JP2010200270A - Image processing device, camera, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a means to extract a major object to be imaged by color information, with a various photographic image whose kind and color of the major object to be imaged is not predetermined previously as a subject. <P>SOLUTION: An image processing device includes a noticed area setting portion, a frequency distribution forming portion, a color component analyzing portion, and an area division portion. The noticed area setting portion obtains a photographed image being taken by a photographic device and a photographic information of the photographed image and sets a noticed area at a part of the photographed image using the photographic information. The frequency distribution forming portion obtains a frequency distribution of color component contained in the image of the noticed area. The color component analyzing portion sets at least one range of a major color component in the noticed area on the basis of the frequency distribution. The area division portion classifies a color component at each position of the photographed image correspondent to the range of major color component and performs the area division of the photographed image on the basis of the result of the classification. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

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

  Conventionally, a technique for extracting a main subject from a captured image based on color information is known. As an example, Patent Document 1 discloses a technique for extracting a skin region from a captured image based on color information on the premise that a main subject is a person.

  By the way, any object can be a subject in photographing by the imaging apparatus. However, with the conventional technology, it has been difficult to extract a main subject from a captured image using color information for a variety of captured images in which the type and color of the main subject are not specified in advance.

  Accordingly, an object of the present invention is to provide means for extracting a main subject from color information for various captured images in which the type and color of the main subject are not specified in advance.

  An image processing apparatus according to an aspect includes an attention area setting unit, a frequency distribution generation unit, a color component analysis unit, and an area division unit. The attention area setting unit acquires a captured image captured by the imaging apparatus and shooting information of the captured image, and sets the attention area in a part of the captured image using the shooting information. The frequency distribution generation unit obtains a frequency distribution of color components included in the image of the attention area. The color component analysis unit sets at least one or more main color component ranges in the region of interest based on the frequency distribution. The region dividing unit classifies the color components at each position of the captured image according to the range of the main color components, and performs region division of the captured image based on the classification result.

  In the one aspect described above, the attention area setting unit may set the attention area using position information of the focus detection area when the captured image is captured.

  In the one aspect described above, hue information may be used as the color component.

  In the one aspect described above, the region dividing unit may extract the region of the main subject from the photographed image based on the range of the main color component showing the highest frequency of the color component in the frequency distribution.

  Note that a camera including the image processing apparatus according to the above aspect, a program that causes a computer to function as the image processing apparatus according to the above aspect, a storage medium that stores the program, and an image according to the above aspect. A representation of the operation of the processing apparatus in the method category is also effective as a specific aspect of the present invention.

  In the present invention, the main subject can be extracted from the photographed image using the color information by setting the range of the main color component from the frequency distribution of the color components of the region of interest and dividing the region based on the range of the main color component.

1 is a block diagram illustrating a configuration example of an image processing apparatus according to an embodiment. FIG. 5 is a flowchart for explaining an example of the operation of area division processing in the embodiment. The figure which shows the example of a setting of the attention area in a picked-up image Histogram of hue component corresponding to the photographed image of FIG. The figure which shows the example which divided | segmented the picked-up image of FIG. 3 into the area | region based on the range of the main color component of an attention area The figure which shows the comparative example which divided the picked-up image of FIG. 3 into the area | region by the range of the main color component determined from the hue of the whole picked-up image The block diagram which shows the structural example of the electronic camera in other embodiment. The flowchart which shows the operation example in imaging | photography mode in the electronic camera of other embodiment

<Description of One Embodiment>
FIG. 1 is a block diagram illustrating a configuration example of an image processing apparatus according to an embodiment. The image processing apparatus according to one embodiment is a personal computer in which an image processing program is installed. A computer constituting the image processing apparatus reads an image file generated by an imaging apparatus such as an electronic camera by executing an image processing program, and performs region division processing on the captured image of the image file.

  Here, the image file to be processed in one embodiment is generated in a file format conforming to, for example, the Exif (Exchangeable image file format for digital still cameras) standard. In the image file to be processed in one embodiment, a color photographed image (main image) photographed (captured) by the imaging device and photographing information (auto focus (AF) focus detection) about the photographed image are included. Are stored in association with each other.

  A computer 11 illustrated in FIG. 1 includes a data reading unit 12, a storage device 13, a CPU 14, a memory 15, an input / output I / F 16, and a bus 17. The data reading unit 12, the storage device 13, the CPU 14, the memory 15, and the input / output I / F 16 are connected to each other via a bus 17. Further, an input device 18 (keyboard, pointing device, etc.) and a monitor 19 are connected to the computer 11 via an input / output I / F 16. The input / output I / F 16 receives various inputs from the input device 18 and outputs display data to the monitor 19.

  The data reading unit 12 is used when reading the image file or the image processing program from the outside. For example, the data reading unit 12 communicates with a reading device (such as an optical disk, a magnetic disk, or a magneto-optical disk reading device) that acquires data from a removable storage medium, or an external device in accordance with a known communication standard. It consists of communication devices (USB interface, LAN module, wireless LAN module, etc.) to be performed.

  The storage device 13 is configured by a storage medium such as a hard disk or a nonvolatile semiconductor memory. The storage device 13 stores the image processing program and various data necessary for executing the program. The storage device 13 can also store the image file read from the data reading unit 12.

  The CPU 14 is a processor that comprehensively controls each unit of the computer 11. The CPU 14 functions as an attention area setting section 21, a frequency distribution generation section 22, a color component analysis section 23, and an area division section 24 by executing the image processing program (Note that the operation of each section included in the CPU 14) Will be described later).

  The memory 15 temporarily stores the calculation result of the image processing program. The memory 15 is composed of, for example, a volatile SDRAM.

  Next, an example of the operation of the area division processing in one embodiment will be described with reference to the flowchart of FIG. 2 is started when the CPU 14 executes the image processing program in accordance with a program execution instruction from the user.

  Step S101: The CPU 14 acquires an image file to be processed from the outside via the data reading unit 12. The image file acquired in S101 is recorded in the storage device 13 or the memory 15 under the control of the CPU 14. Note that when the image file to be processed is stored in the storage device 13 in advance, the CPU 14 may omit the process of S101.

  Step S102: The CPU 14 converts the color space of the captured image (main image) included in the image file to be processed into an HSV color space or an HLS color space. In one embodiment, the CPU 14 converts data of a color photographed image in the RGB color space (or YUV color space) into 8-bit image data corresponding to the HSV color space. If the captured image has a format corresponding to the HSV color space in advance, the CPU 14 may omit the process of S102.

  Step S103: The attention area setting unit 21 reads out the shooting information from the image file to be processed, and the position information of the focus detection area by the AF performed in advance before shooting of the shot image (XY of the focus detection area in the image) Position and its size).

  Then, the attention area setting unit 21 sets the attention area in a part of the captured image with reference to the position of the focus detection area. In one embodiment, the attention area setting unit 21 sets a rectangular partial area in the captured image centered on the focus detection area as the attention area. At this time, the attention area setting unit 21 may directly use the range corresponding to the focus detection area in the captured image as the attention area. FIG. 3 shows an example of setting the attention area in the captured image. In FIG. 3, the information on the focus detection area is indicated by a rectangular frame, and this focus detection area is set as a region of interest as it is. Note that the region of interest in FIG. 3 overlaps the rock portion on the captured image.

  Step S104: The frequency distribution generation unit 22 pays attention to the hue component (H) of each pixel included in the attention area of the photographed image, and obtains a frequency distribution indicating the correspondence between the hue component and the number of pixels in the attention area. .

  Here, FIG. 4 shows a histogram of hue components corresponding to the photographed image of FIG. The horizontal axis in FIG. 4 indicates an 8-bit hue value (0-255), and the vertical axis in FIG. 4 indicates the number of pixels (frequency) corresponding to each hue value. In the example of FIG. 4, the number of pixels on the vertical axis is normalized in the range of 8 bits (0-255). In FIG. 4, the histogram indicating the correspondence between the hue component and the number of pixels in the region of interest is indicated by a solid line. In FIG. 4, as a comparative example, a histogram indicating the correspondence between the hue component and the number of pixels in the entire captured image is indicated by a broken line.

  In the captured image of FIG. 3, the ratio of the green part due to trees or lawn is high in the entire image, and the ratio of the rock part corresponding to the region of interest is relatively small. Therefore, in the histogram of the entire image shown by the broken line in FIG. 4, the frequency in the green hue range (around the hue value 50) is very high, and the frequency in the rock hue range (around the hue value 100-180) is It will be relatively low.

  On the other hand, in the attention area of the captured image of FIG. 3, the ratio of the rock portion is very high, and the green portion is hardly included. Therefore, in the histogram of the attention area indicated by the solid line in FIG. 4, the frequency in the rock hue range is very high, and the frequency in the green hue range is close to zero. Therefore, it can be seen that the hue characteristics of the subject (rock) at the position of the focus detection area are well reflected in the frequency distribution of the hue component in the region of interest.

  Step S105: The CPU 14 smoothes the change in frequency between adjacent hues for the frequency distribution of the hue components in the region of interest (calculated in S104). Specifically, the CPU 14 performs smoothing filters (1/4 [1, 2, 4) for smoothing the frequency between two hue components having different hue values by one for each hue component of the frequency distribution. 1) smoothing filter) is applied. The process of S105 corresponds to smoothing the histogram curve by applying a smoothing filter in the horizontal axis direction of the solid histogram shown in FIG. Note that the CPU 14 applies the periodic boundary condition in the above processing and treats the upper limit (hue value 255) and lower limit (hue value 0) of the hue value as being continuous. As a result, the frequency can be smoothed even at the upper and lower limits of the hue value.

  Further, if the frequency distribution frequency is smoothed to a certain extent in the process of S105, it becomes easy to set a range of a main color component described later. On the other hand, if the frequency distribution frequency is excessively smoothed, the position where the region is divided based on the hue component tends to be ambiguous. Therefore, the number of times smoothing is performed in the process of S105 is appropriately set by the CPU 14 in consideration of the above circumstances. In the example of the embodiment, the CPU 14 performs the smoothing process up to about three times.

  Step S106: The color component analysis unit 23 sets at least one or more main color component ranges in the attention area based on the frequency distribution of the hue components in the attention area (smoothed in S105). As an example, the color component analysis unit 23 sets the range of the main color component by the following processes (A) to (C).

  (A) The color component analysis unit 23 refers to a distribution function (corresponding to the smoothed histogram of the solid line in FIG. 4) indicating the correspondence between the hue value and the frequency in the frequency distribution after smoothing. The position (hue value) at which the frequency becomes a peak in the distribution function is used as a candidate for the main color component. Of course, there may be a plurality of candidates for the main color component.

  Specifically, first, the color component analysis unit 23 has a position where the frequency distribution becomes a maximum value (or frequency in the horizontal axis direction of the distribution function) in the horizontal axis direction (the direction in which the hue value changes) of the above distribution function. The position at which the sign of the difference of (1) changes from positive to negative) is obtained. Then, the color component analysis unit 23 excludes the position (hue value) obtained from the distribution function from which the frequency value is less than the threshold value, and sets it as a candidate for the main color component. In one embodiment, the threshold for narrowing down the main color component candidates is set to 70 with 8-bit gradation (0-255).

  (B) The color component analysis unit 23 determines the hue value of the main color component by paying attention to the frequency value among the candidates for the main color component. Specifically, the color component analysis unit 23 selects up to a predetermined number of hue values of the main color components in descending order of frequency values from among the candidates for the main color components. Note that the color component analysis unit 23 in one embodiment selects up to two hue values of main color components.

  (C) The color component analysis unit 23 refers to the above distribution function, and sets the range of the main color component based on the hue value of the main color component of interest. Note that the color component analysis unit 23 sets the range of the main color component for the hue value of each main color component selected in (b) above.

  Specifically, the color component analysis unit 23 searches for the positions of valleys that occur around the hue value of the main color component of interest in the horizontal axis direction of the distribution function. At this time, the color component analysis unit 23 may obtain a position where the frequency distribution becomes a minimum value (or a position where the sign of the frequency difference changes from negative to positive in the horizontal axis direction of the distribution function). Also, the color component analysis unit 23 excludes positions where the frequency value is equal to or higher than a threshold value (for example, 70 for an 8-bit gradation) when searching for the valley. Then, the color component analysis unit 23 sets the range of the hue value up to two valleys adjacent to the left and right respectively as the range of each main color component with the hue value of each main color component of interest as the center.

  In one embodiment, a range in which the frequency of the hue value of the main color component is the highest among the plurality of main color component ranges is referred to as a first main color component range. In addition, the second highest color component range in which the hue value frequency of the main color component is the second highest is referred to.

  Step S107: The region dividing unit 24 performs region division of the captured image based on the hue value of each pixel of the captured image. Specifically, the region dividing unit 24 classifies the hue value of each pixel of the captured image according to which main color component range (S106). Next, the region dividing unit 24 performs region division by grouping pixels belonging to the same main color component range in the captured image based on the above classification result.

  Further, the area dividing unit 24 in S107 may extract the area of the main subject from the captured image by any one of the following methods (or a combination thereof).

  For example, the region dividing unit 24 may set a region belonging to the range of the first main color component as a main subject region in the captured image. In addition, the region dividing unit 24 may select a region having a high degree of overlapping with the attention region (or a region closer to the attention region) among the regions belonging to the main color component range as the main subject region. Further, the region dividing unit 24 may determine the region of the main subject in consideration of the setting information of the scene mode of the imaging device included in the shooting information.

  As an example, when the scene mode is “portrait shooting”, the area dividing unit 24 may preferentially set an area having a large group in the image as a main subject area. In addition, when the scene mode is “landscape shooting”, the region dividing unit 24 may preferentially set a region that is greatly expanded in the image as the region of the main subject.

  It should be noted that, when determining the grouping or spread of regions in the image, the region dividing unit 24 may obtain the second moment of the image in each region. At this time, if the moment around the center of gravity is small, it can be determined that the region tends to expand, and if the moment around the center of gravity is large, it can be determined that the region tends to be gathered.

  Here, FIG. 5 is a diagram illustrating an example in which the captured image of FIG. 3 is divided into regions based on the range of the main color components of the region of interest. The red part in FIG. 5 corresponds to the range of the first main color component. Further, the green portion in FIG. 5 corresponds to the range of the second main color component. Further, a black portion in FIG. 5 indicates a portion where the hue value does not belong to any of the main color component ranges.

  In general, when a captured image is acquired by an imaging device such as an electronic camera, shooting is performed with the main subject in focus. Therefore, the subject corresponding to the focus detection area is very likely to be the main subject. According to the example of FIG. 5, the range of the first main color component (red) matches the portion of the subject (rock) at the position of the focus detection area, and the lawn and tree portions around the rock are It is black. Therefore, it can be seen that the main subject can be accurately extracted from the captured image in the area division processing according to the embodiment.

  Further, as a comparative example of FIG. 5, FIG. 6 shows an example in which the captured image of FIG. 3 is divided into regions by main color components determined from the hue frequency distribution information of the entire captured image. In the example of FIG. 6, the range of the main color component is shown in red, and the portion not belonging to the range of the main color component is shown in black. In the comparative example of FIG. 6, the subject at the position of the focus detection area is shown in black, and it can be seen that the main subject cannot be extracted by the main color component.

  Step S108: The CPU 14 outputs the result of area division by the process of S107. As an example, the CPU 14 causes the monitor 19 to display a captured image (FIG. 5) divided into regions. Further, the CPU 14 may record the region division result in the storage device 13 or the like in association with the processing target image file. Note that the CPU 14 can also perform various types of image processing (for example, blurring processing on the background area excluding the main subject) on the captured image included in the image file using the result of area division. Above, description of the flowchart of FIG. 2 is complete | finished.

  The image processing apparatus according to the one embodiment sets a region of interest in a part of the captured image based on the position of the focus detection area (S103), and correspondence between the hue component and the number of pixels in the region of interest. A range of main color components is set from the frequency distribution indicating the relationship (S104, S106). Then, the image processing apparatus divides the captured image into regions depending on whether the hue value of each pixel belongs to the main color component range (S107). Thereby, in one embodiment, the main subject can be extracted by segmentation based on hue information for a captured image in which the type and color of the main subject are not specified in advance.

<Description of other embodiments>
FIG. 7 is a block diagram illustrating a configuration example of an electronic camera according to another embodiment. The electronic camera 31 includes a focusing lens 32, a lens driving unit 33, an image sensor 34, a control unit 35, a ROM 36, a main memory 37, a monitor 38, a recording I / F 39, and a release button 40. is doing. Here, the lens driving unit 33, the image sensor 34, the ROM 36, the main memory 37, the monitor 38, the recording I / F 39, and the release button 40 are respectively connected to the control unit 35.

  The focusing lens 32 is a lens for performing focus adjustment. The lens position of the focusing lens 32 is adjusted by the lens driving unit 33 in the optical axis direction.

  The image sensor 34 captures an image of a subject formed by an imaging optical system including the focusing lens 32 and generates an image signal of a color captured image. The image signal output from the image sensor 34 is input to the control unit 35 via an A / D conversion circuit (not shown).

  Here, in the photographing mode of the electronic camera 31, the image sensor 34 captures a still image for recording (main image) in response to a full press operation of the release button 40. Further, the imaging device 34 in the shooting mode continuously takes images for observation (through images) at predetermined intervals even during standby for shooting. Here, the data of the through image acquired in time series is used for moving image display on the monitor 38 and various arithmetic processes by the control unit 35.

  The control unit 35 is a processor that comprehensively controls the operation of the electronic camera 31. For example, the control unit 35 executes well-known autofocus (AF) control and automatic exposure (AE) calculation, respectively, using the through image data. In addition, the control unit 35 functions as an image processing unit 41, an attention area setting unit 42, a frequency distribution generation unit 43, a color component analysis unit 44, and an area division unit 45 by executing a program stored in the ROM 36.

  The image processing unit 41 performs various types of image processing (color interpolation processing, gradation conversion processing, contour enhancement processing, white balance adjustment, color conversion processing, etc.) on the captured image data. Note that the functions of the attention area setting section 42, the frequency distribution generation section 43, the color component analysis section 44, and the area division section 45 are substantially the same as in the above-described one embodiment.

  The ROM 36 stores a program executed by the control unit 35. An example of the operation in the shooting mode by this program will be described later. The main memory 37 temporarily stores image data in a pre-process or post-process of image processing by the image processing unit 41. The monitor 38 displays various images according to instructions from the control unit 35.

  The recording I / F 39 has a connector for connecting a nonvolatile storage medium 39a. The recording I / F 39 executes data writing / reading with respect to the storage medium 39a connected to the connector. The storage medium 39a is composed of a hard disk, a memory card incorporating a semiconductor memory, or the like. In FIG. 7, a memory card is illustrated as an example of the storage medium 39a.

  The release button 40 receives from the user an instruction input for starting an AF operation before photographing by a half-press operation and an instruction input for starting an imaging operation by a full-press operation.

  Next, referring to the flowchart of FIG. 8, an operation example in the shooting mode in the electronic camera 31 of another embodiment will be described.

  The electronic camera 31 in this shooting mode divides the through image region based on the main color component range obtained from the region of interest, and switches the AE algorithm based on the result of the region division. Note that the processing in the flowchart of FIG. 8 is started in response to a user's shooting mode activation operation under the control of the control unit 35.

  Step S201: The control unit 35 drives the imaging device 34 to start capturing a through image. Thereafter, the through images are sequentially generated at predetermined intervals. The through image data output from the image sensor 34 is input to the control unit 35.

  Further, the control unit 35 in the shooting mode causes the monitor 38 to display a moving image of the display image (view image) generated from the through image. Therefore, the user can perform framing for determining the shooting composition with reference to the view image on the monitor 38.

  Step S202: The control unit 35 determines whether or not a half-press operation of the release button 40 has been accepted. If the above requirement is satisfied (YES side), the process proceeds to S203. On the other hand, when the above requirement is not satisfied (NO side), the control unit 35 waits for a half-press operation of the release button 40.

  Step S203: The control unit 35 performs AF by a known contrast detection method using the through image. In the AF described above, the control unit 35 sets a focus detection area in the shooting screen (shooting range of the through image) based on an algorithm such as closest priority or center priority (or designation in the user's manual), and this focus. The position of the focusing lens 32 is adjusted so that the subject in the detection area is in focus. The control unit 35 acquires a through image to be processed after AF.

  Step S204: The image processing unit 41 converts the color space of the through image (S203) to be processed into the HSV color space (or HLS color space). Note that the processing in S204 corresponds to the processing in S102 in FIG.

  Step S205: The attention area setting unit 42 sets the attention area in a part of the through image to be processed with reference to the position of the focus detection area in S203 (the XY position of the focus detection area in the photographing screen). The attention area setting unit 42 in S205 sets the area corresponding to the focus detection area in the photographing screen as the attention area as it is.

  Step S206: The frequency distribution generation unit 43 pays attention to the hue component (H) of each pixel included in the attention area of the through image to be processed, and indicates the correspondence between the hue component and the number of pixels in the attention area. Find the distribution. The process of S206 corresponds to the process of S104 in FIG.

  Step S207: The control unit 35 smoothes the change in frequency between adjacent hues with respect to the frequency distribution of the hue components in the attention area (obtained in S206). Note that the processing of S207 corresponds to the processing of S105 in FIG.

  Step S208: The color component analysis unit 44 sets at least one or more main color component ranges in the attention area based on the frequency distribution of the hue components in the attention area (smoothed in S207). Note that the processing in S208 corresponds to the processing in S106 in FIG.

  Step S209: The area dividing unit 45 performs area division of the through image based on the hue value of each pixel in the through image to be processed. Then, the area dividing unit 45 extracts the area of the main subject from the through image after the area division. Note that the processing of S209 corresponds to the processing of S107 in FIG.

  Step S210: The control unit 35 adjusts the shooting conditions using information on the area of the main subject (obtained in S209).

  As an example, the control unit 35 in S210 changes the AE algorithm according to the extent of the area of the main subject on the shooting screen. Specifically, when the area of the main subject is collected, the control unit 35 performs AE calculation by spot photometry. On the other hand, when the area of the main subject is widened, the control unit 35 performs AE calculation by split photometry.

  As another example, the control unit 35 in S210 may switch the setting of the scene mode based on the extent of the main subject area and the hue component. Specifically, when the area of the main subject is grouped and the hue of the area of the main subject is close to skin color, the control unit 35 sets the scene mode to “portrait shooting”. When the main subject area is wide and the hue of the main subject area is close to green, the control unit 35 sets the scene mode to “landscape photography”.

  Step S211: The control unit 35 determines whether or not a full pressing operation of the release button 40 has been accepted. If the above requirement is satisfied (YES side), the process proceeds to S213. On the other hand, if the above requirement is not satisfied (NO side), the process proceeds to S212.

  Step S212: The control unit 35 determines whether or not the half-press operation of the release button 40 has been released. If the above requirement is satisfied (YES side), the control unit 35 returns to S202 and repeats the above operation. On the other hand, when the above requirement is not satisfied (NO side), the control unit 35 returns to S211 and waits for a full pressing operation of the release button 40.

  Step S213: The control unit 35 drives the imaging device 34 in response to the full press of the release button 40, and executes the imaging process of the main image. The data of the main image is recorded in the storage medium 39a via the recording I / F 39 after being subjected to predetermined processing by the image processing unit 41. Above, description of the flowchart of FIG. 8 is complete | finished.

  The electronic camera 31 of the other embodiment performs the region division of the through image and extracts the region of the main subject by the algorithm almost the same as that of the one embodiment. Then, the electronic camera 31 performs AE calculation, scene mode setting, and the like using information on the area of the main subject. Therefore, the electronic camera 31 according to another embodiment can accurately extract various main subjects from the information of the through image, and can acquire a good shot image under shooting conditions according to the main subject.

<Supplementary items of the embodiment>
(1) In each of the above embodiments, an example has been described in which the functions of the attention region setting unit, the frequency distribution generation unit, the color component analysis unit, and the region division unit are realized by software. Of course, each part may be realized by hardware.

  (2) In the other embodiments described above, the configuration example of the compact electronic camera has been described. However, the imaging apparatus of the present invention can of course be applied to a single-lens reflex type electronic camera in which lenses can be exchanged. Note that when the present invention is applied to a single-lens reflex electronic camera, a through image may be captured by an image sensor that captures the main image, and the through image is separate from the image sensor that captures the main image. An image sensor for imaging the image may be provided.

  The imaging device of the present invention can also be applied to a camera module built in an electronic device such as a mobile phone.

  (3) In the above-described one embodiment, when the position of the focus detection area cannot be acquired from the shooting information, the attention area setting unit 21 selects, for example, an attention area having a vertical and horizontal size of 1/4 at the center position of the captured image. It may be set.

  (4) In the above-described embodiment, the image processing apparatus uses the reduced image having a smaller image size than the captured image of the image file (for example, an image obtained by thinning the captured image) as a processing target. May be performed.

(5) In each of the above-described embodiments, the example in which the image to be processed is converted into the HSV color space or the HLS color space has been described, but the image to be processed may be converted into another color space. Center as an ^example, the case of L ^* a * ^{b *} color space, frequency distribution generating unit maps each pixel of the region of interest on ^{the a} * ^{b * plane,} a * ^{b *} plane of the color coordinates (0, 0) The frequency distribution in the rotation direction is obtained.

  (6) In the one embodiment described above, the color component analysis unit 23 in S106 searches the peak and valley positions on the distribution function in advance, and then determines the range of the main color component according to the frequency value height. May be sequentially determined.

  From the above detailed description, features and advantages of the embodiments will become apparent. It is intended that the scope of the claims extend to the features and advantages of the embodiments as described above without departing from the spirit and scope of the right. Further, any person having ordinary knowledge in the technical field should be able to easily come up with any improvements and modifications, and there is no intention to limit the scope of the embodiments having the invention to those described above. It is also possible to use appropriate improvements and equivalents within the scope disclosed in.

DESCRIPTION OF SYMBOLS 11 ... Computer, 14 ... CPU, 21, 42 ... Attention area setting part, 22, 43 ... Frequency distribution generation part, 23, 44 ... Color component analysis part, 24, 45 ... Area division part, 31 ... Electronic camera, 35 ... Control unit

JP2001-14457

Claims (6)

An attention area setting unit that obtains a captured image captured by the imaging apparatus and shooting information of the captured image, and sets an attention area in a part of the captured image using the shooting information;
A frequency distribution generation unit for determining a frequency distribution of color components included in the image of the region of interest;
A color component analyzer that sets at least one or more main color component ranges in the region of interest based on the frequency distribution;
Classifying the color components at each position of the captured image according to the range of the main color components, and an area dividing unit for dividing the area of the captured image based on the classification result;
An image processing apparatus comprising: The image processing apparatus according to claim 1.
The image processing apparatus, wherein the region of interest setting unit sets the region of interest using position information of a focus detection area when the captured image is captured. The image processing apparatus according to claim 1 or 2,
An image processing apparatus using hue information as the color component. The image processing apparatus according to any one of claims 1 to 3,
The area dividing unit extracts an area of a main subject from the photographed image based on a range of the main color component showing a value with the highest frequency of color components in the frequency distribution. .   A camera comprising the image processing apparatus according to any one of claims 1 to 4. Attention area processing for acquiring a photographed image photographed by the imaging device and photographing information of the photographed image, and setting a attention area in a part of the photographed image using the photographing information;
A frequency distribution generation process for obtaining a frequency distribution of color components included in the image of the region of interest;
A color component analysis process for setting at least one or more main color component ranges in the region of interest based on the frequency distribution;
Classifying the color components at each position of the photographed image according to the range of the main color components, and area division processing for performing area division of the photographed image based on the classification result;
A program that causes a computer to execute.