JP2005020446A - Device and program for photographing image - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image photographing device that reduces the time and effort of a user to designate an image and selects an image whose object photographing state is satisfactory. <P>SOLUTION: A plurality of the images photographed by operating an operation part 13 are temporarily stored in an image memory part 16. Partial images of the plurality of stored images are extracted from the images by using a template about the object on the memory part 14. A photographed state of each partial image extracted on the basis of the template is calculated as an evaluation point and recorded in the memory part 14. An image evaluation point is calculated from the evaluation point of each partial image and recorded in the memory part 14. The specified number of images is selected on the basis of the evaluation point of each image. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
[Technical field to which the invention belongs]
The present invention relates to an image capturing device, and more particularly to an image capturing device having a function of evaluating a captured image.
[0002]
[Prior art]
As a conventional technique, there is an image photographing apparatus that evaluates photographing conditions and photographing environments from an optical standpoint and selects settings for obtaining an optimal image. In such an image capturing device, for example, a screen configuration is automatically set for taking a human photograph, a shutter speed and white balance are set for shooting a night scene, and a saturation and a color tone are automatically set for landscapes and nature, respectively. can do.
[0003]
As another image photographing device, there is an image photographing device capable of recording an image in units of people when taking a group photo. In this image photographing apparatus, a plurality of images are photographed for every person. After all the persons have been photographed, if the user selects an image that seems to be optimal for each person, they can be combined and created as one image (see, for example, Patent Document 1).
[0004]
On the other hand, there is an authentication system for a face portion as a currently disclosed technique for a captured image (for example, Patent Documents 2 and 3). In these systems, it is possible to recognize and extract a person's skin, face, and eyes from an image and to determine the orientation of the face.
[0005]
[Patent Document 1]
JP 2001-251550 A (3rd page, FIG. 3)
[Patent Document 2]
JP 2002-049912 A (page 3-4, FIG. 2-5, FIG. 8-10)
[Patent Document 3]
JP 2002-288670 A (page 3-4, FIG. 6)
[0006]
[Problems to be solved by the invention]
In the image capturing apparatus that performs the automatic setting as described above, an optically “good” image can be obtained. However, when a person is included in a plurality of images as in a group photo, for example, it is not necessarily a “good” image for the user even though it is optically good. This is because, for the user, how the person is reflected in the image is rather a criterion for judging whether the image is good or bad.
[0007]
The image capturing apparatus of Patent Document 1 includes means for synthesizing a “good” image for the user. However, it is necessary for the user to designate and select all images that are considered to be optimal for each person, which is a troublesome operation for the user.
The present invention reduces the labor required for the user to specify by using the authentication system for the face portion of the person described above, and allows the image shooting apparatus to select an image in which the shooting state of the person is good. An object of the present invention is to provide an realized image photographing apparatus.
[0008]
[Means for Solving the Problems]
According to claim 1, in the image photographing device for photographing a plurality of images in succession, the storage means for storing the plurality of images, and the plurality of images stored by the storage means are part of the image using the template relating to the subject. An extraction means for extracting an image; an imaging means for each partial image extracted based on the template is calculated as an evaluation point; an evaluation means for calculating an evaluation value of the image based on the evaluation score for each partial image; An image photographing apparatus is provided, comprising: selection means for selecting a specific number of images based on the evaluation value for each image obtained by the evaluation means.
[0009]
A partial image in the image is extracted based on the template related to the subject, and it is determined whether or not the extracted partial image is captured in a good state in the image. For this reason, it is not necessary to take a large number of images in advance and the user needs to select an image later, and it is possible to provide an image in which the subject is objectively captured. Therefore, the user can obtain a high-quality image by a simple operation.
[0010]
According to a second aspect of the present invention, in the image photographing device according to the first aspect, the storage unit temporarily stores a plurality of images continuously photographed by one operation of the shutter button. An image capture device is provided.
By temporarily storing a plurality of images taken continuously at one time, it is not necessary for the user to perform image evaluation each time the image is taken.
[0011]
According to a third aspect of the present invention, in the image photographing device according to the first or second aspect, there is provided the image photographing device, wherein the extracting means extracts all human parts photographed in the image as the partial images. Is done.
Even when shooting in large numbers, the user does not need to check the shooting state of each person in the image every time one image is shot.
[0012]
According to a fourth aspect of the present invention, in the image photographing device according to the first or second aspect, the extracting means extracts a plurality of human parts photographed at positions close to the center of the image as the image parts. An image capture device is provided.
Since only a specific number of people photographed at positions close to the center of the image are subject to evaluation, when taking an image with a specific person as the center of the image, the evaluation target is narrowed down to the person who is the center of the image. Can do.
[0013]
According to claim 5, in the image photographing device according to claim 3 or 4, the evaluation means sets an evaluation weight for each extracted person part, and sets the evaluation weight set for the person part. There is provided an image photographing apparatus characterized by evaluation in consideration.
[0014]
When shooting an image with a specific person as the center of the image, the evaluation value is higher for an image in which the shooting state of the specific person is better. Therefore, it is possible to obtain an image in which the shooting state of a specific person is suitable.
According to a sixth aspect of the present invention, in the image photographing device according to the first or second aspect, the extracting means extracts a person portion within a predetermined range from the center of the photographing range of the image as the partial image. An image capture device is provided.
[0015]
Since only a person photographed within a predetermined range from the center of the photographing range is set as an evaluation target, the evaluation target can be narrowed down to a person photographed near the center of the photographing range.
According to a seventh aspect of the present invention, in the image photographing device according to any one of the first to sixth aspects, the partial image is a human face portion, and the evaluation means calculates an evaluation score based on a condition including the orientation of the face portion. An image photographing apparatus characterized by calculating is provided.
[0016]
A partial image in the image is extracted based on a subject template created using the technology of the authentication system for the face portion. With respect to the extracted partial image, a determination is made based on the template based on the condition including the face orientation and whether or not the image is captured in a good state in the image. Since the evaluation value of the entire image is calculated based on the evaluation points, it is not necessary for the user to select an image that seems to be optimal, and an image with a good image of a person can be objectively stored in the image storage area.
[0017]
According to Claim 8, in the image photographing device according to any one of Claims 1 to 7, the extraction means includes a partial image of a human face, and the evaluation means has an open eye in the face. An image photographing apparatus is provided that calculates an evaluation score based on a condition including the degree of the image.
[0018]
By calculating the evaluation score using the condition including the degree of opening of the eye as a reference for determining the shooting state of the person in the image, the goodness of the person's face can be evaluated.
According to a ninth aspect of the present invention, in the image photographing device according to any one of the first to eighth aspects, the selecting means determines the evaluation rank of each image by comparing the evaluation values. Provided.
[0019]
Since the evaluation order is comprehensively determined, image evaluation can be performed without bias for each person even when a large number of photographs are taken.
According to claim 10, in the image photographing device according to claim 9, when the image includes a plurality of the partial images, the selection unit determines the evaluation score of the partial images with respect to the number of the partial images. There is provided an image photographing apparatus characterized in that the evaluation order of each image is determined in descending order of the ratio of the number of good partial images.
[0020]
Regarding the shooting state of each person in the image, a high evaluation value is given to an image having a large number of persons determined to be good. When selecting an image to be stored from a plurality of images after shooting, it is suitable for a case where it is preferable that the number of persons in good shooting state is more preferable.
According to an eleventh aspect, in the image photographing device according to any one of the first to tenth aspects, a first mode is obtained in which one image is photographed in response to one shutter button operation, and the photographed image is stored in the storage unit as it is. An image photographing apparatus is provided, further comprising photographing means having a second mode for photographing a plurality of images in response to one shutter button operation and storing the images in the storage means.
[0021]
Select the first mode when you want to perform normal image shooting. Select the second mode when you want to automatically or easily select images with good shooting conditions from multiple images shot with a single shutter button operation. And can shoot.
According to a twelfth aspect of the present invention, there is provided a program that is executed in an image capturing device that continuously captures a plurality of images, stores the plurality of images, and uses the template relating to the subject for the stored plurality of images. A partial image is extracted from the image, the shooting state of each partial image extracted based on the template is calculated as an evaluation point, the evaluation value of the image is calculated based on the evaluation point for each partial image, and each obtained image A program is provided that selects a specific number of images based on the evaluation value.
[0022]
DETAILED DESCRIPTION OF THE INVENTION
The first embodiment is shown below.
FIG. 1 is a diagram illustrating an internal configuration of an image capturing apparatus according to the present embodiment.
In the figure, the image photographing apparatus has a CPU 11, a camera photographing unit 12, an operation unit 13, a memory unit 14, a display unit 15, an image memory unit 16 and a recording medium 17, which are connected via a bus 20. The data can be exchanged between each other.
[0023]
The CPU 11 is a central processing unit, and controls the overall operation of the image capturing apparatus by executing a control program stored in advance in the memory unit 14.
The camera photographing unit 12 is a part that performs image photographing processing. When the CPU 11 is notified of pressing of the shutter button, a subject image formed on an image pickup device such as a CCD (Charge Coupled Device) via the image pickup lens. Is converted into an electric signal by photoelectric conversion and A / D conversion is performed to obtain digital image data.
[0024]
The operation unit 13 is an operation button or the like that receives a user operation instruction, and includes a power key, a shutter button, a setting button for performing various settings, and the like. When the user operates the operation unit 13, the operation content is notified to the CPU 11, and the CPU 11 performs control processing of other elements based on the operation content.
[0025]
The memory unit 14 includes a ROM that stores programs executed by the CPU, a RAM that the CPU 11 uses as a work memory, and the like, and stores a template, a face evaluation table, and an image evaluation table, which will be described later. A counter memory, which will be described later, is provided in the area on the memory unit 14.
[0026]
The display unit 15 is composed of a liquid crystal monitor, a driver thereof, and the like. The display unit 15 displays images taken at the time of image shooting, or sequentially selects the images to allow a user to select a specific number of images from among a plurality of images taken later. Various information such as display is displayed to the user.
[0027]
The image memory unit 16 is a rewritable nonvolatile memory composed of a flash memory or the like, and stores image data of a captured image. As shown in the conceptual diagram of the internal structure of the image memory unit 16 in FIG. 2, the image memory unit 16 includes an image storage area 21 and an image work area 22. The image storage area 21 is used for recording an image. The image work area 22 is used to temporarily store a plurality of captured images.
[0028]
The recording medium 17 is a portable recording medium that can be attached to and detached from the image capturing apparatus such as a memory card. When the recording medium 17 is attached to the image capturing apparatus, it is connected to the bus 20. The image data recorded in the image memory unit 16 is transferred to the recording medium 17. Then, the image data in the recording medium 17 is read and stored by the information processing apparatus at a later date.
[0029]
In the image photographing apparatus of the present embodiment, the CPU 11 executes a program in the memory unit 14 while using the RAM of the memory unit 14 as a work memory on the basis of an operation instruction of the operation unit 13 by the user. Various components to be described later are realized by controlling other components.
[0030]
The flow of processing for capturing and storing an image by such an image capturing apparatus will be described with reference to FIGS.
3 and 4 are flowcharts showing the operation processing performed in the image capturing apparatus. The processing shown in FIG. 1 is realized by the CPU 11 shown in FIG. 1 executing a control program stored in the memory unit 14.
[0031]
In step 301 of FIG. 3 (referred to as S301. Hereinafter, the steps are similarly described), the image capturing apparatus is in a state of waiting for an operation of the shutter button of FIG. When there is no operation of the shutter button, the mode switching operation of S310 can be accepted at any time.
[0032]
If a mode switching operation by the user is detected (YES in S310), the process proceeds to S311. In S311, it is determined whether or not the currently set mode is the group photo mode. The group photo mode is a mode in which a plurality of images are continuously captured when the shutter button is operated, and an image with a good shooting state is extracted from the captured images and recorded. The normal mode is In this mode, an image captured when the shutter button is operated is recorded as it is.
[0033]
If YES is obtained in S311, the process proceeds to S312 and the mode is set to the normal mode (S312). If NO, the process proceeds to S313, and the mode is set to the group photo mode (S313). In S312 / S313, the mode setting process ends.
[0034]
After the mode setting process, the process returns to S301. If there is no mode switching operation (NO in S310), the mode setting process is not executed and the process returns to the state of waiting for the shutter button operation in S301.
As described above, until the shutter button is operated, the image capturing apparatus can always perform the mode switching process from S310 to S312 or S313. If an operation of the shutter button is recognized under this state (YES in S301), the process proceeds to S302, and an image capturing process is executed.
[0035]
In the photographing process, first, it is determined whether or not photographing is performed in the group photograph mode (S302). If NO in S302, that is, if the shooting mode is set to the normal mode, the process proceeds to S308.
In the normal mode, an image is taken in S308. When shooting of one image is completed, the shot image is stored in the image storage area 21 of FIG. 2 in S309.
[0036]
If YES in S302, that is, if the shooting mode is set to the group photo mode, the process proceeds to S303. In photographing in the group photo mode, first, a counter for counting the number of continuous shots is reset (S303).
In step S304, an image is taken. In group photo mode shooting, images are continuously shot at predetermined time intervals. In step S305, the photographed image is first temporarily stored in the image work area 22 shown in FIG. Unlike the shooting in the normal mode, the image data is not directly stored in the image storage area 21 in FIG. After being temporarily stored in the image work area, 1 is added to the counter (S306).
[0037]
In S307, it is determined whether the operation of pressing the shutter button is continued. If YES in S307, it is determined that the user continues to press the shutter button, and the process returns to S304. The processes from S304 to S307 are repeated until it is not recognized that the shutter button has been pressed.
[0038]
If NO in S307, it is determined that the user has stopped pressing the shutter button, and the process proceeds to S401 in FIG. In S401, it is determined whether the value of the counter is 10 or more. If the value of the counter is less than 10 (NO), the process proceeds to S402.
[0039]
In S402, an image is taken. The captured image is temporarily stored in the image work area 22 of FIG. 2 (S403). After temporary storage, 1 is added to the counter (S404), and the process returns to the determination of the counter value (S401).
Thus, in group photo mode shooting, the counter value, that is, the number of images to be shot is 10 or more, and the image is read until it is recognized that the user has finished pressing the shutter button. Continue shooting. That is, in the group photograph mode, at least 10 images are continuously captured, and images are continuously captured while the user presses the shutter button.
[0040]
After the image shooting process in the group photo mode is completed, the image evaluation process temporarily stored in the image work area 22 of FIG. 2 is executed for each image. The image evaluation process will be described with reference to the flowchart of FIG. 5 showing the image evaluation process.
FIG. 5 is a flowchart showing an operation process performed in the image photographing apparatus. The processing in FIG. 10 is also realized by the CPU 11 in FIG. 1 executing a control program stored in the memory unit 14.
[0041]
In S501, one image is read out of the images temporarily stored in the image work area 22 of FIG. First, data relating to skin color is extracted from the image data. Next, based on the template of the human face read from the memory unit 14 in FIG. 1, all the face parts are extracted from the location where the data relating to the skin color is extracted (S502). Note that the template used for face extraction refers to a typical shape of a human face such as a face and a profile as seen from the front, and in S502, the shape of the portion from which data relating to the skin color is extracted. And compare. What matches the shape is extracted as a face.
[0042]
FIG. 6A is a diagram illustrating an example of a face evaluation table for performing evaluation on the face portion extracted from the images used in steps S503 and S504. As shown in the figure, each face part extracted from the image has a face part No. And is calculated based on, for example, the orientation of the face, the degree of hiding of the body, the degree of opening of the eyes, and the like. In group photos, etc., it is generally judged that it is a good condition that more people are facing the front with their eyes open and the body is also unobstructed by the surroundings. Based on this, it is the standard for evaluation.
[0043]
These evaluation points are also determined based on templates such as a face part and an eye part, and the result is digitized and evaluated. For example, regarding the “orientation” of the face in FIG. 6A, it is 3 points if it is determined to be facing the front, 1 point if it is determined to be sideways, and 0 if it is determined to be the other direction. The score is written in the face evaluation table on the memory unit 14 in FIG. 1 (step S504).
[0044]
FIG. 7 shows an example of image evaluation value calculation. An image 701 in FIG. 7 is a captured image. First, data relating to human skin color is extracted from the data of the image 701 in FIG. With respect to the part where the data relating to the skin color is extracted, a part where the extracted part has a round shape is further extracted, and this is matched with the face type of the template. As the template, for example, a face facing forward (rotation angle 0 degree), a face facing sideways (rotation angle ± 30 degrees, ± 60 degrees, etc.) and the like are stored in the memory unit 14 as data. Based on this template, the number of face parts and the face orientation are determined. In the image 702 of FIG. 7, the result of template matching that is evaluated as a human face is surrounded by a white line (703 in the image 702). In this example, the number of face parts is 703-1 to 703-10, the number of faces facing the front is 703-4 to 703-8, and the number of face faces is 703-1 to It is determined that there are five of 703-3, 703-9, and 703-10. Therefore, the evaluation score for “direction” in the face evaluation table of FIG. 6A is calculated as 3 × 5 + 1 × 5 = 20 points. In the case of the example of FIG. 7, the faces of the person A and the person B in the following figure are not extracted. If the faces of these persons are extracted, or the person determined to be in the landscape orientation is photographed in the front direction and determined to be in the front direction, the evaluation score is further increased.
[0045]
Similarly, the score for the degree of hiding and the degree of eye opening is calculated based on the template. Concerning the degree of occlusion, for example, if it is determined that the body is almost completely reflected in the image, it is 3 points, and if it is 2 or more and less than 3/4, it is only 1 point or less than 1/2. When the body does not appear in the image, the score is 0 points. As for the degree of eye opening, for example, the score is 2 points if it is determined that the degree of eye opening is good, and 0 points if it is determined that the degree of eye opening is bad. Similarly, the degree of hiding and the degree of eye opening are recorded in the face evaluation table of FIG.
[0046]
When the evaluation score of the face portion is calculated, the value is assigned to the face No. corresponding to the face portion in the face evaluation table of FIG. Is written in the column of total points of the positions (S504). After writing the total points, it is determined whether or not the evaluation has been completed for all the extracted face portions (S505). If not completed (NO in S505), the process returns to S503, and the next face No. The evaluation score for is calculated.
[0047]
In the case of YES in S505, that is, in the case where the evaluation for all the face parts in one image is completed, the process proceeds to S506. In S506, each face No. Calculate the sum of the evaluation values. With this as the overall evaluation score of the image, the temporary image No. is stored in the image evaluation table of FIG. 6B on the memory unit 14 of FIG. Write a value corresponding to. When the comprehensive evaluation score is written, the process proceeds to S508.
[0048]
In step S <b> 508, it is determined whether calculation of comprehensive evaluation points for all images in the image work area 22 and writing to the image evaluation table have been completed. In the case of NO, the process returns to S501, and the above evaluation process is repeated until writing of the calculated value of the comprehensive evaluation score to the image evaluation table is completed for all images. In the case of YES, the image evaluation process ends, and the process proceeds to an image selection process.
[0049]
An image selection process for selecting an optimum image among a plurality of images taken by one shutter button operation in FIG. 8 will be described below. The processing in FIG. 10 is also realized by the CPU 11 in FIG. 1 executing a control program stored in the memory unit 14.
[0050]
The comprehensive evaluation values of the image evaluation table are read from the memory unit 14 in FIG. Are sorted (S801). Provisional image No. As a result of the rearrangement, the image having the maximum comprehensive evaluation value is selected and displayed on the display unit 15 of the image capturing apparatus (S802).
[0051]
In S803, when selecting an image, it is determined whether or not the user is allowed to designate an image. In the case of NO, the image capturing device automatically selects an optimal image based on the comprehensive evaluation value. For this reason, the image selected in S802 is inevitably stored, and the process proceeds to S807 described later.
[0052]
If YES in S803, that is, if the user can specify an image, the process proceeds to S804. In S804, when it is determined from the user that the displayed image is saved (YES), an image saving process in S807, which will be described later, is executed. In the case of NO, the process proceeds to S805.
[0053]
In step S805, an instruction from the user to display the next image is awaited. If NO, that is, if there is no next candidate display instruction from the user, the process returns to S804. If there is an instruction to display the next candidate, the process proceeds to S806.
In step S806, the temporary image Nos. Sorted in descending order of the overall evaluation value in step S801. Among these, the next candidate image is selected and displayed on the display unit 15 of the image capturing apparatus in FIG. After displaying the next candidate image to the user, the process returns to S804 again and waits for the user's instruction. In S804, when the user instructs OK for the image to be saved, the process proceeds to S807. Until the command indicating that the image displayed on the monitor is OK is received from the user side, the image is displayed on the monitor in descending order of the comprehensive evaluation value.
[0054]
In S807, the selected image is written into the image storage area 21 in FIG. After the image is stored in the image storage area 21, all the image data in the image work area is deleted (S808), and the process returns to the state of waiting for the operation of the shutter button in FIG. 3 (S301). In this embodiment, one image is selected and recorded. However, the present invention is not limited to this. A plurality of images may be selected and recorded.
[0055]
As described above, the image capturing apparatus according to the first embodiment temporarily stores a plurality of images by one operation of the shutter button when taking a group photo. From the viewpoint of whether the image is captured, the most suitable image is digitized as a comprehensive evaluation value. By comparing the comprehensive evaluation values for the plurality of temporarily stored images, the image capturing apparatus can automatically store an image that is determined to be optimal, and provide a simple image option for the user. It becomes possible. Until the user is able to capture a good chance, or to record a large number of images, select an image in good shooting state later, check the image every time it is shot, and shoot a good image There is no need to re-shoot many times.
[0056]
Next, a second embodiment is shown.
In the second embodiment, weighting is performed when an image is evaluated. As a result, it is possible to perform image evaluation focusing on a specific person or area.
The basic configuration of the mechanism of the image photographing apparatus according to the second embodiment is the same as that of the first embodiment. As shown in FIG. 1, the CPU 11, the camera photographing unit 12, the operation unit 13, the memory unit 14, The display unit 15, the image memory unit 16, and the recording medium 17 are connected via a bus 20 so that data can be exchanged between them. As shown in FIG. 2, the memory unit 14 includes an image storage area 21 and an image work area 22.
[0057]
Of the processes for photographing and evaluating images, the photographing process is the same as in the first embodiment, and the flow is as shown in FIGS. The evaluation process of the second embodiment is different from the evaluation process of the first embodiment in that the entire image is not subject to evaluation uniformly but an evaluation is made with an emphasis on a certain range. ing.
[0058]
Hereinafter, the evaluation process according to the second embodiment will be described with reference to the flowchart of FIG. 9 showing the image evaluation process. FIG. 9 is a flowchart showing an operation process performed in the image photographing apparatus. The processing shown in FIG. 1 is realized by the CPU 11 shown in FIG. 1 executing a control program stored in the memory unit 14.
[0059]
In step S901, one image is read out of the images temporarily stored in the image work area 22 in FIG. Next, in calculating the evaluation value of the image, it is determined whether to give priority to the area or to give priority to the person (S902). Note that, in area priority, a person portion photographed within a predetermined range from the center of the photographing range is extracted as a person to be evaluated. In person priority, a person portion recognized within a predetermined number of people from the center of the shooting range is extracted as a person to be evaluated.
[0060]
If the determination result in S902 is YES, that is, if the user selects area priority, the process proceeds to S903. In step S903, only the face of a person in a specific area is extracted from the image using the template of the human face stored in the memory unit 14 of FIG. For example, in the image 101 in FIG. 10A, the face portion is not extracted from the hatched area D. Extract only from areas A, B and C. In the subsequent processing, only the faces extracted from the specific areas A, B, and C are evaluated.
[0061]
If the determination result in S902 is NO, that is, if the user has not selected area priority, the person priority process that has moved to the center is performed, and the process proceeds to S904. In S904, the face of the person close to the center is extracted as an evaluation target from the image using the template of the person's face stored in the memory unit 14 of FIG. For example, in the image 102 of FIG. 10B, the number of face parts to be extracted is designated, the face parts are extracted from the center of the image, and the extraction operation is finished up to a certain number. In this case, for example, no image is extracted from the hatched portion of the image 102 in FIG. In the subsequent processing, only the face extracted from the person extraction area of the image 102 is evaluated.
[0062]
The specific face of S903 or S904 is extracted, and the face part No. After allocating, the process proceeds to S905. In S905, a weight is set for each extracted face part. When the area priority extraction is performed, for example, in the image 101 of FIG. 10A, the area A is set to weight 4, the area B is set to weight 2, the area C is set to weight 1, and so on. If extraction is performed with priority given to people near the center of the image, for example, a certain number of faces from the center are weighted more than faces extracted from locations away from the center. Set.
[0063]
In step S906, an evaluation score is calculated for each of the extracted face parts from the face orientation, the degree of eye opening, and the like. The details of the calculation method are the same as those described in the first embodiment, and are omitted here.
A weighted evaluation score is calculated by multiplying the calculated evaluation score by a weight (S907). This weighted evaluation score is assigned to the face No. Are written in the face evaluation table stored in the memory unit 14 of FIG. 1 (S908).
[0064]
FIG. 11A shows an example of a face evaluation table in the second embodiment. Compared with the face evaluation table in the first embodiment of FIG. 6A, the face evaluation table used in the second embodiment further records the weight of the extracted face part. It is calculated by weighting using the weight.
[0065]
In step S909, it is determined whether evaluation has been completed for all the extracted face portions. If NO, the process returns to S906 and the remaining face No. The weighted evaluation points corresponding to are sequentially calculated and written in the face evaluation table. When the evaluation for all the face portions is completed, the process proceeds to S910.
[0066]
In S910, an average score of weighted evaluation points is calculated. For example, (average score) = (total sum of weighted evaluation points of each face) / (number of faces). The average score obtained in S910 is stored in the image evaluation table in FIG. 11B stored in the memory unit 14 in FIG. Write in correspondence with.
[0067]
After the writing to the image evaluation table is completed, it is determined whether the evaluation has been completed for all the images in the image work area 22 of FIG. 2 (S912). If it is not completed (NO in S912), the process returns to S901, and the remaining temporary image No. The average points corresponding to are calculated and sequentially written in the image evaluation table. When the evaluation is completed for all images (YES in S912), the evaluation process ends.
[0068]
After the evaluation process, an image selection process is performed. This is performed in the same procedure as the selection process according to the first embodiment shown in FIG. However, the average score stored in the image evaluation table of FIG. 11B is used as the evaluation value of FIG.
As described above, the second embodiment has been described. However, with such an image capturing device, it is most preferable to place an emphasis on how a person in a specific location in an image is captured in the image. Images are provided. Even when a large number of photographs are taken, such as a group photo, it is particularly suitable for a case where it is desired to shoot with an emphasis on a specific part, person or the like.
[0069]
In addition, although the image capturing device has been described along the embodiments, the present application is not limited to these. For example, in the image selection process, images may be selected in order from an image that occupies a high ratio of the number of face parts having a high evaluation score with respect to the number of extracted face parts of the person. In addition, for example, in this embodiment, the face orientation, the body hiding condition, and the eye opening condition are used, and the evaluation is performed based on the face template. Images can be provided to the user.
[0070]
In the above-described embodiment, the image recording apparatus including a unit that executes a series of processes has been described. However, the image recording apparatus may be provided as a program that executes a series of processes.
[0071]
【The invention's effect】
As described above, according to the present invention, a partial image in an image is extracted based on a template related to a subject, and it is determined whether or not the extracted partial image is captured in a good state in the image. For this reason, it is not necessary to take a large number of images in advance and the user needs to select an image later, and it is possible to provide an image in which the subject is objectively captured. Therefore, the user can obtain a high-quality image by a simple operation.
[Brief description of the drawings]
FIG. 1 is a block diagram of an image photographing apparatus in the present embodiment.
FIG. 2 is a conceptual diagram illustrating an internal structure of a memory of the image capturing apparatus according to the present embodiment.
FIG. 3 is a flowchart (part 1) illustrating an image capturing process according to the embodiment.
FIG. 4 is a flowchart (part 2) illustrating an image capturing process according to the embodiment.
FIG. 5 is a flowchart illustrating image evaluation processing according to the first embodiment;
6A is an example of a face evaluation table according to the first embodiment, and FIG. 6B is a diagram illustrating an example of an image evaluation table according to the first embodiment.
FIG. 7 is a diagram illustrating an example of calculating an evaluation value of an image.
FIG. 8 is a flowchart illustrating image selection processing according to the embodiment.
FIG. 9 is a flowchart illustrating image evaluation processing according to the second embodiment;
FIGS. 10A and 10B are diagrams illustrating examples of weights to be loaded when calculating an evaluation value of an image according to the second embodiment.
11A is a diagram illustrating an example of a face evaluation table according to the second embodiment, and FIG. 11B is a diagram illustrating an example of an image evaluation table according to the second embodiment.
[Explanation of symbols]
11 CPU
12 Camera shooting part
13 Operation part
14 Memory part
15 Display section
16 Image memory
17 Recording media
20 buses
21 Image storage area
22 Image work area

Claims (12)

In an image capturing apparatus that continuously captures a plurality of images,
Storage means for storing a plurality of images;
Extracting means for extracting a partial image from an image using a template related to a subject for a plurality of images stored by the storage means;
An evaluation unit that calculates a shooting state for each partial image extracted based on the template as an evaluation point, and calculates an evaluation value of the image based on the evaluation point for each partial image;
An image photographing apparatus comprising: a selection unit that selects a specific number of images based on an evaluation value for each image obtained by the evaluation unit. 2. The image photographing apparatus according to claim 1, wherein the storage unit temporarily stores a plurality of images continuously photographed by one operation of a shutter button. The image capturing apparatus according to claim 1, wherein the extracting unit extracts all the human parts captured in the image as the partial images. The image capturing apparatus according to claim 1, wherein the extracting unit extracts a plurality of person portions photographed at positions close to a center portion of the image as the image portions. 5. The evaluation unit according to claim 3, wherein the evaluation unit sets an evaluation weight for each of the extracted person parts, and evaluates the evaluation part in consideration of the evaluation weights set for the person part. Image shooting device. The image capturing apparatus according to claim 1, wherein the extraction unit extracts a person portion within a predetermined range from a central portion of an image capturing range as the partial image. The said partial image is a person's face part, The said evaluation means calculates an evaluation score based on the conditions containing the direction of this face part, The Claim 1 characterized by the above-mentioned. Image shooting device. The extraction means is characterized in that the partial image is a human face, and the evaluation means calculates an evaluation score based on a condition including a degree of opening of an eye in the face. Item 8. The image capturing device according to any one of Items 1 to 7. The image photographing apparatus according to claim 1, wherein the selection unit determines an evaluation rank of each image by comparing the evaluation values. When the image includes a plurality of the partial images, the selection unit determines the number of the partial images in descending order of the ratio of the partial images having the good evaluation score among the partial images. The image capturing apparatus according to claim 9, wherein an evaluation order is determined. A first mode in which one image is captured for one shutter button operation, and the captured image is stored in the storage unit as it is, and a plurality of images are captured in response to one shutter button operation, and the storage unit The image photographing apparatus according to claim 1, further comprising a photographing unit having a second mode stored therein. A program that is executed in an image capturing apparatus that continuously captures a plurality of images,
Memorize multiple images,
For a plurality of stored images, extract a partial image from the image using a template related to the subject,
The shooting state for each partial image extracted based on the template is calculated as an evaluation point, the evaluation value of the image is calculated based on the evaluation point for each partial image,
A program for selecting a specific number of images based on the obtained evaluation value for each image.

Images