JP2010220122A - Image processing apparatus, image capturing apparatus, image processing method, and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To correctly detect an object area and thereby to provide image data high in power of expression. <P>SOLUTION: The image processing apparatus includes: a face area detection processing unit 103 for detecting a face area of an object included in image data; an image area division processing unit 105 for obtaining a plurality of divided areas of the image data in response to luminance information or color information of the image data; and a personal area generation part 106 for obtaining divided areas constituting the object within the plurality of obtained divided areas based on the detected face area. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing device, an imaging device, an image processing method, and an image processing program.

  In recent years, image data having a shallow depth of field has been demanded in order to improve the ability to express image data. However, since the digital camera has a small CCD (Charge Coupled Device) size, the focal length of the lens is short. Therefore, image data captured by a digital camera is often image data having a deep depth of field. Therefore, the expressiveness of the image data can be improved by detecting the face area of the image data and performing blurring processing around the detected face area. However, in order to obtain image data with higher expressive power, it is necessary to detect not the face area but the entire subject area with higher accuracy.

  As a technique for detecting a subject area in this manner, for example, a technique is known in which a subject area is detected from an image obtained by photographing a target using a single color of blue or green as a background (see Patent Document 1). .

  For example, a technique of detecting a face area included in a subject area of image data is known (see Patent Document 2). Specifically, in the technique of Patent Document 2, the skin color of the face area is detected, the area is divided by the saturation, and the detection is performed based on the size of the area.

  For example, a technique of detecting a body part of a subject area of image data is known (see Patent Document 3). Here, the body part includes the head, face, hands, feet, and torso of the subject.

  However, the invention disclosed in Patent Document 1 has a problem that the subject area cannot be detected when a single color of blue or green is not used as the background of the image data.

  In the invention disclosed in Patent Document 2, a face area can be detected from image data, but a subject area including the face area cannot be detected.

  Further, in the invention disclosed in Patent Document 3, when the subject area is detected from the image data, the subject area is approximated by an elliptical shape, and therefore there is a possibility that the detected area includes an area other than the subject. In this case, there is a problem that the subject area cannot be accurately detected.

  The present invention has been made in view of the above, and is capable of accurately detecting a subject area, thereby obtaining image data with high expressive power, an imaging apparatus, and an image processing method. And an image processing program.

  An image processing apparatus according to the present invention obtains a plurality of pieces of partial area information of the image data according to brightness information or color information of the image data, and a face area detection unit that detects a face area of a subject included in the image data. An area information acquisition means for performing acquisition, and a subject area acquisition means for acquiring partial area information constituting the subject among the plurality of acquired partial area information based on the detected face area. To do.

  An imaging apparatus according to the present invention includes an imaging unit that images a subject, image information acquisition means that acquires image information captured by the imaging unit as image data, and a face area of the subject included in the image data. Acquired based on the detected face area detection means, area information acquisition means for acquiring a plurality of partial area information of the image data in accordance with luminance information or color information of the image data, and the detected face area Subject area obtaining means for obtaining partial area information constituting the subject among the plurality of pieces of partial area information.

  According to the present invention, a plurality of pieces of partial area information is acquired from image data according to luminance information or color information, and the subject's face area information detected from the image data is referred to, and the subject is obtained from the pieces of partial area information. Is selected. As a result, the entire area including the face area can be detected with higher accuracy.

FIG. 1 is a block diagram illustrating a functional configuration of the image processing unit according to the first embodiment. FIG. 2 is an explanatory diagram illustrating an example of a processing result of the face detection processing according to the first embodiment. FIG. 3 is an explanatory diagram illustrating an example of elliptical area generation according to the first embodiment. FIG. 4 is an explanatory diagram illustrating an example of generation of a small divided area in the area division of the image area dividing process according to the first embodiment. FIG. 5 is an explanatory diagram illustrating an example of generation of a divided area in the area division of the image area division processing according to the first embodiment. FIG. 6 is an explanatory diagram illustrating an example of a person area generation process according to the first embodiment. FIG. 7 is an explanatory diagram illustrating an example of a processing result of the person area generation according to the first embodiment. FIG. 8 is a flowchart illustrating a processing procedure in the image processing unit according to the first embodiment. FIG. 9 is a flowchart illustrating a processing procedure of image region division performed by the image region division processing unit according to the first embodiment. FIG. 10 is a flowchart illustrating a procedure of generating a person area performed by the person area generating unit according to the first embodiment. FIG. 11 is a block diagram illustrating a hardware configuration of the digital camera according to the first embodiment. FIG. 12 is a block diagram of a functional configuration of the image processing apparatus according to the second embodiment. FIG. 13 is a block diagram of a hardware configuration of the image processing apparatus according to the second embodiment. FIG. 14 is a flowchart illustrating a processing procedure in the image processing apparatus according to the second embodiment.

  Exemplary embodiments of an image processing apparatus, an imaging apparatus, an image processing method, and an image processing program according to the present invention are explained in detail below with reference to the accompanying drawings.

(First embodiment)
A first embodiment will be described with reference to the accompanying drawings. First, a configuration example of an image processing unit included in a digital camera to which the present invention is applied will be described.

  FIG. 1 is a block diagram illustrating a functional configuration of the image processing unit according to the first embodiment. Image data generated by the imaging unit 100 is subjected to image processing by the image processing unit 101 and transmitted to the external storage device 109. The image processing unit 101 includes an image input unit 102, a face region detection processing unit 103, an elliptical region generation unit 104, an image region division processing unit 105, a person region generation unit 106, an image correction processing unit 107, an image An output unit 108 is mainly provided.

  The image input unit 102 receives input of image data from the outside, and inputs the image data to the face region detection processing unit 103 and the image region division processing unit 105.

  The face area detection processing unit 103 performs face area detection processing on the image data acquired by the image input unit 102, and detects a face rectangular area as face area image information. The face rectangular area is a rectangle recognized as a rectangle including the face area, and the rectangle in this embodiment is described as a square.

  Here, the face area detection process uses a known face area detection technique. For example, a vertex of a person's hair is detected by chroma key processing, and a face rectangular area based on the vertex is detected. Further, the user may manually specify the face rectangular area, or the face rectangular area may be detected semi-automatically based on the information input by the user.

  FIG. 2 is an explanatory diagram illustrating an example of a processing result of the face detection processing. The image 200 is image data that has undergone face detection processing, and includes a face area 201, a face rectangular area 202, a body area 203, and a background area 204. The face area 201 is a face area included in the person area. Here, the person area corresponds to the subject area in other words. Although the subject area of the present embodiment has been described as a person area, it can also be applied to an overall image of an object such as a doll or an animal as an example of another subject area.

  The face rectangular area 202 is output as a result of the face detection process, and is a rectangular area. The body area 203 is an area other than the face area included in the person area. The background area 204 is a background area of a person.

The ellipse area generation unit 104 functioning as candidate area generation means generates an ellipse using the center coordinates (x _o , _yo ) of the face rectangular area detected by the face area detection processing unit 103 and the width w of the face rectangular area. To do. Here, the position and size of the face area correspond to the center coordinates and the width of the face rectangular area, respectively.

The ellipse indicates a person candidate area, in other words, corresponds to a subject candidate area. The ellipse region generation unit 104 generates a candidate region, in other words, corresponds to a candidate generation unit. Note that although the ellipse generation unit has been described as the candidate generation unit of the present embodiment, other forms may be applied to indicate the person candidate region.

FIG. 3 is an explanatory diagram showing an example of elliptical region generation. The ellipse 301 is determined from the center coordinates (x _o , y _o ) of the face rectangular area 202 and the width w of the face rectangular area. The ellipse is defined by E (x, y, a, b), with the ellipse center coordinates (x, y), the short axis of the ellipse as a, the long axis of the ellipse as b. In this case, as illustrated, the center point of the face rectangular area 202 and the center point of the ellipse 301 are on the same straight line.

As an example of how to obtain an ellipse, the ellipse is derived by an experiment by the following method. First, when the width of the person area is Wp and the ratio of Wp to w is ka, ka = 2 can be obtained as an example of the experimental result. Here, when the maximum value of Wp is the same as the ellipse minor axis a, the following equation (1) is obtained.
a = 2w (1)

Next, the relationship between the major axis b of the ellipse and the width w of the face rectangular area is obtained. Assuming that half the height of the person is hb and the ratio of hb to w is kb, kb = 6.5 could be obtained as an example of the experimental result. Here, when the maximum value of hb is the same as the radius of the major axis, the following equation (2) is obtained.
b = 13w (2)

Further, as described above, since the center point of the face rectangular area and the center point of the ellipse are on the same straight line, the following equation (3) is obtained.
x = x _o (3)

Also, the y coordinate of the ellipse is obtained. The distance in the y-axis direction from the center point of the face rectangular area to the vertex of the face area is yb. As an example of the experiment, yb was able to obtain a result of about 1.5 times the width w of the face rectangular area. Therefore, the following expression (4) is obtained.
_{y = y o + 1.5w-0.5b} ··· (4)

Therefore, as shown in FIG. 3, when the ellipse is determined from the center coordinates (x _o , _yo ) of the face rectangular area and the width w of the face rectangular area, the ellipse is obtained by Expressions (1) to (4) as an example. It is done.

In the present embodiment, the ellipse is obtained from the equations (1) to (4). However, since the experiment result changes by changing the experiment environment, x, y, a, b and w, x _o , _yo The relationship may be changed.

  Further, the ellipse area generation unit 104 may be configured to show an ellipse in an operation unit described later so that the user can confirm the person candidate area when acquiring the person area from the image data. Here, the operation unit is a display unit for displaying an ellipse.

  The image region division processing unit 105 performs image processing on the image data acquired by the image input unit 102. The image area division processing unit 105 corresponds to an area information acquisition unit in other words. Focusing on the luminance information and color information of the image data, the division processing is performed by setting the regions where the difference between contrast and color is small as the same region.

  First, the image region division processing unit 105 performs filtering on image data with a low-pass filter. By performing the filtering, the brightness and color of the image data are smoothed.

  Next, the image area division processing unit 105 specifies areas having different colors and contrasts from the image data in which colors and edges are smoothed. That is, if the difference between the color and contrast of adjacent pixels in the smoothed image data is equal to or less than a certain threshold value, the pixels are in the same group. Therefore, the image area is divided into a plurality of areas by generating a large number of groups. This area is defined as a small divided area.

  FIG. 4 is an explanatory diagram showing an example of generation of a small divided area in the area division of the image area dividing process. The image 400 is image data that has been subjected to image region division processing, and includes small divided regions 401 to 416.

  Then, when the number of pixels existing in the grouped sub-divided area is smaller than a certain threshold number of pixels, the image area division processing unit 105 combines with a group of adjacent areas having a large number of adjacent pixels that are close in color and contrast. . The divided area is a group of the combined areas, and in other words, corresponds to partial area information. The image data of the divided area can be obtained by performing the above processing.

  FIG. 5 is an explanatory diagram showing an example of generation of divided areas in the image area dividing process. The image 500 is image data in which a divided area is generated in the image area dividing process, and includes a divided area 501, a divided area 502, and a divided area 503.

  The divided area 501 is an area including the small divided area 401, the small divided area 402, the small divided area 403, the small divided area 404, and the small divided area 405 of FIG.

  The divided area 502 is an area including a small divided area 414, a small divided area 415, and a small divided area 416.

  The divided area 503 is an area including a small divided area 406, a small divided area 407, a small divided area 408, a small divided area 409, a small divided area 410, a small divided area 411, a small divided area 412, and a small divided area 413. .

  The person area generation unit 106 generates a person area by selecting a divided area constituting the person from the image data of the divided area output from the image area division processing unit 105 using the ellipse generated by the ellipse area generation unit 104. Perform the process. Specifically, the person area generation unit 106 acquires a divided area included in the ellipse by removing the divided area that contacts the outer periphery of the ellipse, and detects and generates the person area. In other words, the person area generation unit 106 corresponds to subject area acquisition means.

  There is a method of dividing the image data into regions by grouping neighboring pixels whose luminance information or color information is below an arbitrary threshold by referring to the luminance information and color information of the image data. Therefore, it is impossible to acquire a person region with high accuracy. Therefore, the person area generation unit 106 according to the present embodiment generates a candidate area by referring to the position and size information of the face area, and acquires a divided area included in the generated person candidate area as a person area. .

  FIG. 6 is an explanatory diagram illustrating an example of a person area generation process. The image 600 is image data for performing a human region generation process by superimposing the divided region image data output from the image region division processing unit 105 on the ellipse output from the elliptic region generation unit 104. The image 600 includes a divided area 501, a divided area 502, a divided area 503, and an ellipse 301. The inner area of the ellipse 301 is a person area candidate.

  Here, by removing the divided area 502 and the divided area 503 that are in contact with the outer periphery of the ellipse 301, the divided area 501 can be generated as a person area.

  FIG. 7 is an explanatory diagram illustrating an example of a processing result of person area generation. An image 700 is image data of a person area generation processing result, and includes a person area 701 and an outside person area 702.

  The image correction processing unit 107 performs image correction processing on each of the person area 701 and the outside person area 702 using the image data generated from the person area generation unit 106.

  For example, the image correction processing unit 107 performs AWB (Auto White Balance) processing on each of the person area 701 and the outside person area 702, and performs optimal color processing. By performing this image correction process, it is possible to improve the image quality of the image data.

  Further, for example, the image correction processing unit 107 performs background blurring processing by performing blurring processing only on the non-person area 702, and can generate image data with high expressive power that makes a person appear. .

  The image output unit 108 outputs the image data corrected by the image correction processing unit 107.

  Next, processing for generating a person area from input image data in the image processing unit 101 according to the present embodiment configured as described above will be described. FIG. 8 is a flowchart illustrating the above-described processing procedure in the image processing unit 101 according to the present embodiment.

  First, the image input unit 102 inputs image data to the face area detection processing unit 103 and the image area division processing unit 105 (step S801).

  Next, the face area detection processing unit 103 detects a face area from the image data acquired by the image input unit 102 (step S802). As an example of processing for detecting a face area, a vertex of a person's hair can be detected by chroma key processing, and a face rectangular area based on the vertex can be detected.

  Next, the ellipse area generation unit 104 generates an ellipse by referring to the center coordinates of the face rectangle area detected by the face area detection processing unit 103 and the width of the face rectangle area (step S803). As an example of an ellipse, an ellipse is generated using equations (1) to (4).

  The image area division processing unit 105 divides the image area from the image data acquired by the image input unit 102 (step S804). Note that step S804 is executed in parallel with the processing of step S802 and step 803. Details of the image region dividing process will be described later.

  Next, the person area generation unit 106 generates a person area by superimposing the image data of the divided area output from the image area division processing unit 105 on the ellipse generated by the ellipse area generation unit 104 (step S805). Details of the person area generation processing will be described later.

  Next, the image correction processing unit 107 corrects the image using the image data generated from the person area generation unit 106 (step S806). That is, image correction processing is performed on each of the person area and the outside person area.

  Next, the image output unit 108 outputs the image data corrected by the image correction processing unit 107 (step S807).

  By detecting the face area for the image data by the processing procedure described above, it is possible to generate an ellipse from the face area information and to generate a person area from the ellipse area. Note that the above-described procedure performs face area detection processing on the image data in the image processing unit 101 according to the first embodiment to generate an ellipse, and removes the non-human area existing inside the ellipse area. Shows an example of a procedure for generating a person area, and is not limited to the processing procedure described above.

  Next, details of the image region dividing process will be described. FIG. 9 is a flowchart illustrating a processing procedure of image region division performed by the image region division processing unit 105.

  First, the image area division processing unit 105 acquires image information (step S901).

  Next, a filtering process is performed on the image data (step S902). First, the image data is filtered with a low-pass filter. As the low-pass filter, a normal Gaussian filter is used. The brightness and color of the image data are smoothed by filtering.

  In this embodiment, a normal Gaussian filter is used as a low-pass filter for image data in the image region division processing unit 105, but the Gaussian filter is not used, and the luminance of the image data is not reduced by another low-pass filter. Processing may be performed so as to smooth the colors.

  Next, each pixel is grouped to generate a small divided region (step S903). That is, areas having different colors and contrasts are specified for image data in which colors and edges are smoothed. That is, if the difference between the color and contrast of adjacent pixels in the smoothed image data is equal to or less than a certain threshold value, the pixels are in the same group. A large number of groups are generated as small divided areas.

  Next, a small divided region with a small number of pixels is combined with a small divided region with a large number of pixels to generate a divided region (step S904). That is, when the number of pixels existing in the grouped small divided region is smaller than a certain threshold number of pixels, the divided region is generated by combining with a group of adjacent regions having a large number of adjacent pixels that are close in color and contrast.

  Then, the image data of the divided area is output to the person area generation unit 106 (step S905).

  By paying attention to adjacent pixels close in color and contrast by the processing procedure described above, the image area can be divided. The above-described procedure is an example of a procedure for dividing an image area by performing a smoothing process on the image data in the image area division processing unit 105 according to the first embodiment. The present invention is not limited to the processing procedure described above.

  Next, details of the person area generation processing will be described. FIG. 10 is a flowchart showing a procedure for generating a person area performed by the person area generator 106.

  First, the person area generation unit 106 acquires an ellipse that is a person candidate area from the ellipse area generation unit 104 (step S110). The acquired inner area of the ellipse is a candidate area for the person area.

  Next, the image data of the divided area is acquired from the image area division processing unit 105 (step S111).

  Next, the ellipse acquired in step S110 and the image data of the divided area acquired in step S111 are combined, and the partial area that contacts the ellipse is deleted (step S112). That is, it is determined that the plurality of divided areas that are in contact with the ellipse are not person areas and are removed. Thereby, the remaining divided areas can be identified and generated as person areas.

  Next, a hardware configuration of a digital camera that is an example of an imaging apparatus that performs the above-described image processing will be described. FIG. 11 is a block diagram showing a hardware configuration of the digital camera according to the present embodiment. As shown in FIG. 11, subject light first enters a CCD (Charge Coupled Device) 3 through the photographing optical system 1 of the digital camera 1000. A mechanical shutter 2 is disposed between the photographing optical system 1 and the CCD 3, and incident light on the CCD 3 can be blocked by the mechanical shutter 2. The photographing optical system 1 and the mechanical shutter 2 are driven by a motor driver 6.

  The CCD 3 converts an optical image formed on the imaging surface into an electrical signal and outputs it as analog image data. The image information output from the CCD 3 is subjected to removal of noise components by a CDS (Correlated Double Sampling) circuit 4 and converted to a digital value by an A / D converter 5, and then to an image processing circuit 8. Is output.

  The image processing circuit 8 performs various image processing such as YCrCb conversion processing, white balance control processing, contrast correction processing, edge enhancement processing, and color conversion processing using an SDRAM (Synchronous DRAM) 12 that temporarily stores image data. . The white balance control process is an image process for adjusting the color density of image information, and the contrast correction process is an image process for adjusting the contrast of image information. The edge enhancement process adjusts the sharpness of image information, and the color conversion process is an image process that adjusts the hue of image information. The image processing circuit 8 displays the image information subjected to signal processing and image processing on a liquid crystal display 16 (hereinafter abbreviated as “LCD 16”).

  The image information subjected to the signal processing and the image processing is recorded in the memory card 14 via the compression / decompression circuit 13. The compression / decompression circuit 13 compresses the image information output from the image processing circuit 8 according to the instruction acquired from the operation unit 15 and outputs the compressed image information to the memory card 14, and decompresses the image information read from the memory card 14. This is a circuit for outputting to the image processing circuit 8.

  The timing of the CCD 3, the CDS circuit 4, and the A / D converter 5 is controlled by a CPU (Central Processing Unit) 9 via a timing signal generator 7 that generates a timing signal. Further, the image processing circuit 8, the compression / decompression circuit 13, and the memory card 14 are also controlled by the CPU 9.

  In the imaging apparatus, the CPU 9 performs various arithmetic processes in accordance with a program, and has a ROM (Read Only Memory) 11 that is a read-only memory storing the program, a work area used in various processes, and various data storage areas. A RAM (Random Access Memory) 10 that is a writable memory is built in, and these are interconnected by a bus line.

  The imaging apparatus first inputs image data, and temporarily stores the input image in the memory area SDRAM. At this time, a person area generation process and an image correction program are started from the ROM 11 to perform the person area generation process. In response to the person region generation result, image correction processing is performed.

  The image processing program executed by the digital camera according to the present embodiment has a module configuration including the above-described human area separation and image correction functions. As actual hardware, a CPU (processor) can store images from the storage medium. By reading and executing the processing program, the above-described units are loaded onto the main storage device, a person area is generated, image correction processing is performed, and the image is compressed to be generated on the memory card.

  As described above, according to the imaging apparatus according to the first embodiment, the image input unit 102 sends the image data acquired from the imaging unit 100 to the face area detection processing unit 103, and the face area detection processing unit 103 When the face area is detected and the ellipse area generation unit 104 generates an ellipse from the detected face area information, the image area division processing unit 105 selects a plurality of divided areas from the image data acquired from the image input unit 102. When acquired, the person area generation unit 106 superimposes the divided area on the ellipse, thereby acquiring the divided area included in the ellipse as a person area. Therefore, the person area including the face area can be detected with higher accuracy. it can. For this reason, the expressive power of image data can be improved.

  In the first embodiment, an example in which the first embodiment is applied to an imaging apparatus has been described. However, the present invention is not limited to the imaging device, and can be applied to various devices. Therefore, the second embodiment will be described as an example of an embodiment adapted to another device.

(Second Embodiment)
A second embodiment will be described with reference to the accompanying drawings. The second embodiment is an example in which an image processing apparatus is applied. Here, a different part from 1st Embodiment is demonstrated.

  In this embodiment, an image file recorded from the photographing apparatus is input by an image input unit. A human region generation process is performed on the input image data to perform image correction.

  FIG. 12 is a block diagram illustrating a functional configuration of the image processing apparatus. Image data captured from the memory card driver 120 is subjected to image processing by the image processing device 121 and transmitted to the storage device 129 and the printer engine 130. The image processing apparatus 121 includes an image input unit 122, a face region detection processing unit 123, an elliptical region generation unit 124, an image region division processing unit 125, a person region generation unit 126, an image correction processing unit 127, an image An output unit 128 is mainly provided. Here, the image processing device 121, the image input unit 122, the face area detection processing unit 123, the ellipse area generation unit 124, the image area division processing unit 125, the person area generation unit 126, and the image correction processing unit 127. Since the function and configuration of the image output unit 128 are the same as those in the first embodiment, description thereof is omitted.

  The memory card driver 120 is a driver that reads an image file stored in the memory card. Further, the storage device 129 stores the image data that has been subjected to image processing by the image processing device 121. The printer engine 130 is a part that executes printing.

  Next, processing in the image processing apparatus 121 configured as described above will be described. FIG. 14 is a flowchart illustrating the above-described processing procedure in the image processing apparatus 121.

  First, the image input unit 122 acquires an image file, and inputs image data to the face area detection processing unit 123 and the image area division processing unit 125 (step S141).

  Next, in the same manner as steps S802 to S807 in FIG. 8 of the first embodiment, face area detection processing is performed on the image data to generate an ellipse, and an area outside the person existing inside the ellipse area is determined. The process until the person area is generated by removing is performed (steps S142 to S147). Therefore, by acquiring an image file and detecting the face area, it is possible to generate an ellipse from the face area information and generate a person area from the ellipse area.

  FIG. 13 is a block diagram showing a hardware configuration of the image processing apparatus according to the present embodiment. The image processing apparatus 2000 includes a CPU (Central Processing Unit) 24 that centrally controls each unit. The CPU 24 includes a ROM (Read Only Memory) 22 that is a read-only memory storing a BIOS and the like, and various types of CPUs. A RAM (Random Access Memory) 21 that stores data so as to be rewritable and functions as a work area of the CPU is connected by a bus to constitute a microcomputer. Further, an HDD 25 in which a control program is stored, a CD-ROM drive 26 that reads a CD (Compact Disc) -ROM, and an I / F 23 that is an interface that manages communication with a printer unit and the like are connected to the bus. .

  A CD-ROM 28 shown in FIG. 13 stores a predetermined control program. The CPU 24 reads the control program stored in the CD-ROM 28 with the CD-ROM drive 26 and installs it in the HDD 25. Thereby, it will be in the state which can perform various processes as mentioned above. The memory card 29 stores image information and the like and is read by the memory card driver 27.

  As storage media, not only CD-ROMs and memory cards but also various types of media such as various optical disks such as DVDs, various magneto-optical disks such as DVDs, floppy disks (registered trademark), semiconductor memories, etc. Can be used. Alternatively, the program may be downloaded from a network such as the Internet and installed in the HDD 25. In this case, the storage device storing the program in the server on the transmission side is also a storage medium of the present invention. Note that the program may operate on a predetermined OS (Operating System), in which case the OS may execute a part of various processes described later, or a word processor. It may be included as part of a group of program files that constitute predetermined application software such as software or an OS.

  The background blurring program executed by the image processing apparatus according to the present embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Further, the image processing program executed by the image processing apparatus of the present embodiment may be provided or distributed via a network such as the Internet.

  Further, the image processing program according to the present embodiment may be provided by being incorporated in advance in a ROM or the like.

  In this embodiment, when shooting, it is necessary to record shooting conditions at the time of image recording, and shooting condition information is recorded in an image file. The person area generation method and the image correction processing method are the same as those in the first embodiment.

  An image processing program executed by the image processing apparatus according to the present embodiment is an installable or executable file, such as a CD-ROM, a flexible disk (FD), a CD-R, or a DVD (Digital Versatile Disk). The program is provided by being recorded on a computer-readable recording medium.

  As described above, according to the image processing apparatus according to the second embodiment, the face area detection processing unit 123 detects the human face area from the image data acquired from the image input unit 122, and the ellipse is detected from the detected face area information. When the region generation unit 124 generates an ellipse and the image region division processing unit 125 acquires a plurality of divided regions from the image data acquired from the image input unit 122, the person region generation unit 126 divides the ellipse into ellipses. Since the divided areas included in the ellipse are acquired as person areas by overlapping the areas, the person area including the face area can be detected with higher accuracy. For this reason, the expressive power of image data can be improved.

  Further effects and modifications can be easily derived by those skilled in the art. The embodiments of the present invention are not limited to the specific embodiments as described above.

DESCRIPTION OF SYMBOLS 100 Image pick-up part 101 Image processing part 102 Image input part 103 Face area detection process part 104 Elliptical area generation part 105 Image area division | segmentation process part 106 Person area generation part 107 Image correction process part 108 Image output part 109 External storage device 200 Image 201 Face Area 202 face rectangular area 203 body area 204 background area 301 ellipse 400 image 401 small divided area 402 small divided area 403 small divided area 404 small divided area 405 small divided area 406 small divided area 407 small divided area 408 small divided area 409 small divided area 409 Area 410 Subdivision area 411 Subdivision area 412 Subdivision area 413 Subdivision area 414 Subdivision area 415 Subdivision area 416 Subdivision area 500 image 501 subdivision area 502 subdivision area 503 subdivision area 600 image 700 image 701 person area 02 people outside the region

JP-A-8-191458 JP 2004-185555 A JP 2004-303193 A

Claims (7)

Face area detecting means for detecting a face area of a subject included in image data;
Area information acquisition means for acquiring a plurality of partial area information of the image data according to luminance information of the image data or color information;
Subject area acquisition means for selecting partial area information constituting the subject from the plurality of acquired partial area information based on the detected face area;
An image processing apparatus comprising: Candidate generation means for generating a subject candidate area for generating a candidate for the subject area based on the detected face area;
The image processing apparatus according to claim 1, wherein the subject area acquisition unit selects the partial area information included in the generated subject candidate area. The image processing apparatus according to claim 1, wherein the subject area acquisition unit acquires the partial area information based on a position and a size of the face area. A display unit for a user to confirm the subject candidate region in order to obtain the subject region from the image data;
The candidate generation means displays the subject candidate area as an elliptical area in a frame on the display unit;
The image processing apparatus according to any one of claims 1 to 3. An imaging unit for imaging a subject;
Image information acquisition means for acquiring image information captured by the imaging unit as image data;
Face area detecting means for detecting a face area of a subject included in the image data;
Area information acquisition means for acquiring a plurality of partial area information of the image data according to luminance information of the image data or color information;
Subject area acquisition means for acquiring partial area information constituting the subject among the plurality of acquired partial area information based on the detected face area;
An imaging apparatus comprising: A face area detecting step for detecting a face area of a subject included in the image data;
A region information acquisition step of acquiring a plurality of partial region information of the image data according to luminance information of the image data or color information;
A subject region acquisition step of acquiring partial region information constituting the subject among the plurality of acquired partial region information based on the detected face region;
An image processing method comprising:   An image processing program for causing a computer to execute an image processing method for acquiring a subject area from image data according to claim 6.

Images