JP2003319169A - Image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing method for automatically correcting the tilt of a face area corresponding to the face of a person in an original image. <P>SOLUTION: The image processing method of this invention includes the steps of detecting positions corresponding to both eyes of the person in the original image on the basis of image data of the original image including the face area corresponding to the face of the person, correcting the original image so that the detected positions corresponding to both the eyes of the person in the original image are placed on a line in parallel with a preset reference line to the original image or a straight line orthogonal to the reference line, and generating corrected image data. <P>COPYRIGHT: (C)2004,JPO

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing method, and more particularly, it automatically corrects image data so as to correct the inclination of a face area corresponding to the face of a person in photographed image data. The present invention relates to an image processing method.

[0002]

2. Description of the Related Art At present, a photograph of a predetermined size (certificate photo) showing the face of the person himself / herself, such as application for issuance of a passport or license, or creation of a resume.
There are many opportunities to attach or submit. For this reason,
A photography room is set up for taking pictures of users, and a user sitting on a chair in the photography room is photographed, and a certification photo sheet is created in which multiple images for the certification photograph of the user are recorded on a single sheet. 2. Description of the Related Art A device for automatically creating an ID photo that automatically does this has been used.

Further, in recent years, image data obtained by reading a film image recorded on a photographic film and image data input from a digital camera are subjected to various kinds of image processing and then printed. Images can be recorded on recording materials such as paper, and other output formats (for example,
An image processing system capable of outputting an image by storing image data in an information recording medium such as a smart medium has become popular. Along with that, at DPE stores (laboratory) and photo studios, a customer is photographed with a silver salt camera to create an ID photo, or an ID photo is taken from a photographic film taken by the customer to create an ID photo. In addition to the conventional service to create, create an ID photo by shooting with a digital camera, or create an ID photo from the image data of the ID photo creation image recorded on the information recording medium brought in by the customer Services are also being provided.

By the way, in a photograph used as a certification photograph, it is necessary that the face of the person to be certified is arranged in a predetermined size and at a proper position. Therefore, when the user (customer) unintentionally tilts his / her neck or upper body or the camera is tilted at the time of taking the ID photo, the face area in the taken image is tilted. In this case, after the image is output, the face area in the image is cut so as to correct the inclination, or the image processing apparatus processes the image data before outputting the image to correct the inclination of the face area.

As an image processing apparatus for correcting the inclination of image data, Japanese Patent Application Laid-Open No. 11-341272 discloses an image (an image showing a person's face) used for creating an identification photograph by enlarging or reducing it at a predetermined position. There is proposed an image processing apparatus which is arranged at a position and is printed out, and when an operator instructs a rotation angle of image data, a computer rotates the image data by the instructed rotation angle. Further, the processing of rotating the image data by the angle designated by the operator is also performed by using the existing image processing software or the like.

[0006]

It is desirable to take a photograph in which the face area is not tilted in such an image for identification photograph, if image processing is not performed. It is difficult for both the user (customer) and the photographer that the photographer corrects the inclination of the user's (customer) neck or upper half of the body at the time of photographing, which is a heavy burden. on the other hand,
When cutting to correct the inclination of the subject's face after outputting the image, the work load on the user and operator is heavy, and in addition to the amount of cropping, a large size is added to the required image size. Since it is necessary to output the data, there is a problem that the time required for the output is long and the waste of the output paper is large.

On the other hand, when performing image processing, in the technique described in Japanese Patent Laid-Open No. 11-341272, the existing image processing software, etc., the operator can confirm the original image displayed on the display device. , The rotation angle of the original image data is instructed, and the rotated image data is confirmed on the display device.However, when determining the rotation angle to be instructed, many operations rely on the sense of the operator or user. In addition to the heavy burden, especially for users who are not accustomed to the work, it is often necessary to repeat the work multiple times until the inclination is corrected,
There was a problem that the processing load was very heavy and the processing time was long.

An object of the present invention is to solve the above-mentioned problems of the prior art and to provide an image processing method for automatically correcting the inclination of the face area corresponding to the face of a person in the original image.

[0009]

The inventor of the present invention has found that a person who views an identification photograph first pays attention to both eyes of a person in the image, whereby the person in the image makes a straight line with respect to the cut edge of the identification photograph. Knowing that there is a strong tendency to judge whether or not they are arranged, as an image processing method that automatically corrects the inclination of the face area corresponding to the face of the person in the original image, It was found that the method of creating the corrected image data is effective so that the position corresponding to is located on the same straight line that is parallel or perpendicular to the frame of the image corresponding to the cut side of the ID photo.

Based on the above, the present invention detects the positions corresponding to both eyes of the person in the original image based on the image data of the original image including the face area corresponding to the face of the person,
The positions corresponding to both eyes of the person in the detected original image are positioned on the same straight line parallel to the reference line preset for the original image or a straight line orthogonal to the reference line. Further, there is provided an image processing method for modifying the original image to create modified image data.

Here, when the original image is a rectangle, the reference line is preferably a straight line parallel to one side of the rectangle.

Further, the corrected image data is obtained by rotating the original image around one point substantially in the center of the original image or one point substantially in the center corresponding to both eyes of a person in the original image. Thus, it is preferably created by modifying the image data of the original image.

A position corresponding to the crown of the person in the corrected original image is detected based on the corrected image data, and a position corresponding to the crown of the person in the detected original image and It is preferable that a trimming area for the corrected original image is set so that the face area is located at a predetermined position in the trimming area with a predetermined size based on the positions corresponding to both eyes.

According to one aspect of the present invention, the position corresponding to the eye part and the position corresponding to the crown of the person in the original image are detected based on the image data of the original image including the face area. To detect the position corresponding to the eye part of the person in the original image, as described in, for example, Japanese Patent Laid-Open No. 2000-242768, filtering processing is performed by a filter that detects a light-dark pattern corresponding to the eye part. , Setting a predetermined region including a region corresponding to one eye, set a specific region including a black eye portion in the central portion of the set predetermined region, the region excluding the specific region of the predetermined region,
A search area in which it is presumed that an area corresponding to the other eye is present by creating a template by inverting the axis parallel to the vertical direction of the subject in the original image as the axis of symmetry and combining it with the specific area. A preferable example is an algorithm for setting a predetermined area including the area corresponding to the other eye by obtaining the cross-correlation coefficient while operating the template in the inside. However, the present invention is not limited to this, and it goes without saying that another algorithm may be used.

In order to detect the position corresponding to the top of a person's head in the original image or the corrected image of the original image, for example, the position along the lateral direction orthogonal to the preset reference line in the substantially vertical direction of the subject is detected. At a plurality of locations on the original image, the density change amount is repeatedly calculated while scanning the original image from the upper side to the lower side in the vertical direction, and the position where the density change amount first becomes equal to or more than a predetermined value is set as a candidate. A preferable example is an algorithm for storing and detecting the uppermost candidate among the portions where the positions of the candidates are concentrated along the vertical direction as the position corresponding to the crown. However, this is not limited to this method, and another algorithm may be used.

Further, the trimming area is set based on the image data of the original image including the face area corresponding to the face of the person so that the face area is located at a predetermined position with a predetermined size ratio. An algorithm for setting the trimming area for is preferably exemplified. However, other algorithms may be used.

In the trimming area setting algorithm described above, the setting of the trimming area in the vertical direction of the subject in the original image or the corrected image of the original image is performed by, for example, setting the face in the vertical direction in the trimming area. An appropriate value of the size ratio along the top-bottom direction of each of the above-head region, the face region, and the submandibular region present below the face region along the top-bottom direction in the trimming region above the region. The position corresponding to the tip of the person's chin is estimated based on the position corresponding to the top of the person's head and the position corresponding to the eye in the detected original image. Based on the distance on the original image or the corrected image of the position corresponding to the top and the position corresponding to the tip of the jaw,
Among the trimming area, the size ratio along the top-bottom direction, the face area, and the submandibular area along the top-bottom direction matches the top-bottom direction so that the size ratio matches the appropriate value of the size ratio stored in the storage unit or the like. This can be achieved by setting the position and size of the trimming area along the line.

The setting of the trimming area in the horizontal direction orthogonal to the vertical direction of the subject in the original image or the corrected image of the original image is performed, for example, in the horizontal direction at the position corresponding to the detected binocular portion. The center position of the trimming area along the lateral direction is set to a position corresponding to a substantially center along the horizontal direction, and the aspect ratio of the trimming area is stored in the storage unit or the like based on the size of the trimming area along the vertical direction. The information indicating the aspect ratio (for example, the information indicating the aspect ratio itself, or the information indicating the vertical and horizontal sizes of the recorded image when the image area corresponding to the trimming area is recorded on the recording material) This can be achieved by setting the position and size of the trimming area along the horizontal direction so as to coincide with (good).

[0019]

DETAILED DESCRIPTION OF THE INVENTION An image processing method according to the present invention will be described below in detail with reference to the preferred embodiments shown in the accompanying drawings. FIG. 1 shows a schematic configuration of an embodiment of an image creating system that performs image processing by the image processing method according to the present invention.

The image creating system 1 shown in FIG. 1 includes a photographing means 2, an image data input means 3, an image display means 4, and
Image processing means 5, key input means 6, and image output means 7
With. Here, the photographing means 2 is one of means for acquiring image data of an original image (hereinafter, simply referred to as original image data), and photographs the subject including a face area corresponding to a person's face to obtain the original image data. Anything can be used as long as it can be acquired, and examples thereof include a digital still camera. The image data input unit 3 is one of the original image data acquisition units, and may be any unit as long as it can acquire the original image data in which a subject including a face region corresponding to a person's face is photographed. , Various media for reading original image data from an information recording medium (media) such as a film scanner (transparent original reading device) for reading an image of a photographic film, a magnetic disk on which original image data is recorded, an optical disk, a magneto-optical disk, etc. Examples thereof include a reader (media driver) and an image data receiving device that receives original image data via a communication network such as the Internet.

The image display means 4 displays the original image data obtained by the photographing means 2 and the image data input means 3, or the image data for identification photograph corrected and processed from the original image data by the image processing means 5. For displaying the corrected image data and the processed image data and related additional information such as CRT display device, liquid crystal display (LCD), plasma display and other monitors and displays. Based on the original image data acquired by the image capturing unit 2 and the image data inputting unit 3, the image processing unit 5 sets a position corresponding to both eyes of a person to a reference line which is preset for the original image or Correct the image data so that it is located on the same straight line parallel to the straight line orthogonal to this reference line, and set the trimming area for the original image so that the face area of the person is located at a predetermined position with a predetermined size ratio. , Which creates processed image data such as ID photo image data, and may be, for example, a dedicated image processing apparatus having these functions, but will be described in detail later in a personal computer (hereinafter referred to as a PC). It may be configured by installing image data creation software for ID photo.

The key input means 6 outputs a predetermined size ratio of the processed image data and the identification photograph output by the image output means 7 in order to create modified image data such as image data for identification photograph and processed image data. It is for inputting a predetermined size of an image and for instructing image correction processing and image processing processing. In addition to this, it is for inputting information and data necessary for the operation of the image creating system 1 described above. Also, for example, a PC as the image processing means 5
It can be configured with a keyboard or a mouse connected to the. The image display unit 4, the image processing unit 5, and the key input unit 6 may be those integrally configured as a so-called PC. The image output means 7
An image of a predetermined size such as an ID photo is output using processed image data such as image data for ID photo processed by the image processing unit 5. For example, an image of a predetermined size such as an ID photo is a visible image. A laser printer that outputs a hard copy image, including a photo printer that outputs recorded recording materials (photo prints), and image data for outputting an image of a predetermined size such as a certification photo as a hard copy image on a CD. A media driver (writing device) for recording on an information recording medium (media) such as -R can be given.

In the image creating system 1 shown in FIG.
When an image is acquired using the image capturing means 2, when an operator (photographer) shoots a customer using the image capturing means 2, the captured image captured by the image capturing means 2 is immediately sent to the image processing means 5. Alternatively, the image processing means 5 immediately reads the photographed image from the photographing means 2, and the image display means 4
To display. On the other hand, in the case of acquiring an image using the image data input means 3, the operator uses a photographic film on which an original image such as an ID photo image brought in by a customer is recorded or an information recording medium on which the original image data is recorded. When the original image (original image data) is read by the image data input means 3 such as a film scanner or a media reader, the read original image is immediately sent to the image processing means 5,
Alternatively, the image processing unit 5 reads the original image immediately read from the image data input unit 3 and displays it on the image display unit 4. In addition, the operator inputs from the key input means 6 a size ratio of images such as ID photos and instructions to execute various processes for creating an appropriate image, and the size of images such as ID photos output from the image output means 7. If the information such as the type, the type, and the required number of sheets is input, the image processing unit 5
Then, based on the inputted instruction, size ratio, size, and other information, the photographed image and the original image are subjected to image correction and processing such as ID photo processing, and the ID photo output unit 7 is provided with the ID photo in accordance with instructions from the operator or user. A processed image such as an image is output.

Next, an image processing system in which the image creating system for performing image processing by the image processing method according to the present embodiment is further embodied will be described in more detail with reference to FIG. FIG. 2 shows a schematic configuration of an image processing system 10 that is a more specific version of the image creating system according to the present embodiment. An image processing system 10 shown in the figure includes a digital still camera (DSC; hereinafter referred to as a digital camera) 13 as an image capturing unit 2 that is an acquiring unit that acquires image data, and an image data input unit 3 that is also an acquiring unit. A film scanner 14, a media driver 15, and an image data receiving device 16 are each provided. In the following, the digital camera 13, the film scanner 14,
The media driver 15 and the image data receiving device 16 are collectively referred to as the image data input device 12. In the image processing system 10, the image processing unit 5 is provided with the image processing device 18 for processing the image data input from the image data input device 12, and the key input unit 6 is provided with the key input unit 64. There is. The image processing device 18
For example, it can be configured by a PC. Further, the image processing system 10 is an output device for outputting image data (or an image) processed by the image processing device 18, a display 20 for displaying the image, a laser printer 22 for exposing and recording the image on a photographic paper, Each of the CD-R writing devices 24 writes image data on the CD-R. Here, the display 20 corresponds to the image display means 4, and includes the laser printer 22 and the CD-R writing device 2.
Reference numeral 4 corresponds to the image output means 7.

The digital camera 13 captures the original image data including the face area corresponding to the person's face by taking the face of the person of the customer who requests the image creation such as the ID photo as a subject. . The digital camera 13 is not particularly limited as long as it can acquire original image data capable of creating an image such as an identification photograph, but considering the required quality of an output image such as an identification photograph, about 1 million pixels. It is preferable that the number of pixels as described above or a photographing resolution of about 1000 × 1000 is provided.

In the present embodiment, the digital camera 13
Are directly connected to the image processing device 18. Therefore,
A captured image (image data) of a subject including a person's face captured by the digital camera 13 is immediately captured by the image processing device 18.
And is displayed on the display 20 as a monitor.
That is, the image processing device 18 is an operator (photographer).
At the timing when the shutter of the digital camera 13 is pressed, the captured image is read from the digital camera 13 and is displayed on the display 20 as a monitor. Here, it is preferable that the digital camera 13 has a buffer capable of temporarily storing a plurality of captured images. As a result, display 2
It is possible to continuously display captured images to 0 and continuously shoot with the digital camera 13. Also, in the display 20,
It is preferable to sequentially display the images taken by the digital camera 13 in the order of shooting. As a result, the display 20
You can check the shooting history at a glance. Display 2
The photographed image displayed at 0 is displayed with a higher resolution and higher resolution than the photographed image displayed on the monitor of the digital camera 13. Therefore, the photographer or the customer, who is the subject, can confirm that the photographed image is an identification photograph or the like. You can easily and accurately check whether it is suitable as an image, and if it is not suitable,
Can be retaken immediately.

The media driver 15 is, for example, a magnetic disk such as a flexible disk (FD), an optical disk such as a CD-R, a magneto-optical disk (MO), a PC card that can be loaded into a digital still camera (DSC), smart media, or an IC. Any one of various information storage media such as cards is set, and the image data stored in the set information storage media is read and output to the image processing device 18.
The image data receiving device 16 is connected to a computer network such as the Internet, and receives R, G, B image data from an information processing device (for example, a personal computer (PC)) via the computer network, and receives the image data. The generated image data is output to the image processing device 18.

The film scanner 14 uses the photographic film 3
8 (for example, a negative image or a positive image visualized by developing processing after photographing a subject, which is recorded on a photographic light-sensitive material (hereinafter simply referred to as photographic film) such as a negative film or a reversal film) Is read and the image data obtained by the reading is output to the image processing device 18. The light emitted from the LED light source 30 and having the light amount unevenness reduced by the light diffusion box 34 is set on the film carrier 36. The light that has been irradiated onto the photographic film 38 and that has passed through the photographic film 38 is configured to form an image on the light receiving surface of the area CCD sensor 42 (may be a line CCD sensor) via the lens 40.

The film carrier 36 intermittently conveys the photographic film 38 so that the film image is sequentially positioned on the optical axis (reading position) of the light emitted from the LED light source 30. The LED light source 30 includes a large number of LEDs that emit R light,
A large number of LEDs that emit G light and a large number of LEDs that emit B light are arranged on the entire surface of a substrate (not shown) at a constant and high density, and a single image is located at the reading position. It is driven by the driver 32 so as to sequentially emit the R, G, and B lights in the state. As a result, the film image recorded on the photographic film 38 is transferred to the CCD sensor 4
Then, the CCD sensor 42 outputs R, G, and B signals corresponding to the film image.
The signal output from the CCD sensor 42 is the A / D converter 4
It is converted into digital image data by 4 and input to the image processing device 18.

The image processing device 18 includes an image data preprocessing unit 50, a first memory 52, a second memory 54, a first image processing unit 56, an image processing control unit 58, a second image processing unit 60, and a color reproduction conversion. The image processing control unit 5 includes a unit 62.
A key input unit 64 is connected to the switch 8. A first memory 52 and a second memory 54 are connected to the image data preprocessing unit 50, a first image processing unit 56 and an image processing control unit 58 are connected to the first memory 52, and a second memory 54 is connected to the second memory 54. Is connected to the second image processing unit 60. The digital camera 13, the film scanner 14, the media driver 15, and the image data receiving device 16 described above are connected to the image data preprocessing unit 50 of the image processing device 18, as shown in FIG. The image data output from the image data input device 12 is the image data preprocessing unit 5
Input to 0.

The image data preprocessing unit 50 performs different predetermined preprocessing on the input image data depending on the image data input source. As preprocessing for the image data input from the digital camera 13, for example, when the image data is compressed image data similar to that recorded in an information storage medium, decompression, image processing such as sharpness improvement, and the like are performed. In the case of the image data before the image processing in the digital camera 13, dark correction, density conversion, defective pixel correction, etc. may be mentioned.
Further, examples of the preprocessing for the image data input from the film scanner 14 include dark correction, density conversion, shading correction, defective pixel correction, and the like. Further, as the preprocessing for the image data input from the media driver 15, for example, decompression of the image data compressed and recorded in the information storage medium and image processing such as sharpness improvement can be mentioned. In addition, the image data receiving device 16
Examples of the preprocessing for the image data input from the device include decompression of compressed image data (for example, JPEG format image data) received by the image data receiving device 16.

By the way, the film scanner 14 according to the present embodiment reads each film image recorded on the photographic film twice at different resolutions. In the first reading with relatively low resolution (hereinafter referred to as prescan), even when the density of the film image is very low (for example, the negative image of the exposure underneath on the negative film), the CCD sensor 42 saturates the accumulated charge. Reading is performed under the reading conditions determined so as not to cause such inconvenience. The image data preprocessing unit 50 performs predetermined preprocessing on the low resolution image data input from the film scanner 14 by performing the prescan, and then outputs the image data to the first memory 52.

The image data preprocessing section 50 outputs the image data input from each of the digital camera 13, the media driver 15 and the image data receiving device 16 to the first memory 52 and the second memory 54, respectively. However, among these, the image data to be output to the first memory 52 is converted to low-resolution image data equivalent to the low-resolution image data obtained by the prescan, and then output to the first memory 52. The low resolution image data output to the first memory 52 is further input to the image processing control unit 58.

The image processing control unit 58 and the first image processing unit 56 have a CPU, a ROM, a RAM, and an input / output port connected to each other via a bus, and the input / output port stores a hard disk device (HDD) or the like. The image processing PC can be realized by a single image processing PC having a configuration in which the device is connected. By causing the image processing PC to execute a predetermined program, the image processing PC can be operated by the first image processing unit 56.
And the image processing control unit 58 can function.

When the low resolution image data input via the first memory 52 is the image data obtained by pre-scanning with the film scanner 14, the image processing control unit 58 is based on the low resolution image data. Then, image characteristics such as density are calculated to determine the reading conditions for the film scanner 14 to read again at a relatively high resolution (hereinafter referred to as fine scan) for the prescanned photographic film. The determined reading conditions are output to the film scanner 14. The film scanner 14 receives this reading condition and executes a fine scan.

Further, the image processing control unit 58, based on the input low resolution image data, the image data preprocessing unit 5
0 to high resolution image data of the same image output to the second image processing unit 60 via the second memory 54 (image data input from the film scanner 14 by performing a fine scan, or the digital camera 13, media Image data input from either the driver 15 or the image data receiving device 16), the second image processing unit 60
The processing conditions of the various image processing performed by are automatically determined by calculation (setup calculation), and the determined processing conditions are notified to the first image processing unit 56.

The image processing executed by the second image processing unit 60 is, for example, gray balance adjustment of the image, density adjustment, gradation control, hypertone processing for compressing the gradation of the ultra low frequency luminance component of the image. Image processing for improving the image quality of an output image, such as hyper-sharpness processing that emphasizes sharpness while suppressing graininess, can be cited.
In addition, image processing that intentionally changes the image tone (for example, image processing that finishes the output image in portrait style) and image processing that processes the image (for example, make a person present in the original image slender on the main image). Image processing such as image processing for finishing) may be executable.

The first image processing unit 56 includes the image processing control unit 5
Based on the processing condition notified from 8, image processing equivalent to the image processing performed by the second image processing unit 60 for the high resolution image data is performed on the low resolution image data stored in the first memory 52. Then, the simulation image data is generated. The color reproduction conversion unit 62 and the display 20 are sequentially connected to the first image processing unit 56.
Further, the display 20 includes a buffer for holding the input image data, has a function of generating an analog electric signal based on the image data held in the buffer, and displaying the image represented by the image data on the display 20. is doing. The simulation image data generated by the first image processing unit 56 is output to the color reproduction conversion unit 62, is subjected to color reproduction conversion processing such as density conversion by the color reproduction conversion unit 62, and is then output to the display 20. It is displayed on the display 20 as (output image). The output image displayed on the display 20 is used by the operator for verification of image finish and the like.

A key input section 64 is connected to the image processing control section 58. The key input unit 64 corresponds to the key input unit 6 shown in FIG. 1, and can be configured by, for example, a keyboard or a mouse (these are connected to the input / output port of the image processing PC described above). Display 20
The operator who has verified the output image displayed on the screen operates the key input unit 64 to input the test result. Then, the image processing control unit 58 notifies the second image processing unit 60 of the confirmed processing conditions when the processing conditions are confirmed after the verification by the operator.

The second image processing section 60 is provided with a plurality of types of image processing circuits for performing the various types of image processing described above.
When the high resolution image data is input from the image data preprocessing unit 50 via the second memory 54, various image processing is performed on the input high resolution image data according to the processing conditions notified from the image processing control unit 58. I do. The second image processing unit 60 is connected to the color reproduction conversion unit 62, and the image data output from the second image processing unit 60 undergoes color reproduction conversion processing in the color reproduction conversion unit 62, and then the laser printer 2
2 or output to the CD-R writing device 24 and used for recording an image on photographic paper by the laser printer 22, or
Alternatively, it is written on the CD-R by the CD-R writing device 24. In this way, the processed image such as the identification photograph can be output as a print or as an image file (to the information recording medium) of the image data of the processed image.
As a result, the photographed image (including the original image of the photographic film or the information recording medium) can be diverted to other uses or products, and reordering (reorder) can be easily performed.

The laser printer 22 has R, G, B
The laser light source of R, G, and B emitted from the laser light source is modulated based on the image data input from the image processing device 18, and is deflected by a deflecting unit such as a polygon mirror. The image is exposed and recorded on the photographic paper by scanning the photographic paper. The photographic printing paper on which the image is exposed and recorded is sent to a paper processor and subjected to color development, bleach-fixing, washing with water and drying.
As a result, the image exposed and recorded on the printing paper is visualized. The laser printer 22 is used in the image processing device 18.
However, it is not limited to the one directly connected, and may be one connected via a communication network such as a LAN.

Next, as an operation of the present embodiment, creation of a certification photograph will be described. The ID photo is created, for example, by the customer taking a picture for the ID photo at a DPE store (laboratory) or a photo studio equipped with a digital ID photo creation system to which the image forming system of the present invention is applied.
Alternatively, for example, an information recording medium such as a photographic film on which an image for ID photo creation is recorded, or a smart medium on which image data of an image for ID photo creation is recorded is brought by a customer to a DPE store or a photo studio, This is done by the customer requesting the creation of an ID photo. At the time of requesting the creation of the ID photo, conditions such as the type of ID photo to be created and the number of sheets for each type (color / monochrome) are specified. The request for creating the ID photo may be accepted online including the reception of the image data of the image for which the ID photo is to be created.

When the photographer and the operator are requested to take and create the ID photograph, first, the photographer or the operator photographs the customer with the digital camera 13 at a predetermined position. The image data of the photographed image photographed by the digital camera 13 is sent to the image processing device 18 immediately after photographing, and is temporarily stored in the first memory 52.
And stored in the second memory 54, read from the first memory 52, and displayed on the display 20 via the first image processing unit 56 and the color reproduction conversion unit 62. The photographed image including the face of the customer displayed on the display 20 by the photographer, the operator or the customer is observed,
When it is confirmed that the original image is suitable as the original image for the ID photo, the operator instructs the creation of the ID photo with the high-resolution image data of the original image to be the ID photo stored in the second memory 54. Here, if it is confirmed that the captured image is inappropriate, such as when the customer was photographed with his eyes closed, or when the customer's facial expression was disliked, it is not possible to retake the image. Needless to say. However, in the image processing system using the image processing method of the present invention, it is possible to automatically correct the tilt and size of the subject, and therefore it is not necessary to re-shoot to adjust the tilt and size.

On the other hand, when a request for the production of the ID photo is made by the customer's photographic film or information recording medium, or by the online reception containing the image data of the image for which the ID photo is to be created, it is recorded on the photographic film 38 brought in. Film scanner 1
4, the fine scan is performed, the image data of the image for the ID photo creation is read from the information recording medium by the media driver 15, or the image data of the image for the ID photo received by the image data receiving device 16 is changed. By being read, the high-resolution image data of the image of the ID photograph is stored in the second memory 54, and at the same time, the prescan image by the film scanner 14, the media driver 15, and the image data receiving device 16 are also read. The operator gives an instruction to create an identification photograph in a state where the input image data having the reduced resolution is stored in the first memory 52. An image taken by the digital camera 13 and the film scanner 14
The film scan image by the device, the image read out from the information recording medium by the media driver 15, and the online received image by the image data receiving device 16 are stored in an HDD (not shown) or a database connected to the image processing device,
It is preferable to make a backup, and it is more preferable to make an automatic backup with a number limit setting.

The ID photograph creating process executed by the image processing control unit 58 and the first image processing unit 56 of the image processing apparatus 18 according to the instruction from the operator will be described below with reference to the flowchart of FIG. It should be noted that this ID photograph creation processing is processing to which the image processing method according to the present invention is applied, and more specifically, the image processing control unit 58 and the first
It is realized by the CPU of the image processing PC constituting the image processing unit 56 executing the identification photograph creating program. Initially, the ID photo creation program is the information storage medium 6
8 (see FIG. 2). Although the information storage medium 68 is shown as a flexible disk in FIG.
It may be configured by a D-ROM, a memory card, or the like.

When the information storage medium 68 is loaded into the information reading device (not shown) incorporated in the image processing PC, and the transfer (installation) of the program from the information storage medium 68 to the image processing device 18 is instructed. The identification photo creating program is read from the information storage medium 68 by the information reading device and stored in the HDD of the image processing PC. Then, when the timing to execute the ID photo creating process comes, the ID photo creating program is read from the HDD and executed by the CPU.

In the ID photo creation process, first, step 10
In step 0, the low-resolution image data of the image designated as the ID photo creation target is loaded from the first memory 52 into the image processing controller 58, and in the next step 102, the image data loaded in step 100 is used as an example. As shown in FIG. 6, the display 20 displays a creation condition specification screen for specifying the creation condition of the ID photo. In step 100, the high-resolution image data of the image designated as the ID photo creation target is stored in the second memory 5
It is also possible to load the image data from No. 4 into the second image processing unit 60, reduce the resolution in the second image processing unit 60, and then import the image data into the image processing control unit 58 to perform the processing of step 102 and subsequent steps.

The creation condition designation screen shown in FIG. 6 has a display area 70A for displaying an image for which an ID photo is to be created, and an instruction button 70 for instructing automatic inclination correction of the displayed image.
B, an instruction button group 70C for instructing rotation of the image,
Selection field 70D for selecting whether to automatically or manually set the trimming area, selection field 70E for selecting the type (size) of the ID photo to be created, and each type (color / monochrome) of the ID photo Input field 70F for inputting the number of created images, an instruction button group 70G for instructing the scaling of the image displayed in the display area 70A, and an instruction button group 70 for instructing the movement of the position of the trimming area.
H and an enter button 70J for confirming the conditions for creating the ID photo are provided respectively. Further, a selection field and an input field for adjusting the image quality of the ID photo are also provided.

When the image for ID photo creation is displayed in the display area 70A, the reference line L in the displayed image for ID photo creation is set. In this embodiment, one of the horizontal frame lines of the display area 70A (for example, the display area 7
The straight line in the image corresponding to the bottom of 0A) is set as the reference line L in the image being displayed. Here, when the image data is rectangular, one side of the image data (for example,
The horizontal direction of the subject is displayed so as to be parallel to one of the horizontal frame lines (for example, the bottom side) of the display area 70A, and the reference line L of the image being displayed is parallel to one side of the image data. . The edge (trimming frame) K of the trimming area described later is displayed at a position where one side (for example, the bottom side P) is parallel to one of the frame lines (for example, the bottom side) of the display area 70A. Therefore, the reference line L is also parallel to the bottom side P of the edge (trimming frame) K of the trimming area.

In this embodiment, it is possible to create a plurality of types of ID photos having different sizes, and the HDD
As shown in Table 1 below, "type (name)", "print size", "overhead / face / submandibular ratio (details described later)" are set for each type of ID photo that can be created. ID photo information is stored (see FIG. 10).

[0051]

[Table 1]

In the state where the creation condition designation screen is displayed on the display 20, the operator performs an operation such as clicking the button marked "∇" on the right side of the selection field 70E for the ID photo information. The selection field 70E indicates the type (name) of the ID photo that can be created
Is listed as an option. On the other hand, a rectangular figure (hereinafter referred to as a trimming frame K) that represents the outer edge of the trimming area having a size corresponding to the type of ID photo selected in 70E.
: Refer to FIG. 6) is displayed in the approximate center of the display area 70A so as to be superimposed on the image of the ID photo creation target displayed in the display area 70A. Trimming frame K displayed here
The size of is determined according to the display magnification of the image data set as the initial value and the conversion magnification of the image data at the time of printing, and is a size according to the actual print size.
It is set regardless of the position and size of the subject in the display image.

In the next step 104, it is determined whether or not the operator has input any information via the key input unit 64 (keyboard, mouse, etc.), and the process waits until the determination is affirmed. If any information is entered, step 104
Is affirmative, the process proceeds to step 106, the content of the input information is determined, and the process branches depending on the determination result.

When the information indicating that the operator has selected the "automatic tilt correction" of the instruction button 70B or the "automatic trimming" of the selection field 70D is input, step 1
If the “automatic tilt correction” is selected, the process proceeds to step 10, and the step 110 is affirmed and the process proceeds to the step 112. Otherwise, the step 110 is denied and the process proceeds to the step 116. If the information indicating that the operator has selected the decision button 70J is input, step 11
8 (details will be described later). When information indicating that there is an operation other than these is input, the process proceeds from step 106 to step 108, and processing is performed according to the input information (for example, the type of ID photo to be created is selected. If so, the type of the selected ID photo is stored, and if the number of created ID photos for each type is input, the number of created ID photos is stored for each type), and then the process returns to step 104.

When the operator selects the "automatic tilt correction" of the instruction button 70B, step 11
In step 2, the inclination correction is automatically processed. Hereinafter, this processing will be described with reference to the flowchart of FIG. In step 150, the positions corresponding to both eyes of the person in the image are detected based on the image data of the image for which the identification photograph is to be created, which is taken into the image processing controller 58 in step 100. In the following description, the direction of the reference line L of the image data will be referred to as the X direction, and the direction orthogonal to the reference line L (corresponding to the substantially vertical direction of the subject) will be referred to as the Y direction.

When detecting the positions corresponding to the both eyes,
First, an axis M passing through the approximate center of the face area of the person in the original image is set. In the case of an ID photograph, since the face area is normally located at the center of the image, an axis M parallel to the Y direction and passing through the approximate center of the original image data with respect to the X direction as shown by a broken line in FIG. 7B. For example, a bright and dark pattern as shown in FIG. 7E or 7F is set on one side (here, the left side in FIGS. 7A to 7D) with the axis M as a boundary. By performing the filtering process using the filter to be detected, the first predetermined region A1 including the eye region corresponding to the left eye is set (see FIG. 7B).

Next, as shown in FIG. 7 (G), a specific area N1 estimated to include an area corresponding to a black eye is set in the central portion of the first predetermined area A1, and the areas other than the specific area N1 are set. By inverting the left and right of the area N2 (reversing with the axis parallel to the Y direction as the axis of line symmetry) and synthesizing with the specific area N1, FIG.
A template T as shown in (H) is created. Subsequently, a search area E having a sufficiently larger area than the template T is set on the other side (the right side in FIGS. 7A to 7D) with the axis M as a boundary (see FIG. 7C), and the search area is set. E
The cross-correlation coefficient is repeatedly calculated while scanning the template T in the area, and the area having the maximum correlation coefficient is set as the second predetermined area A2.

Then, the central coordinate value (X
1, Y1) is the position of the left eye, and the center coordinate value (X2, Y2) of the predetermined area A2 is the position of the right eye. Thereby, the positions of both eyes in the image can be detected accurately in a short time.

The detection of the positions corresponding to both eyes of the person in the image for which the ID photograph is to be created is not limited to the above algorithm. For example, the axis M has a predetermined area A1,
Since it is for narrowing down the processing target range when setting A2, a point (head vertex) corresponding to the top of the head of the person in the image is detected by a method described later and the axis passing through the head vertex is used as the axis M. Alternatively, the first predetermined area A1 may be set by a filtering process in which the entire surface of the ID photograph creation target image is set as the processing target range without using the axis M, the template T is created, and the first predetermined area A1 is created. By scanning the template T within the search area set in the vicinity, the second
The predetermined area A2 may be set.

In the next step 152, step 150
An acute angle R formed by a straight line S1 connecting both eyes and a straight line S2 parallel to the reference line L based on the positions of the both eyes detected in
Is calculated (see FIG. 8A). This angle R represents the inclination angle of the face area of the person in the image. In step 154,
Coordinates of both eyes calculated in step 150 (X1, Y1)
From (X2, Y2), the average X coordinate value and Y
The average value of the coordinate values is calculated, and the coordinates of the position corresponding to the center of both eyes are obtained. Then, in step 156, with the position corresponding to the center of both eyes calculated in step 154 as the center of rotation, in the direction in which the tilt angle R of the face area calculated in step 152 decreases, the entire image data is converted by the angle R. Rotate (see FIG. 8 (B)). That is,
So that the straight line S1 connecting both eyes is parallel to the reference line L,
In other words, the inclination is corrected by rotating the image so as to be parallel to the bottom side P of the trimming frame K.

In the setting of the reference line L, when the vertical frame line of the display area 70A is used as the reference line, the straight line connecting both eyes becomes parallel to the straight line orthogonal to this reference line. A program for rotating an image may be used.

When the rotation processing of the image data of the image for which the ID photograph is to be created is performed as described above, the next step 15
8, the image after the inclination correction processing (FIG. 8B) is displayed in the display area 70A of the creation condition designation screen, and the process proceeds to step 114 in FIG.

In the above inclination correction processing, it is preferable that the center of rotation of the image data is a point where the rotation processing does not significantly change the position of the image in the display area or largely prevent the image data from moving outside the display area. It is preferable to set one point at the approximate center of the image. Further, in the ID photograph, the face area, particularly the positions of both eyes are important, and the positional change amount of both eyes when rotated at a position corresponding to the center of both eyes is relatively small, further, Since the coordinates of the position corresponding to the center of both eyes are easily obtained from the position coordinates of both eyes and the calculation efficiency is high, it is more preferable to set the position corresponding to the center of both eyes as the center of rotation. preferable.

When "automatic tilt correction" is selected as described above, the eye position of the image for which the ID photograph is to be created is automatically detected, and the tilt is automatically corrected based on the detected eye position. Since the rotation processing is performed, it is possible to reduce the burden on the operator and the user when creating the ID photo.

In the next step 114, it is determined whether or not "automatic trimming" in the selection field 70D is selected, and if it is selected, the process proceeds to step 116,
Otherwise, return to step 104.

In step 104, when the information indicating that the operator has selected "automatic trimming" in the selection field 70D is input, or "automatic trimming"
In the state where is selected, the information indicating that the “inclination automatic correction” is instructed is input by the instruction button 70B, and when the automatic processing of the inclination correction is completed in step 112, the trimming area automatic setting processing is performed in step 116. Hereinafter, this processing will be described with reference to the flowchart of FIG. In step 170, the position of a point corresponding to the top of the person's head in the image (hereinafter, simply referred to as the apex) is detected based on the image data of the image for which the ID photograph is to be created. The position of the head apex can be detected, for example, as follows.

That is, an image (one example of which is shown in FIG. 9A) for which an ID photograph is to be created has a constant width (for example, several pixels) whose longitudinal direction is the Y direction which is the substantially vertical direction of the subject (person) in the image. A plurality of long regions each having a width of about a minute) are divided (a part of the dividing line is shown by a broken line in FIG. 9B), and the long regions are moved from the upper side to the lower side in the substantially vertical direction of the subject. While scanning, the density change amount is repeatedly calculated, and the position where the density change amount first becomes equal to or more than a predetermined value is stored as a head vertex candidate for each long region.

As a result, in FIG. 9B, the boundary position between the hair portion and the background is stored as a head vertex candidate for each of the elongated regions whose dividing lines are indicated by broken lines. Then, as shown in FIG. 9C, of the parts where the positions of the head vertex candidates are concentrated along the Y direction, the head vertex candidate located at the uppermost position is set as the head vertex, and its X coordinate value is set. And Y
Detect the coordinate value. As a result, the position of the head vertex in the image can be detected accurately in a short time. As a method of detecting the apex of the head, a position corresponding to both eyes of the person in the image is detected in advance, and the position of both eyes of the boundary position between the hair portion and the background detected by the above method is detected. A point on the vertical bisector may be used as the apex.

In the next step 172, the positions corresponding to both eyes of the person in the image are detected based on the image data of the image for which the ID photograph is to be created. This is a process similar to the process of step 150 (see FIG. 4) in the tilt automatic correction process of step 112 (see FIG. 3) described above,
If the inclination correction process is performed first in step 112,
Since the positions of both eyes have already been detected, the processing here is omitted.

In the next step 174, step 170
Of the head vertex position (specifically, the Y coordinate value of the head vertex) and the position of both eyes detected in step 172 (specifically, the Y coordinate value of either one of the eyes, or the Y coordinate value of both eyes). Based on the average value, the Y coordinate value of the position corresponding to the tip of the person's chin in the image is estimated. The present inventor has found that the distance along the Y direction between the eye position and the position of the tip of the jaw is substantially constant with respect to the distance along the Y direction between the head vertex position and the eye position (for example, 2 It was empirically found that it will be about 1 time).

The above empirically found ratio is stored in the HDD, and in step 174, the eye area is calculated based on the distance between the head vertex position and the eye position along the Y direction and the above ratio. The distance between the position and the position of the tip of the jaw along the Y direction is calculated, and the Y coordinate value of the position separated from the eye position by the calculated distance in the Y direction is calculated as the Y coordinate of the position of the tip of the jaw. We are seeking as a value. Note that the above ratio may be changeable by an operator's instruction or the like as a trigger.

In step 176, the face area corresponding to the face of the person in the image for which the ID photograph is to be created is determined in step 170.
Y of the face area is assumed to be distributed between the head vertex position detected in step 174 and the jaw tip position estimated in step 174.
As the directional length, a distance along the Y direction between the head vertex position and the jaw tip position (for example, the distance converted into the number of pixels on the image of the identification photograph creation target) is calculated.

In the next step 178, the length in the Y direction of the trimming area set for the image to be created for creating the ID photograph is calculated. The “overhead / face / submandibular ratio” in the ID photo information shown in Table 1 above is an overhead area existing above the face area in the trimming area and a face area as shown in FIG. And the appropriate ratio of the Y-direction length of each submandibular region existing below the face region in the trimming region, the desired size (size) of the face region in the ID photo depending on the type of the ID photo. In consideration of the fact that the ratios may be different, the “overhead / face / submandibular ratio” is stored for each type of identification photograph in this embodiment. Therefore, in step 178, the “overhead / face / submandibular ratio” stored corresponding to the type of the ID photograph selected on the creation condition designation screen is fetched, and step 1
At 80, the Y-direction lengths of the above-head region and the submandibular region are obtained based on the captured ratio and the Y-direction length of the face region calculated at the previous step 176, and at step 182,
As the Y-direction length of the trimming area, the sum of the Y-direction lengths of these areas is calculated.

Then, in step 184, the upper end position of the trimming area on the image for which the identification photograph is to be created is calculated based on the Y coordinate value of the head vertex position and the length of the overhead area in the Y direction, or Y of the jaw tip position is calculated. The position of the trimming region in the Y direction is set by calculating the lower end position of the trimming region on the image of the ID photo creation target based on the coordinate value and the length of the submandibular region in the Y direction. As a result, the size ratio along the Y direction of each of the above-head region, the face region, and the submandibular region in the trimming region matches along the Y direction so that the size ratio matches the appropriate ratio determined for each type of ID photo. The position of the trimming area is set.

At the next step 186, the aspect ratio of the trimming area corresponding to the type of the ID photograph selected on the creation condition designation screen is acquired. The aspect ratio of the trimming area is the same as the aspect ratio of the ID photo to be created, and in step 186, the “actual print size” corresponding to the type of ID photo selected from the ID photo information stored in the HDD. The aspect ratio of the trimming area is obtained by calculating the aspect ratio from the vertical and horizontal lengths represented by the captured “actual print size”.

In step 188, the length in the Y direction of the trimming area calculated in step 182 and step 186 are set.
The length of the trimming area in the X direction is calculated on the basis of the aspect ratio of the trimming area acquired in (3). Step 190
Then, the X coordinate value of the left eye part calculated in step 172 (=
X1) and the X coordinate value (= X2) of the right eye portion, that is, the X coordinate value of the position corresponding to the center of both eye portions along the X direction is calculated. This is because step 154 (FIG. 4) in the automatic tilt correction processing of step 112 (see FIG. 3) described above.
If the automatic tilt correction processing of step 112 is performed first, the X coordinate value of the position corresponding to the center of both eyes has already been obtained. Is omitted.

Then, in step 192, step 1
The position of the trimming area along the X direction is set so that the position corresponding to the center of both eyes along the X direction calculated at 90 coincides with the center of the trimming area along the X direction. As a result, the X of the trimming area is set so that the face area is located substantially at the center of the trimming area along the X direction.
The directional position will be set.

When the position and length of the trimming area along the Y direction and the position and length of the trimming area along the X direction are set as described above, the creation condition designation screen is displayed in the next step 194. The trimming frame in which the position and the length in the X direction and the Y direction are set is displayed in an overlapping manner on the image of the ID photograph creation target displayed in the area 70A, and at the same time, the trimming frame that has been displayed until then is deleted. , And returns to step 104 in FIG.

When “automatic trimming” is selected as described above, the head vertex position and the eye position of the image for which the ID photograph is to be created are automatically detected, and the detected head vertex position and the eye position are detected. The trimming area is set automatically, but if "Auto trim" is selected with "Auto trimming" selected, the trimming area is automatically trimmed after the image tilt is automatically corrected. Is set to, it is possible to reduce the burden on the operator for creating the ID photo.

When the displayed frame is adjusted according to the customer's preference, the operator performs an operation such as clicking any button of the instruction button group 70H to select the automatic trimming. If so, the selection is canceled and the manual trimming is selected, and the movement of the trimming frame (area) can be manually instructed. The size of the trimming frame (area) can be instructed by the operator performing an operation such as drag and drop on the displayed trimming frame. When an operator operates any button of the instruction button group 70C, the angle of the display image with respect to the trimming frame can be manually changed. The instruction button group 70C may be rotated clockwise or counterclockwise by a preset unit angle for one click, or may be rotated in response to an angle input. The angle to rotate with one click is
It may be changeable by using an operator's instruction or the like as a trigger. When the position and size of the trimming frame (area) and the rotation of the display image are instructed, the process proceeds from step 104 to step 108 to step 108,
As processing according to the input information, processing for changing the position or size of the trimming frame displayed in the display area 70A is performed.

On the other hand, when it is judged that the inclination of the image displayed in the display area 70A and the position and size of the trimming frame are proper, the operator selects the enter button 70J. As a result, the process proceeds from step 104 to step 118 via step 106, and a message is displayed on the display 20 asking the operator whether or not the designation of all the images to be recorded as the ID photo has been completed. In response, based on the information input by the operator, it is determined whether the designation of all the images is completed.

In the present embodiment, it is possible to create a plurality of types of ID photos from a single ID photo creation target image. When creating a plurality of types of ID photos,
It is necessary to specify the creation condition including the setting of the trimming area for each type. If there is a plurality of types of ID photos to be created whose creation conditions have not been specified, the determination at step 118 is denied, the process returns to step 102, and step 10
The processing from 2 is repeated. If the creation conditions including the setting of the trimming frame have been specified for all types of ID photos to be created, the determination at step 118 is affirmative and the process proceeds to step 120.

In step 120, based on the number of images to be recorded as the ID photo and the actual print size of each image, the individual images to be recorded in a recording frame (for example, a frame having the same size as the L size photo print) are recorded. Determine the layout such as position and orientation. And step 1
At 22, as shown in FIG. 11 as an example, a layout confirmation screen is displayed on the display 20 for the operator to confirm the layout determined at the previous step 120.

The layout confirmation screen shown in FIG. 11 is selected in the display area 72A for displaying a simulation image showing how the image corresponding to the ID photo whose creation is instructed is recorded on the photographic paper. Selection field 72 for finely adjusting the size of the image actually recorded on the photographic paper with respect to the actual print size corresponding to the type of the ID photograph.
B, a selection field 72C for selecting the recording interval of the ID photo (image), a selection field 72D for selecting the change of the arrangement order of the images, and a selection field for selecting the type of character information to be printed with the image. 72E and a print button 72F for instructing to print an image are provided respectively.

Then, in step 122, the second image processing section 60 extracts the data of the image area corresponding to the previously set trimming area from the high resolution image data of the image for which the ID photograph is to be created, and the extracted image The data is enlarged or reduced according to the actual print size, and according to the layout determined in step 120, the same number as the instructed number of sheets is pasted on the mount image (for example, a white image on the front side) (monochrome as a type). The designated image is pasted in monochrome and then pasted) for the number of types of the ID photo for which creation has been instructed, thereby generating recording image data used for recording the ID photo on the photographic paper. Then, in order to display the generated recording image data on the display 20, the resolution is reduced by the second image processing unit 60 and is displayed as an image in the display area 72A of the layout confirmation screen. Thus, by visually observing the image displayed in the display area 72A, the operator can easily understand the layout of the certification photograph instructed to be created on the photographic paper.

In the next step 124, it is determined whether or not the operator has input any information, and the process waits until the determination is affirmed. If any information is entered, step 12
If the determination of No. 4 is affirmative, the process proceeds to step 126, the content of the input information is determined, and the process branches depending on the determination result. When the information indicating that the operator has selected one of the plurality of options regarding the print characters displayed in the selection field 72E is input, the process proceeds to step 130.

The options displayed in the selection field 72E are
The type of character information that can be printed together with the image is shown in FIG.
3 types are displayed as options. Step 13
At 0, the character information selected by the operator is added to a predetermined position on the image displayed in the display area 72A, and the process returns to step 124. The character information indicating the date can be generated by obtaining the date information from the operating system of the image processing PC, and the character information indicating the size can be obtained from the ID photo information stored in advance in the HDD. . Further, the character information that is optionally added such as a comment may be set in the registry of the image processing PC or may be stored in the HDD. As a result, as an example, as shown in FIG. 11, the operator can visually confirm the added character information. Needless to say, as shown in FIG. 12, other character information such as the type of ID photo and the store name may be printed.

When the operator gives an instruction to change the image recording size, the recording interval, the arrangement order, etc., the processing proceeds from step 124 to step 126, and then step 12
8 and display area 72A according to the operator's instruction
A process of changing the image displayed on the screen is performed. When the operator selects the print button 72F, the process proceeds from step 124 to step 132 to step 132, and the same image as the image displayed in the display area 72A is recorded on the photographic paper. Therefore, in the second image processing unit 60, the above-described recording image data is generated again based on the high resolution image data.

Then, in step 134, step 13
The recording image data generated in 2 is used as the second image processing unit 60.
To the laser printer 22 via the color reproduction conversion unit 62. As a result, the same image as the image finally displayed in the display area 72A of the layout confirmation screen is exposed and recorded on the photographic paper by the laser printer 22, and is visualized through processing such as development by the paper processor. The ID photo is obtained by cutting out the image in a predetermined size from the photographic paper on which the image is recorded.
When the operator specifies the printing of the size and the like, as shown in FIGS. 11 and 12, character information representing the specified size is printed in the vicinity of each image. It is possible to prevent misidentification of the size and the like.

Although the trimming area has a rectangular shape in the above description, it is not limited to this and any shape can be adopted. In this case, the reference line of the image to be created may be set according to the form of the recorded image to be created.

Further, in the above-described example, the case where the image creating system using the image processing method of the present invention is applied to the ID photo creating image processing system 10 has been described, but the present invention is not limited to this. Instead, the customer installs the ID photo creation program on the PC at home, connects the customer's digital still camera, printer, or scanner to the PC to configure the image creation system of the present invention, and takes an image of the subject with this digital still camera. Or, using the image data obtained by exposing the subject to the photographic film by an ordinary camera and recording it, and then reading the visualized image with a scanner etc. after performing processing such as imaging on the photographic film. By executing the ID photo creation process,
The ID photo may be created by a printer connected to the PC.

In the above description, the program for automatically correcting the inclination of the original image is selectively performed for each target image, but the program is not limited to this and may be a program for all the acquired image data. in this case,
The image processing method of the present invention can be suitably used even in an automatic ID photo creating apparatus or the like without an operator.

Further, although the above description has been made by taking the creation of the ID photo as an example, the present invention is not limited to this, and can be applied to the creation of a photo of each student to be published in the school album. .

The image processing method according to the present invention has been described in detail above with reference to various embodiments. However, the present invention is not limited to the above examples, and within the scope not departing from the gist of the present invention. Of course, various improvements and changes may be made.

[0095]

As described in detail above, according to the present invention,
Original image data including a face area corresponding to a person's face is automatically corrected so that the positions of both eyes in the original image are at a predetermined angle with respect to a preset reference line, and a certification photograph, etc. Since it is possible to create an image suitable for the use of, it is possible to reduce the burden on the photographer or the customer to be photographed at the time of photographing, and the burden on the operator or the like when correcting the tilt of the image. Even a user who is not familiar with image processing operations using a PC, etc. can easily create a corrected image.

Further, according to one aspect of the present invention, based on the corrected image data in which the inclination of the original image is corrected, the face area corresponding to the face of the person in the corrected image has a predetermined size ratio within the trimming area. The trimming area can be automatically recognized more accurately so that it can be positioned, and it can be automatically set, so it is possible to quickly and easily create an image suitable for an application such as an ID photo. It is possible to reduce the burden on the photographer or the customer who is photographed and the burden on the operator or the like when setting the trimming area.

[0097]

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of an embodiment of an image creating system to which an image processing method according to the present invention is applied.

FIG. 2 is a block diagram showing a schematic configuration of an image processing system to which the image creating system shown in FIG. 1 is applied.

FIG. 3 is a flowchart showing the contents of a certification photograph creating process.

FIG. 4 is a flowchart showing the contents of an automatic tilt correction process according to the present invention.

FIG. 5 is a flowchart showing the contents of trimming area automatic setting processing.

FIG. 6 is an image diagram showing an example of a creation condition designation screen.

7A to 7H are conceptual diagrams for explaining the detection of both eyes.

8A and 8B are conceptual diagrams for explaining image inclination correction processing, in which FIG. 8A is a diagram before correction and FIG. 8B is a diagram after correction.

9A to 9C are conceptual diagrams for explaining the detection of head vertices.

FIG. 10 is an image diagram for explaining an overhead / face / subchinal ratio.

FIG. 11 is an image diagram showing an example of a layout confirmation screen.

FIG. 12 is an image diagram showing another example of character information that can be printed together with an image of a certification photograph.

[Explanation of symbols]

1 Image creation system 2 Photography means 3 Image data input means 4 Image display means 5 Image processing means 6 key input means 7 Image output means 10 Image processing system 12 Image data input device 13 digital camera 14 film scanner 15 Media driver 16 Image data receiving device 18 Image processing device 20 display 22 Laser printer 24 CD-R writing device 50 Image data preprocessing unit 52 First memory 54 second memory 56 First Image Processing Unit 58 Image processing control unit 60 Second image processing unit 62 color reproduction converter 64 key input section 68 Information storage medium

Claims (4)

[Claims] 1. A position corresponding to both eyes of a person in the original image is detected based on image data of the original image including a face area corresponding to a person's face, and the detected original image is detected. The original image is corrected so that the positions corresponding to both eyes of the person are located on the same straight line parallel to the reference line set in advance with respect to the original image or a straight line orthogonal to the reference line. Then, an image processing method for creating corrected image data. 2. The image processing method according to claim 1, wherein, when the original image is a rectangle, the reference line is a straight line parallel to one side of the rectangle. 3. The corrected image data is obtained by rotating the original image around a point in the approximate center of the original image or a point in the approximate center of a position corresponding to both eyes of a person in the original image. 3. The image processing method according to claim 1, wherein the image data is created by modifying the image data of the original image. 4. The image processing method according to claim 1, wherein a position corresponding to the crown of the person in the corrected original image is detected based on the corrected image data. , Based on the position corresponding to the crown and binocular part of the person in the detected original image, so that the face region is located at a predetermined position in a trimming region with a predetermined size, An image processing method comprising setting a trimming area for the corrected original image.