JP2012095363A - Image processor, image processing method, and image processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processor for correcting a whole person, and for improving appearance of the subject person without limiting to the case that the person is photographed at a center of an image to be corrected.SOLUTION: An image processor extracts a face region of a person from an image to be corrected, specifies a region including the extracted face region as a reduction region to be corrected by reducing in the image to be corrected, specifies the region including the extracted face region as an enlargement region to be corrected by enlarging in the image to be corrected, reduces the image of the reduction region of the image to be corrected based on a prescribed reduction ratio, and generates a correction image in which the image of the enlargement region of the image to be corrected is enlarged, according to ratio of the reduction region to the enlargement region.

Description

  The present invention relates to an image processing apparatus, an image processing method, and an image processing program for correcting an image.

Conventionally, as a technique to improve the appearance of a person who is the subject of an image, the center part of an image such as a photograph containing a person is reduced, and both ends of the image are enlarged and corrected so that the aspect ratio of the image is not changed. There is a technology to improve the appearance by making the subject person photographed in the center of the screen slim. For example, a multifunction printer (MFP (Multifunction Peripheral) printer) or the like may be equipped with such a slim function.
As another technique for improving the appearance of a person who is a subject of an image, Patent Document 1 proposes a function for specifying a face area of a person included in an image and correcting the contour of the face.

JP 2004-318204 A

However, the subject person is not always located at the center of the image. With the function of slimming the center of the image as in the prior art, when the person is off the center of the image, the person is distorted or thick. There was a case. For example, in the prior art, as shown in FIG. 5A, even when a person is off the center of the image, a process for slimming the image with respect to the center is performed. In this process, as shown in FIG. 5B, a certain range from the center of the image is a reduced area, the outside of the reduced area is an enlarged area, and (b-1) and (b-4) The boundary between the reduced area and the enlarged area is specified. Then, the images in the reduced areas inside (b-1) and (b-4) are reduced so as to fit inside (b-2) and (b-3). At the same time, the images in the enlarged areas outside (b-1) and (b-4) are enlarged to the areas outside (b-2) and (b-3). In this case, as shown in FIG. 5B, there is a problem that the person shown at a position off the center of the image is enlarged and distorted or thickened.
On the other hand, the technique of Patent Document 1 corrects only the face area and cannot correct the entire person of the subject.

  The present invention has been made in view of such a situation, and is not limited to the case where a person is photographed at the center of the correction target image, and is an image that corrects the entire person and improves the appearance of the subject person. A processing apparatus, an image processing method, and an image processing program are provided.

The present invention has been made to solve the above problems, and an image processing apparatus according to the present invention includes a face area extraction unit that extracts a face area of a person included in an image to be corrected, and an image to be corrected. A region including the face region extracted by the face region extracting unit is specified as a reduced region, a correction region specifying unit that specifies a region other than the reduced region as an enlarged region, and a correction target image based on a predetermined reduction rate And a correction execution unit that reduces the image of the reduced area and generates a corrected image in which the image of the enlarged area of the correction target image is enlarged according to the ratio of the reduced area to the enlarged area.
In the image processing apparatus of the present invention having the above-described configuration, a human face area is extracted from an image to be corrected, and an area including the extracted face area is specified as a reduction area to be corrected to reduce the correction target image. The image to be corrected is identified as an enlargement area to be corrected, and the image in the reduction area of the image is reduced based on a predetermined reduction ratio, and the image enlargement area is set according to the ratio of the reduction area to the enlargement area. A corrected image is generated by enlarging the image.
This makes it possible to specify the reduction area and the enlargement area based on the position of the person's face included in the correction target image, and the person's face can be located at any position in the correction target image. For example, even when the image is present at a position off the center, the image can be corrected according to the position of the person.

The image processing apparatus according to the present invention further includes a central axis detection unit that detects a central axis that passes through the center of the face of the facial region extracted by the facial region extraction unit, and the correction region specifying unit is detected by the central axis detection unit. A region in a range perpendicular to the center axis is a reduced region.
In the image processing apparatus of the present invention having the above-described configuration, a central axis passing through the center of the face of the extracted facial area is detected, and an area including a facial area extending in a direction perpendicular to the detected central axis is defined as a reduced area. I tried to do it.
As a result, the reduction area of the image to be corrected can be specified with the face area of the person included in the image as the center, and for example, even when the person is photographed at an angle with respect to the image Regardless of the angle, an area in a range including a face area extending in a direction perpendicular to the center axis of the person's face can be set as a reduced area.

The face area extracting unit of the image processing apparatus of the present invention extracts each face area of the plurality of persons when the correction target image includes a plurality of persons, and the correction area specifying unit includes the plurality of face areas. When the reduced areas corresponding to each of these include areas overlapping each other, a plurality of reduced areas and the overlapping areas are defined as reduced areas.
In the image processing apparatus of the present invention configured as described above, when a plurality of persons are included in the image to be corrected, the respective face areas of the plurality of persons are extracted, and the reduced areas corresponding to the plurality of face areas are mutually connected. When overlapping areas are included, multiple reduced areas and overlapping areas are reduced.
Thereby, even when a plurality of persons are included in the image to be corrected and the persons are close to each other, it is possible to specify an area including any one of the persons as a reduced area.

The image processing apparatus according to the present invention also receives a reduction rate storage unit that stores a reduction rate of an image in a reduction area, and an input of the reduction rate of an image in the reduction region, and the input reduction rate is stored in the reduction rate storage unit. A correction rate input unit that stores the correction rate, and the correction execution unit reduces the image of the reduced area based on the reduction rate stored in the correction rate storage unit.
In the image processing apparatus of the present invention configured as described above, the input of the reduction ratio of the image in the reduction area is received, and the image in the reduction area is reduced based on the input reduction ratio.
Thus, the image can be corrected based on the reduction rate input from the user of the image processing apparatus according to the present invention.

Further, the correction execution unit of the image processing apparatus of the present invention generates a corrected image in accordance with an area ratio or a width ratio between the reduced area and the enlarged area.
In the image processing apparatus of the present invention configured as described above, a corrected image is generated in accordance with the area ratio or width ratio between the reduced area and the enlarged area of the image to be corrected.
As a result, it is possible to generate an optimum corrected image corresponding to the area ratio or width ratio between the reduced area and the enlarged area.

In the image processing method of the image processing apparatus according to the present invention, the face area extracting unit extracts the face area of a person included in the correction target image, and the correction area specifying unit extracts the face area from the image. A region including the face region extracted by the image processing unit is specified as a reduction region, and a region other than the reduction region is specified as an enlargement region, and a correction execution unit selects an image in the reduction region of the image based on a predetermined reduction ratio. And generating a corrected image obtained by enlarging the image in the enlarged area of the image in accordance with the ratio between the reduced area and the enlarged area.
The image processing method of the image processing apparatus of the present invention having the above-described configuration is a reduction for performing correction for extracting a human face area from the correction target image and reducing the area including the extracted face area in the correction target image. Identify the area to be corrected, specify the enlargement area to be corrected among the correction target images, reduce the image of the reduction area of the image based on the defined reduction ratio, and according to the ratio of the reduction area to the enlargement area A corrected image is generated by enlarging the image in the enlarged region of the image.
This makes it possible to specify the reduction area and the enlargement area based on the position of the person's face included in the correction target image, and the person's face can be located at any position in the correction target image. For example, even when the image is present at a position off the center, the image can be corrected according to the position of the person.

The image processing program of the image processing apparatus of the present invention includes a step in which a face area extracting unit extracts a person's face area included in an image to be corrected, and a correction area specifying unit, A step of identifying a region including the face region extracted by the face region extraction unit from the image as a reduction region and a region other than the reduction region as an enlargement region, and a correction execution unit based on a predetermined reduction ratio A step of reducing the image of the reduced region of the image and generating a corrected image in which the image of the enlarged region of the image is enlarged according to the ratio between the reduced region and the enlarged region.
The image processing program of the image processing apparatus of the present invention having the above configuration extracts a human face area from an image to be corrected, and performs a reduction for correcting the area including the extracted face area in the correction target image. Identify the area to be corrected, specify the enlargement area to be corrected among the correction target images, reduce the image of the reduction area of the image based on the defined reduction ratio, and according to the ratio of the reduction area to the enlargement area A corrected image is generated by enlarging the image in the enlarged region of the image.
This makes it possible to specify the reduction area and the enlargement area based on the position of the person's face included in the correction target image, and the person's face can be located at any position in the correction target image. For example, even when the image is present at a position off the center, the image can be corrected according to the position of the person.

1 is a block diagram illustrating a configuration of an image processing apparatus according to an embodiment of the present invention. It is a figure which shows the example of the correction target image by one Embodiment of this invention. 6 is a flowchart illustrating an operation example of the image processing apparatus according to the embodiment of the present invention. It is a figure which shows the example of the correction target image by one Embodiment of this invention. It is a figure which shows the example of the correction target image by a prior art.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram illustrating a configuration of an image processing apparatus 10 according to the present embodiment. In the present embodiment, the multi-function printer is described as being applied to the image processing apparatus 10. However, the multi-function printer may be applied to a device that prints, edits, and displays an image including a person. (Personal computer), PDA (Personal Digital Assistant), mobile phone terminal, camera, ID photo photographic apparatus installed in a station or department store, a photo studio minilab, and the like.

The image processing apparatus 10 according to the present embodiment includes an input unit 11, a face region extraction unit 12, a central axis detection unit 13, a correction region specification unit 14, a reduction rate storage unit 15, a correction execution unit 16, and an output. Part 17.
The input unit 11 receives input of an image to be corrected such as a photograph including a person and information such as a reduction rate of image correction. The input unit 11 includes, for example, a scanner that scans a printed image, reads information bit by bit, and accepts input of image information. The input unit 11 has a screen as illustrated in FIG. A photographic image in which a person is photographed at a position off the center is input as an image to be corrected. Here, it is assumed that the input photographic image is a color image. The input unit 11 only needs to accept input of image information. For example, the input unit 11 includes an image sensor such as a charge coupled device (CCD) or a complementary metal oxide semiconductor (CMOS), and accepts input of image information. But it ’s okay. In addition, the input unit 11 may accept input of image information from an external storage device via a connector such as a USB (Universal Serial Bus), or accept input of image information via a network such as the Internet. Anyway. Furthermore, the input unit 11 includes input devices such as a keyboard and buttons, and accepts input of numerical values such as an image reduction ratio at the time of image correction.

  The face area extraction unit 12 extracts a human face area from the correction target image input to the input unit 11. For example, the face area extraction unit 12 acquires color information of each pixel of the input correction target image, and extracts a skin color area from the correction target image. The face area extraction unit 12 compares the arrangement of holes and depressions in the extracted skin color area with the template information of the face including the positions of eyes, nose, mouth, etc. stored in advance in its own storage area. When the two values exceed a predetermined threshold value, the skin color area is determined as the face area. In this way, for example, the face area extraction unit 12 calculates the orientation, size, and coordinate position of the face area from the correction target image shown in FIG. A face region as shown in (b-1) is extracted.

  The central axis detection unit 13 detects the central axis of the face according to the orientation of the facial area extracted by the facial area extraction unit 12. The central axis detection unit 13 detects a central axis that passes through the center of the face from the arrangement of eyes, nose, mouth, and the like in the facial region detected by the facial region extraction unit 12. In this way, the central axis detection unit 13 detects the face as shown in (c-1) of (c) of FIG. 2 from the face region shown in (b-1) of (b) of FIG. The center axis of is detected.

  Based on the face area extracted by the face area extraction unit 12, the correction area specifying unit 14 specifies a reduction area for performing correction for reduction and an enlargement area for performing enlargement correction. At this time, as shown in FIG. 2 (d), the correction area specifying unit 14 includes a face area that extends in a direction perpendicular to the central axis (c-1) detected by the central axis detection unit 13. The region (the region inside (d-1) and (d-3)) is set as a reduced region. In addition, an area other than the reduced area (the hatched area outside (d-1) and (d-3)) in the correction target image is set as an enlarged area.

  The reduction rate storage unit 15 stores the reduction rate of the image in the reduced area. The reduction rate stored in the reduction rate storage unit 15 may be stored in advance at the time of shipment, or a value input from the input unit 11 may be stored. The reduction ratio is numerical information represented by numerical values up to the second decimal place, for example, “0.90”.

  The correction execution unit 16 reads the reduction rate stored in the reduction rate storage unit 15 and reduces the image of the reduction region of the correction target image in the direction perpendicular to the central axis of the face region based on the read reduction rate. Then, the enlargement ratio of the enlargement area of the correction target image is calculated according to the ratio between the reduction area and the enlargement area, and a corrected image is generated by enlarging the image according to the calculated enlargement ratio. For example, an area inside (d-1) and (d-4) shown in FIG. 4D is set as a reduced area, and “an area from the left end of the correction target image to (d-1) (enlarged area): The ratio of the area inside (d-1) and (d-4) (reduced area): (d-4) to the right end of the image to be corrected (enlarged area) is “1: 4: 5”. Suppose that At this time, when the reduction ratio of the reduction area is “0.90”, the reduction area inside (d−1) and (d-4) corresponds to the reduction ratio of “0.90” (d -2) and (d-3).

  Here, the correction execution unit 16 calculates the enlargement ratio of the enlargement area according to the ratio between the reduction area and the enlargement area so that the aspect ratio of the correction target image before and after correction is kept constant. For example, the ratio of the area inside (d-2) and (d-3), which is the reduced area after the reduction correction, to the entire correction target image (10) is 4 × 0.90 = 3.6. Become. Here, in order to make the aspect ratio of the image the same as that before the correction, the difference (6.4) between the entire image (10) and the ratio of the reduced area after the reduction correction to the entire image (3.6) is calculated as follows: The value divided by the ratio (6) of the enlarged area to the entire image may be used as the enlargement ratio of the enlarged area. At this time, the enlargement ratio is (10 (entire image) -3.6 (ratio of reduction area after reduction correction to the entire image)) ÷ 6≈1.06. The correction execution unit 16 enlarges the image in the enlargement area with the calculated enlargement ratio.

  The output unit 17 outputs a corrected image obtained by correcting the correction target image. For example, the output unit 17 includes a display unit such as a display, and the corrected image may be displayed on the display unit, or the corrected image may be printed on a paper medium and output. Then, the corrected image information may be output to a connected storage medium, or may be output to the outside via a network.

Next, an operation example in which the image processing apparatus 10 according to the present embodiment corrects an image to be corrected will be described. FIG. 3 is a flowchart showing an operation example of the image processing apparatus 10 according to the present embodiment. Here, it is assumed that the reduction rate storage unit 15 stores the reduction rate “0.90” input from the user via the input unit 11 in advance.
First, the input unit 11 receives an input of a correction target image (step S1). In this operation example, as shown in FIG. 2A, a photographic image in which a person is photographed at a position off the center of the screen is input as a correction target image.

Returning to FIG. 3, the face area extraction unit 12 extracts a face area from the correction target image input to the input unit 11 in step S <b> 1 (step S <b> 2). Here, as shown in FIG. 2B, the face area indicated by (b-1) is extracted from the image to be corrected.
Returning to FIG. 3, the center axis detection unit 13 detects the center axis of the face area from the face area extracted by the face area extraction unit 12 in step S <b> 2. Here, as shown in FIG. 2C, the central axis (c-1) of the face region is detected (step S3).

  Returning to FIG. 3, based on the central axis detected by the central axis detection unit 13 in step S <b> 3, the correction area specifying unit 14 specifies the correction area of the correction target image (step S <b> 4). Here, as shown in FIG. 2D, (d-1) and (d-4) are specified as the boundary of the correction region, and the inner side of (d-1) and (d-4). Is a reduced area and the outside of (d-1) and (d-4) is an enlarged area, and the correction area is specified.

  Returning to FIG. 3, the correction execution unit 16 reads the reduction rate stored in the reduction rate storage unit 15 (step S5). Further, the correction execution unit 16 calculates the enlargement ratio of the enlargement area according to the reduction ratio of the reduction area (step S6). Then, the correction execution unit 16 reduces the reduction region among the correction regions specified in step S4 based on the reduction rate read from the reduction rate storage unit 15, and specifies in step S4 based on the calculated enlargement rate. Correction processing for enlarging the image in the enlargement area is executed (step S7). Here, the image of the reduced area inside (d-1) and (d-4) shown in (d) of FIG. 2 fits inside (d-2) and (d-3). At the same time, the image of the enlarged area outside (d-1) and (d-4) is enlarged to the area outside (d-2) and (d-3). In this way, as shown in FIG. (E), even when a person is present at a position deviating from the center of the image to be corrected, image correction for reduction and enlargement is performed around the person, The image is corrected so that the captured person becomes thinner. Then, the output unit 17 outputs the corrected image (Step S8).

  Note that when the image to be corrected includes a plurality of persons, the image processing apparatus 10 may specify the reduced area and the enlarged area with each person as the center. For example, when an image including three persons is to be corrected as shown in FIG. 4A, the center detected from each person as shown in FIG. 4B. Based on the axis, a reduction area and an enlargement area are specified. In FIG. 4B, (b-1), (b-2), (b-3), and (b-4) are specified as boundaries between the reduced area and the enlarged area. The image processing apparatus 10 uses reduced areas between (b-1) and (b-2) and between (b-3) and (b-4), and the other hatched parts are The image is specified as an enlarged region and image correction processing is performed. As described above, when a plurality of persons are included in the correction target image, the face area extraction unit 12 extracts each face area of the plurality of persons, and the correction area specifying unit 14 extracts each of the plurality of face areas. When the corresponding reduced area includes an overlapping area, an area including a plurality of reduced areas and an overlapping area (between (b-3) and (b-4)) is set as the reduced area.

  Further, the image processing apparatus 10 specifies the face area of the person in the tilted state even when the person included in the image to be corrected is displayed tilted rather than in the vertical direction with respect to the image, The reduction area and the enlargement area may be specified by detecting the central axis of the face area based on the arrangement of eyes, nose, mouth and the like. For example, as shown in FIG. 4C, when a person is displayed tilted, the center axis of the person is detected as shown in (d-2), and the reduced area is based on the person's center axis. And the boundary (d-1) and (d-2) between the enlarged region are specified. Also, if the image to be corrected contains multiple people and each has a different slope, calculate the average value of the slopes and specify the reduced area based on the calculated average slope value. Alternatively, the reduced area may be specified based on an inclination having many close angles among a plurality of different angles.

  It should be noted that a program for realizing the function of the processing unit in the present invention is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read by a computer system and executed to correct an image. You may go. Here, the “computer system” includes an OS and hardware such as peripheral devices. The “computer system” includes a WWW system having a homepage providing environment (or display environment). The “computer-readable recording medium” refers to a storage device such as a flexible medium, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Further, the “computer-readable recording medium” refers to a volatile memory (RAM) in a computer system that becomes a server or a client when a program is transmitted via a network such as the Internet or a communication line such as a telephone line. In addition, those holding programs for a certain period of time are also included.

  The program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the “transmission medium” for transmitting the program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. The program may be for realizing a part of the functions described above. Furthermore, what can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

  DESCRIPTION OF SYMBOLS 10 Image processing apparatus 11 Input part 12 Face area extraction part 13 Center axis detection part 14 Correction area specification part 15 Reduction ratio memory | storage part 16 Correction execution part 17 Output part

Claims (7)

A face area extraction unit that extracts a face area of a person included in an image to be corrected;
A correction area specifying unit that specifies an area including the face area extracted by the face area extraction unit as a reduced area, and specifies an area other than the reduced area as an enlarged area of the image;
Correction for reducing the image of the reduced area of the image based on a predetermined reduction ratio, and generating a corrected image in which the image of the enlarged area of the image is enlarged according to the ratio of the reduced area and the enlarged area Execution part,
An image processing apparatus comprising: A center axis detecting unit for detecting a center axis passing through the center of the face of the face region extracted by the face region extracting unit;
The image processing apparatus according to claim 1, wherein the correction area specifying unit sets an area in a range perpendicular to the central axis detected by the central axis detecting unit as the reduced area. The face area extraction unit extracts a face area of each of the plurality of persons when the correction target image includes a plurality of persons;
The correction area specifying unit, when the reduced areas corresponding to each of the plurality of face areas include areas overlapping each other, the plurality of reduced areas and the overlapping areas are defined as the reduced areas. The image processing apparatus according to claim 1 or 2. A reduction rate storage unit that stores the reduction rate of the image in the reduced area;
A correction rate input unit that receives the input of the reduction rate of the image of the reduced region and stores the input reduction rate in the reduction rate storage unit;
The said correction execution part reduces the image of the said reduction | restoration area | region based on the said reduction rate memorize | stored in the said correction rate memory | storage part. The Claim 1 characterized by the above-mentioned. Image processing apparatus. The correction execution unit generates the correction image according to a ratio of an area ratio or a width between the reduced area and the enlarged area. 5. The image processing apparatus described. An image processing apparatus that corrects an image including a person,
A face area extracting unit extracting a face area of a person included in the correction target image;
A step of specifying a region including the face region extracted by the face region extraction unit as a reduced region, and specifying a region other than the reduced region as an enlarged region in the image;
A correction execution unit reduces the image of the reduced area of the image based on a predetermined reduction ratio, and expands the image of the enlarged area of the image according to the ratio of the reduced area and the enlarged area Generating an image; and
An image processing method comprising: In the computer of the image processing apparatus that corrects an image including a person,
A face area extracting unit extracting a face area of a person included in the correction target image;
A step of specifying a region including the face region extracted by the face region extraction unit as a reduced region, and specifying a region other than the reduced region as an enlarged region in the image;
A correction execution unit reduces the image of the reduced area of the image based on a predetermined reduction ratio, and expands the image of the enlarged area of the image according to the ratio of the reduced area and the enlarged area Generating an image; and
An image processing program for executing

Images