in addition to the size of the detected face area. An image processing apparatus according to any one of claims 1 to 4,
The selection area setting means, based on the ratio of the length and width of the image represented by the image data,
By determining the ratio of the vertical and horizontal lengths of the selection area, and changing the size of the special area while maintaining the vertical and horizontal lengths of the selection area at the determined ratio, the special area in the image An image processing apparatus which is means for setting. An image processing apparatus according to any one of claims 1 to 5,
The target position determining means is an image processing apparatus which is a means for determining a target position in the image based on at least one face area selected from the plurality of detected face areas. An image processing method for setting a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
Detecting a face area, which is an area in which the face of a person appears in the image, by analyzing the image data;
Determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
Determining the position of the selected region in the image;
An image processing method comprising: setting the selection area in the image by changing a size of the selection area while keeping a reference point of the selection area coincident with a target position in the image. A program for realizing, using a computer, an image processing method for setting a rectangular selection area in an image represented by the image data by reading and analyzing the image data,
A function of detecting a face area that is an area in which a person's face is captured in the image by analyzing the image data;
A function for determining a target position in the image to be included at least in the selected area set in the image based on a detection result of the face area;
A reference point of the selection area provided at a position that divides the selection area in the vertical direction and the horizontal direction at a predetermined ratio inside the selection area so as to overlap the target position in the image.
A function for determining the position of the selected region in the image;
A program for realizing by a computer a function of setting the selection area in the image by changing the size of the selection area while keeping the reference point of the selection area coincident with the target position in the image.

Images