JP5136335B2 - CAMERA DEVICE, IMAGE CUTTING METHOD, PROGRAM - Google Patents

Description

  The present invention relates to a camera device having a function of cutting out a specific area from an image, a cut-out image display method, and a program used for realizing them.

  Conventionally, as a technique for cutting out (extracting) an image of a specific area corresponding to a desired subject from an image photographed by a camera device, for example, in Patent Document 1 below, a main subject desired by a user is arranged on an arbitrary background. A technique is described in which after capturing a photographed subject-incorporated image and a background image with only a background where no main subject exists, a subject region that does not match in both images is cut out.

In such a conventional technique, the subject region that does not match between the subject-incorporated image and the background image is the region of the main subject desired by the user. Therefore, according to the prior art, an image of only the main subject can be cut out from the captured image.
JP-A-9-186936

  However, in the above technique, for example, when the background state when the image including the subject is photographed and the background state when the background image is photographed are changed, the changed background region is also cut out. End up. For example, when a cloud in the sky as the background moves between the time when the subject-included image is captured and the time when the background image is captured, even the cloud that the user does not desire is cut out. In addition, such a situation has a problem that the photographer cannot know unless the subject-included image and the background image are captured.

  The present invention has been made in view of such a conventional problem, and is capable of reliably acquiring an image in which only a specific region corresponding to an intended subject is cut out, and an image cutting method used for realizing the camera device. The purpose is to provide a program.

The camera device according to the first aspect of the present invention is a camera device having a function of cutting out a specific area from an image, and an imaging unit that captures an image of an object and an image captured by the imaging unit at a constant period. Display means for displaying the image as a through image, a first image captured by the imaging means, and the imaging means during the display period of the through image by the display means after the first image is captured. A specifying means for specifying the main subject area based on the second image, and a partial image of the main subject area specified by the specifying means from either one of the first image and the second image and clipping means for cutting out a storage target image, while displaying the through image by said display means, and an imaging control means for imaging repeatedly subject to said imaging means, leaving the cutting Of storage target image repeatedly extracted by means, characterized in that Ru and a storage means for storing the maximum storage target image in far.

The camera device according to the second aspect of the present invention is a camera device having a function of extracting a specific area from an image, and is imaged at a constant cycle by an imaging means for imaging a subject. A display unit that displays the captured image as a through image, a first image captured by the imaging unit, and an image captured by the imaging unit during a through image display period by the display unit after the first image is captured. Specifying means for specifying a main subject area based on the second image thus obtained, and a partial image of the main subject area specified by the specifying means as either one of the first image and the second image and clipping means for cutting out a stored target image from one, and a storage means for storing the storage target image extracted by the cutout unit, the first image and the second The image, characterized in that an image having different background together with containing the same main object.

Further, in the camera device according to the invention of claim 3 , the specifying means is obtained by a subtracting means for obtaining a difference between the first image and the second image, and the subtracting means. A labeling processing unit for performing a labeling process based on the difference, and specifying the largest connected region among the plurality of connected regions grouped by the labeling processing unit as a main subject region.

In the camera device according to the fourth aspect of the present invention, feature point acquisition for acquiring a plurality of feature points for a predetermined same region from both the first image and the second image, respectively. And a plurality of feature points corresponding to each other in the first image and the second image acquired by the feature point acquisition unit in one of the first image and the second image. Correction means for performing a matching correction, and the specifying means includes an image on a side corrected by the correction means among the first image and the second image, the first image, and the second image. The main subject region is specified based on the second image and the image on the side not corrected by the correcting means .

In the clipped image display method according to the fifth aspect of the present invention, in the camera device having a function of cutting out the specific area from the image, the step of capturing the first image, and after the capturing of the first image A step of displaying an image captured at a fixed period as a through image, a step of capturing a second image during the display period of the through image, and specifying a main subject region based on the first image and the second image A step of cutting out a partial image of the identified main subject area as a storage target image from one of the first image and the second image, and a second image during a through image display period And a step of storing the largest storage target image among the storage target images repeatedly cut out .
In the clipped image display method according to the sixth aspect of the present invention, in the camera device having a function of cutting out the specific area from the image, the step of capturing the first image, and after capturing the first image A step of displaying an image captured at a fixed period as a through image, a step of capturing a second image during the display period of the through image, and specifying a main subject region based on the first image and the second image A step of cutting out a partial image of the identified main subject area as a storage target image from either one of the first image and the second image, and a step of storing the cut out storage target image In addition, the first image and the second image are images that include the same main subject and have different backgrounds.

According to a seventh aspect of the present invention, there is provided a program for capturing a first image on a computer having a camera device having a function of extracting a specific area from an image, and after capturing the first image. A procedure for displaying an image captured at a fixed period as a through image, a procedure for capturing a second image during a through image display period, and a main subject region based on the first image and the second image A procedure for cutting out a partial image of the identified main subject area as a storage target image from one of the first image and the second image, and a second image during a through image display period And a procedure for storing the largest storage target image among the storage target images repeatedly cut out .
In the program according to the eighth aspect of the present invention, a procedure for capturing the first image on the computer of the camera device having a function of cutting out the specific area from the image, and after capturing the first image A procedure for displaying an image captured at a fixed period as a through image, a procedure for capturing a second image during a through image display period, and a main subject region based on the first image and the second image A procedure for cutting out a partial image of the identified main subject area as a storage target image from either the first image or the second image, and a procedure for storing the cut out storage target image A program for execution, wherein the first image and the second image are images that include the same main subject and have different backgrounds.

  According to the present invention, it is possible to reliably acquire an image in which only a specific area corresponding to an intended subject is cut out.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
(Embodiment 1)
1A and 1B are views showing the appearance of a digital camera according to the present invention. FIG. 1A is a front view, FIG. 1B is a rear view, and FIG. 1C is a top view.

  As shown in FIG. 1A, the digital camera of this embodiment has an imaging lens 2 and a strobe light emission window 3 on the front side of the main body 1. Further, as shown in FIG. 1B, a liquid crystal monitor 4, a cursor key 5, a SET key 6, and a menu key 7 as display means are provided on the back of the main body 1. Further, as shown in FIG. 1C, a shutter button 8 and a power button 9 are provided on the upper surface of the main body 1. Although not shown, a USB terminal connection unit (described later) used when connecting the digital camera to a personal computer or the like via a USB cable is provided on the side of the main body 1.

  FIG. 2 is a block diagram showing an outline of the electronic circuit configuration of the digital camera shown in FIG. The digital camera has a camera module 11 for capturing image data of a photographed subject. The camera module 11 includes an imaging optical system block 12 including the imaging lens 2, a CMOS sensor 13 as an imaging means, an ISP (Image Signa1 Processor) 14, and an optical system drive control unit 15.

  The CMOS sensor 13 photoelectrically converts and A / D-converts the optical image of the subject imaged by the imaging optical system 2 and outputs it to the ISP 14 as digital data. The output of the CMOS sensor 13 is an output according to the color filter array (Bayer array in this embodiment) on the light receiving surface of the CMOS sensor 13. In the ISP 14, color adjustment, data format conversion (conversion from a Bayer array to a luminance signal Y, color difference signals Cb, Cr), and the like are performed on the input digital data. Each digital signal of Y, Cb, and Cr is output from the ISP 14 with a resolution of 8 bits.

  The imaging optical system block 12 includes a zoom motor and a focusing motor for driving a lens group constituting the imaging lens 2, an aperture, and a mechanical shutter, which are driven by the optical system drive control unit 15 in accordance with a command from the CPU 21. Controlled. Output signals (Y, Cr, and Cb data) from the camera module 11 are transferred to the work memory 23 by the DMA 22. The work memory 23 is a storage means of the present invention configured by a DRAM or the like.

  The Y, Cr, and Cb data transferred to the work memory 23 is converted into RGB format image data by the image engine 24 and then transferred to the VRAM 25. Various CG images are combined with the image data in the image engine 24 as necessary.

  Further, the image engine 24 compresses each data of Y, Cr, Cb transferred to the work memory 23 according to a command of the CPU 21 and converts it into image data of a desired file format such as JPEG. The converted image data is stored in the flash memory 26, read out as necessary, decompressed by the image engine 24, and expanded in the work memory 23. Note that the flash memory 26 also stores image data of a subject cut out during shooting in a subject cut-out shooting mode described later.

  The display control unit 27 generates display data based on the image data stored in the work memory 23, outputs the display data to the liquid crystal monitor 4, and causes the liquid crystal monitor 4 to display an image. That is, a normal through image captured by the camera module 11 at a predetermined frame rate in a shooting standby state, a through image in which a CG image is synthesized by the image engine 24, and an image after being read and expanded from the flash memory 26 A recorded image based on the data is displayed on the liquid crystal monitor 4.

  The key input unit 28 includes the cursor key 5, the SET key 6, the menu key 7, the shutter button 8, and the power button 9, and outputs a state signal indicating the operation state of each key to the CPU 21. The USB control unit 29 controls communication of image data between a personal computer or the like connected to the USB connection terminal unit 30 via a USB cable and the digital camera.

  The CPU 21 controls the operation of each unit described above according to various operation programs. The operation program of the CPU 21 is stored in the flash memory 26 together with menu data used for various operation settings of the digital camera in a program storage area secured separately from an image recording area for recording image data. Yes.

  Then, the CPU 21 takes out imaging programs and menu data corresponding to the plurality of operation modes stored in the flash memory 26 in response to the status signal from the key input unit 28, and controls the operation of the digital camera. For example, shooting operation when the shutter button 8 is pressed, recording of image data, playback / display of the recorded image, display control of the function selection menu by the cursor key 5 when the menu key 7 is pressed, and display of the setting screen Take control.

  The CPU 21 functions as the specifying means (including subtracting means and labeling processing means), the clipping means, the display control means, and the imaging control means of the present invention by operating according to the imaging program in the subject clipping shooting mode. Thus, the processing described later is executed.

  Next, an operation according to the present invention of the digital camera having the above configuration will be described. FIG. 3 is a flowchart showing the processing procedure of the CPU 21 when the subject cut-out shooting mode prepared in advance as the lower mode of the recording mode is set in the digital camera of the present embodiment.

  The CPU 21 enters a shooting standby state together with the setting of the subject cutout shooting mode, and causes the camera module 11 to start an image capturing operation at a predetermined frame rate, thereby displaying a through image on the liquid crystal monitor 4 as in the normal shooting mode. Is started (step SA1). Thereafter, the user is immediately requested to shoot the subject with the first background (step SA2). For example, a predetermined message prepared in advance is displayed on the liquid crystal monitor 4 to prompt the user to perform a shooting operation. This step may be omitted on the assumption that the user understands the shooting method in the subject cutout shooting mode.

  Thereafter, the operation of the shutter button is waited (NO in step SA3), and when the shutter button is pressed (YES in step SA3), a photographing process is executed to acquire a reference image (step SA4). That is, an image is captured by the camera module 11 and the captured image data is temporarily stored as a reference image in a predetermined area of the work memory 23.

  FIG. 5A is a diagram illustrating an example of the reference image G1. The illustrated reference image G1 is an example in which the subject image desired by the user is a cat image, and an arbitrary background is used as the first background, and the cat, which is the main subject, is placed in the foreground, and shooting is performed. It is.

  Thereafter, the CPU 21 once initializes the storage target storage area secured in the work memory 23 (step SA5). Although not shown, the processing is skipped immediately after the subject cut-out shooting mode is set.

  Thereafter, it is requested to shoot a subject with a second background different from the first background used in the previous shooting (however, continuous shooting at a predetermined time interval by continuously pressing the shutter button 8) (step SA6). . At this time, similarly to step SA1, for example, a predetermined message is displayed on the liquid crystal monitor 4. Note that this step may be omitted. The shooting timing in the continuous shooting may be the same as or different from the timing of capturing (imaging) an image displayed as a through image.

  Then, it waits for the operation of the shutter button again (NO in step SA7), and when the shutter button is pressed (YES in step SA7), in response thereto, the first shooting process by continuous shooting is executed and a reference image is acquired. (Step SA8). That is, an image is captured by the camera module 11 and the captured image data is temporarily stored as a reference image in a predetermined area of the work memory 23. FIG. 5B is a diagram showing an example of the reference image G2.

  Subsequently, the CPU 21 executes the photographing target candidate extraction process shown in FIG. 4 (step SA9). In this process, first, the difference between the two images is acquired with respect to the luminance component of the previously acquired standard image and reference image (step SA101). That is, the pixel value (luminance value) is subtracted for each corresponding pixel between the standard image and the reference image.

  Next, a labeling process is performed on the data after the subtraction process for pixels whose absolute value of the difference (subtraction) result is equal to or less than a predetermined threshold value TH (step SA102). As is well known, the labeling process is a process of grouping the pixel group into a plurality of regions by adding the same label to pixels connected to each other. As a specific method, an arbitrary method (labeling process using four neighborhoods, etc.) is used. The threshold value TH is a predetermined value, for example, TH = 1.

  FIGS. 6A and 6D show examples of pixel groups in which the absolute value of the difference (subtraction) result is equal to or less than a threshold value TH, and this is hereinafter referred to as a labeling target image G3 for convenience. Call it. That is, (a) in the figure shows an example of the labeling target image G3 in the case where the position of the main subject (cat) in the image (within the angle of view at the time of shooting) is different between the reference image G1 and the reference image G2 described above. FIG. 4D shows an example of the labeling target image G3 when the main subject (cat) is in the same position. Usually, when the reference image G2 is first acquired, that is, at the time of shooting immediately after the background is changed, the position of the main subject is different from the reference image G1, and therefore the labeling target image G3 (pixel group having a threshold value TH or less) is shown in FIG. As shown in FIG.

  Subsequently, the CPU 21 determines the largest connected region among the connected regions (regions where pixels having the same label are connected) grouped in the labeling process, and determines the connected region as a shooting target region, that is, a user. It is specified as the intended main subject area (step SA103). FIG. 6B shows the shooting target area 101 in the labeling target image G3 in FIG. 6A, and FIG. 6E shows the shooting target area 101 in the labeling target image G3 in FIG. It is.

  Thereafter, a portion corresponding to the above-described shooting target area 101 is extracted from the reference image G2 as a shooting target candidate (step SA104), the shooting target candidate extraction process is terminated, and the process returns to the process of FIG. In step SA104, if there is a middle window-like region (hole) to which the label is not added in the photographing target region 101, the region including the region is extracted as a photographing target candidate.

  FIG. 6C and FIG. 6F show examples of imaging target candidate images (hereinafter referred to as imaging target candidate images) extracted (cut out) in step SA104. c) is an example of a photographic target candidate image G4 corresponding to FIG. 8B, and FIG. 10F is an example of the photographic target candidate image G4 corresponding to FIG.

  Then, returning to the processing of FIG. 3, the CPU 21 saves the work memory 23 described above when the above-described shooting target candidate extraction processing is the first processing after the start of continuous shooting, that is, immediately after the start of continuous shooting. Since the image to be stored is not stored in the target storage area (NO in step SA10), the process proceeds to step SA12 as it is, and the shooting target candidate image extracted (cut out) by the shooting target candidate extraction process is used as the storage target image. Temporarily store in the storage target storage area.

  Thereafter, the image to be stored stored here is synthesized with the determined synthesis area in the through image and displayed on the liquid crystal monitor 4 (step SA12). In the present embodiment, as shown in FIG. 7A, a composite area 102 having a determined size is provided at the upper right of the through image G5, and a storage target image (in this case, a shooting target candidate image) is provided. ) And display it. FIG. 7A shows an example in which the storage target image is the photographing target candidate image G4 illustrated in FIG.

  Subsequently, the CPU 21 checks whether or not the operation of the shutter button has been released. If the operation has not been released (NO in step SA13), the CPU 21 returns to step SA8 to execute a new shooting process at the next shooting timing and refer to it. An image is acquired, and the imaging target candidate extraction process is performed again based on the standard image acquired in step SA4 and the new reference image, thereby acquiring a new imaging target candidate image (step SA9).

  After that, the size of the newly acquired shooting target candidate image and the size of the saving target image stored in the saving target storage area of the work memory 23 at that time are compared, and the shooting target candidate image is compared with the saving target image. If not larger (NO in step SA10), the process proceeds to step SA12 as it is, and a through image obtained by synthesizing the same image to be stored as the previous time is displayed on the liquid crystal monitor 4.

  On the contrary, if the newly acquired shooting target candidate image is larger than the saving target image (YES in step SA10), the shooting target candidate image is stored in the saving target storage area as a new saving target image (step SA11). A through image obtained by synthesizing the newly stored image to be stored is displayed on the liquid crystal monitor 4 (step SA12).

  Thereafter, until the operation of the shutter button is released (while the shutter button is pressed), the processing of steps SA8 to SA12 is repeated, so that a newly acquired photographing target candidate image is saved as the angle of view changes. Each time the image becomes larger than the target image, the storage target image is updated sequentially. In the meantime, when the position of the main subject (cat) in the reference image G2 taken at any time coincides with the standard image G1, the save target image displayed in the composite region 102 of the through image G5 at that time is shown in FIG. ) As shown in FIG. 5B, and thereafter, the candidate image G4 for photographing is continuously displayed in the synthesis area 102.

  When the operation of the shutter button is released at any time (YES in step SA13), the CPU 21 flashes the save target image stored in the save target storage area at that time as the image of the subject intended by the user. Save in the memory 26 (step SA14). As a result, the photographing operation in the subject cut-out photographing mode is completed, and all the processes described above are repeated while the mode is set.

  In the present embodiment, when shooting using the subject cutout shooting mode, if the user performs shooting of an arbitrary subject for which an image is desired to be acquired in the following manner, only a specific area corresponding to the intended subject is cut out. Thus, it is possible to reliably acquire the desired image, that is, the subject image desired by the user.

  That is, at the time of shooting, the user first selects an arbitrary background (first background) and causes an arbitrary subject (a cat in the example described above) to be captured to be captured. Next, after the user moves the position of the digital camera to change the background to another background (second background), continuous shooting of the same subject is started. At this time, the digital camera continues the continuous shooting when the user keeps pressing the shutter button, and adjusts the framing while allowing the user to check the storage target image (G4) displayed in the through image G5. Thereafter, when the user determines that the image to be stored (G4) matches the subject, that is, when the user determines that the subject portion has been cut out, the user releases the shutter button to end the shooting. Can reliably acquire a desired subject image.

  Further, in the present embodiment, the digital camera performs continuous shooting while the user presses the shutter button when shooting the reference image G2 after shooting the standard image G1. The digital camera then synthesizes and displays the through image while sequentially updating and storing only the largest storage target image G4 among the storage target images G4 obtained repeatedly, and the storage target image G4 is finally displayed. It was recorded as a photographed image.

  Therefore, the user can take a large number of reference images G2 without operating the shutter button one by one, and a desired subject image can be acquired easily and reliably in a short time. If it is only necessary to reliably obtain a desired subject image, it takes time, but the reference image G2 can be obtained every time the shutter button is pressed.

  In addition, in the present embodiment, when the user adjusts the framing, the subject image displayed in the composite area 102 on the through image becomes a desired subject (in the above example, as shown in FIG. 7B). When the user determines that the entire image of the cat has been obtained, if the user releases the shutter button to end the shooting, the entire image of the desired subject can be reliably cut out and stored.

  Furthermore, in the shooting target candidate extraction process in step SA9, the shooting target area (main subject area) 101 is specified by performing a labeling process on the difference result between the reference image G1 and the reference image G2. The imaging target area 101 can be specified with high accuracy and in a short processing time.

  Here, in the present embodiment, the shooting target candidate image G4 is extracted from the reference image G2, but the shooting target candidate image G4 may be extracted from the reference image G1.

  Further, in the above-described labeling process (step SA103) in the photographing target candidate extraction process shown in FIG. 4, a predetermined threshold TH is used. However, when the image quality state of the reference image G1 and the reference image G2 are different. May increase the threshold value TH. For example, prior to the labeling process, a difference in brightness of a portion determined to be the main subject is detected in the base image G1 and the reference image G2, and the threshold TH after the adjustment is increased by increasing the threshold. Labeling processing may be performed using TH. Thereby, even when the image quality states of the standard image G1 and the reference image G2 are different, it is possible to extract a more accurate photographing target candidate image G4 from the reference image G2.

  Prior to the labeling process described above, the process of acquiring the difference between the base image G1 and the reference image G2 (step SA101) may be performed as follows. For example, when the standard image G1 and the reference image G2 have different image quality states such as the brightness of the portion determined to be the main subject, at least one of the standard image G1 and the reference image G2 is once normalized, That is, the difference may be acquired after performing an adjustment process that brings the brightness of the portion determined to be the main subject in both the images G1 and G2 closer. Thereby, even when the image quality states of the standard image G1 and the reference image G2 are different, it is possible to extract a more accurate photographing target candidate image G4 from the reference image G2.

(Embodiment 2)
Next, a second embodiment according to the present invention will be described. In the present embodiment, in the digital camera having the configuration shown in FIGS. 1 and 2, the CPU 21 performs processing to be described later, which is different from the first embodiment in the subject cutout shooting mode, and a program for this is stored in the flash memory 26. It is stored in the program storage area, and the CPU 21 functions as the feature point acquisition means and correction means of the present invention by operating according to the program.

  If the outline is described first, also in the present embodiment, the CPU 21 performs the processing described in FIG. 3 when the subject cut-out shooting mode is set. However, in the above-described shooting target candidate extraction process in step SA9, the above-described reference image is once subjected to projective transformation processing, and after the above-described shooting target area 101 is specified in the processed reference image, the shooting target candidate image is extracted.

  FIG. 8 is a flowchart showing the photographing target candidate extraction process executed by the CPU 21 in the present embodiment. In the present embodiment, it is assumed that the user performs shooting so that the subject is as large as possible and positioned at the center within the angle of view during the continuous shooting after step SA8.

  In the following description, in the photographing target candidate extraction process, the CPU 21 first sets feature points (in a predetermined central partial region) in each of the reference image acquired in step SA4 and the reference image acquired in step SA8. Four points with large feature values are extracted (step SB101).

  For example, a Harris feature point detection function is used for feature point extraction. That is, when the pixel value at a certain position (x, y) of the image is I (x, y), the covariance matrix G is given by the following equation (1).

  When the two eigenvalues of the covariance matrix G are large, it indicates that there is a corner at that position. Therefore, the corner detection function, that is, the Harris feature point detection function R_H, can be expressed by the following equation (2). In equation (2), del () represents a determinant, and tr () represents a trace (sum of diagonal components). k is a desired constant, for example, 0.04 is used.

  Based on the above, in step SB101, four points each having a large R_H represented by [Equation 2] are obtained in the vicinity of the central portion of the base image I1 and the reference image I2. FIG. 9A shows a standard image I1, and FIG. 9B shows a reference image I2. FIG. 4C shows an example of four feature points extracted from the standard image I1, and FIG. 4D shows an example of four feature points extracted from the reference image I2. Note that a portion (center portion) indicated by a white cross in the drawing is a feature point.

  The four feature points extracted from the reference image I1 are identified as (x1, yl), (x2, y2), (x3, y3), (x4, y4) in descending order of the feature amount (R_H), and the same Are identified as (u1, v1), (u2, v2), (u3, v3), (u4, v4) in descending order of the characteristic amount (R_H). The four feature points in both the images I1 and I2 are associated (step SB102).

  Here, it is assumed that the subject in the standard image (x, y) I1 and the subject in the reference image (u, v) I2 are present in the center region of both images and all feature points are on the subject. For example, this corresponds to the projective transformation on the homogeneous coordinates expressed by the following equation (3). G is a projective transformation matrix, and its elements are represented by the following equation (4).

  Therefore, the projective transformation matrix G is obtained by the determinant represented by the following formula (5) (step SB103).

  Subsequently, in order to match the subject of the reference image (u, v) I2 with the subject of the standard image I1, the reference image (u, v) I2 is obtained using the projection transformation matrix G expressed by the following equation (6). Correction is performed by projective transformation, and a corrected reference image (u ′, v ′) I3 is acquired (step SB104). In other words, the reference image (u, v) I2 has the same shooting direction and angle as the subject when the reference image (x, y) I1 is taken. The corrected image shown in FIG. 9E is used as a corrected reference image (u ′, v ′).

  Thereafter, the difference between the modified reference image I3 and the base image I1 is acquired (step SB105). Thereafter, similarly to the shooting target candidate extraction process of the first embodiment, a labeling process is performed for pixels whose absolute value of the difference (subtraction) result is equal to or smaller than a predetermined threshold TH (step SB106). After determining the largest connected area among the grouped connected areas and specifying the connected area as a shooting target area (step SB107), a portion corresponding to the shooting target area is shot from the corrected reference image I3. The target candidate is extracted (step SB108), and the photographing target candidate extraction process is terminated.

  As described above, in the present embodiment, when the shooting target region 101 is specified in the shooting target candidate extraction process, the reference image is once corrected by the projective transformation process, and then the corrected reference image (corrected reference image I3). Is used to obtain the difference from the reference image and to perform the labeling process. Therefore, as compared with the first embodiment, the shooting target area 101 can be specified with higher accuracy, and a more accurate shooting target candidate image G4 can be extracted. That is, a better image can be obtained as a desired subject image.

  In the first and second embodiments, the case where the present invention is applied to a digital camera has been described. However, the present invention is not limited to this and may have a still image shooting function. For example, the present invention can be applied to other camera devices such as a digital video camera and a mobile phone terminal with a camera.

1 is an external view of a digital camera according to the present invention common to each embodiment. It is a block diagram which shows the outline of the electronic circuit structure of the digital camera. 6 is a flowchart illustrating a processing procedure of a CPU when a subject cutout shooting mode is set in the first embodiment. It is a flowchart which shows the content of the imaging | photography candidate candidate extraction process. It is a figure which shows the example of a reference | standard image and a reference image. It is a figure which shows an example of the image data produced | generated in the process of a photographic subject candidate extraction process. It is a figure which shows the example of a display of a through image. It is a flowchart which shows the content of the imaging | photography candidate candidate extraction process in 2nd Embodiment. It is a figure which shows the projection conversion procedure of the reference image in the same imaging | photography candidate candidate extraction process.

Explanation of symbols

4 LCD monitor 8 Shutter button 11 Camera module 13 CMOS sensor 21 CPU
23 Work memory 26 Flash memory 28 Key input unit 101 Shooting target region 102 Composite region G1 Reference image G2 Reference image G3 Labeling target image G4 Shooting target candidate image G5 Through image I1 Reference image I2 Reference image I3 Modified reference image

Claims (8)

A camera device having a function of extracting a specific area from an image,
Imaging means for imaging a subject;
Display means for displaying, as a through image, an image picked up at a fixed period by the image pickup means;
The main subject based on the first image captured by the imaging unit and the second image captured by the imaging unit during the through image display period by the display unit after the first image is captured. An identification means for identifying the area;
Clipping means for cutting out a partial image of the main subject area specified by the specifying means as a storage target image from either one of the first image and the second image;
An imaging control unit that causes the imaging unit to repeatedly image a subject during display of a through image by the display unit;
Wherein among the repeated storage target image extracted by excision means, that up to a maximum of storing storage target image storage means, features and to Luke camera device that Ru equipped with in. A camera device having a function of extracting a specific area from an image,
Imaging means for imaging a subject;
Display means for displaying, as a through image, an image picked up at a fixed period by the image pickup means;
The main subject based on the first image captured by the imaging unit and the second image captured by the imaging unit during the through image display period by the display unit after the first image is captured. An identification means for identifying the area;
Clipping means for cutting out a partial image of the main subject area specified by the specifying means as a storage target image from either one of the first image and the second image;
Storage means for storing an image to be saved cut out by the cut-out means;
With
Wherein the first image and the second image, features and to Luke camera device that is an image having different background together with containing the same main object. The specifying unit includes a subtraction means for obtaining a difference between the first image and the second image, and a labeling processing unit which performs labeling processing based on the difference obtained by the subtraction means, the labeling process 3. The camera device according to claim 2 , wherein the largest connected area among the plurality of connected areas grouped by the means is specified as the main subject area. Feature point acquisition means for acquiring a plurality of feature points for a predetermined same region from both the first image and the second image;
Correction for matching a plurality of feature points corresponding to each other in the first image and the second image acquired by the feature point acquisition unit with one of the first image and the second image Correction means for applying
The specifying unit, the image of the correction means according to the corrected side by one of the first image and the second image, the correction means of the said first image and the second image identifying the main subject area based on the image of the uncorrected side of the camera device according to any one of claims 1 to 3, wherein. In a camera device having a function of cutting out a specific area from an image,
Capturing a first image;
Displaying an image captured at a constant period after capturing the first image as a through image;
Capturing a second image during a through image display period;
Identifying a main subject region based on the first image and the second image ;
Cutting out the identified partial image of the main subject region from any one of the first image and the second image as a storage target image;
Repeatedly capturing a second image during a through image display period;
And a step of storing the largest image to be saved among the images to be saved that are repeatedly cut out . In a camera device having a function of cutting out a specific area from an image,
Capturing a first image;
Displaying an image captured at a constant period after capturing the first image as a through image;
Capturing a second image during a through image display period;
Identifying a main subject region based on the first image and the second image ;
Cutting out the identified partial image of the main subject region from any one of the first image and the second image as a storage target image;
Viewing including the step of storing the storage target image cut out,
The cut-out image display method, wherein the first image and the second image are images that include the same main subject and have different backgrounds . A computer having a camera device having a function of cutting out a specific area from an image,
A procedure for capturing a first image;
A procedure for displaying, as a through image, an image captured at a fixed period after capturing the first image;
A procedure for capturing a second image during a through image display period;
A procedure for identifying a main subject area based on the first image and the second image ;
A procedure for cutting out a partial image of the identified main subject area as a storage target image from either one of the first image and the second image;
A procedure for repeatedly capturing a second image during a through image display period;
A program for executing a procedure for storing the largest image to be saved among the images to be saved repeatedly cut out so far . A computer having a camera device having a function of cutting out a specific area from an image,
A procedure for capturing a first image;
A procedure for displaying, as a through image, an image captured at a fixed period after capturing the first image;
A procedure for capturing a second image during a through image display period;
A procedure for identifying a main subject area based on the first image and the second image ;
A procedure for cutting out a partial image of the identified main subject area as a storage target image from either one of the first image and the second image;
To execute the steps of storing the storage target image cut out a because the program,
The program according to claim 1, wherein the first image and the second image are images including the same main subject and having different backgrounds .

Images