JP2001148780A - Method for setting red-eye correction area and red-eye correction method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a method for setting a red-eye correction area and a red-eye correction method that can efficiently perform setting of a red-eye correction area for the correction of red-eyes so as to enhance the quality of a red-eye corrected image. SOLUTION: In the case of correcting red-eyes in a picture caused at photographing to a prescribed pupil color, only the red-eyes are automatically extracted from an area including the red-eyes designated by an operator so as to set a red-eye correction object area. In the case that only the red-eyes cannot automatically be extracted, the operator manually designates only the red-eyes to set the red-eye correction object area, applies red-eye correction to the red-eye correction object area and converts the red-eye into a prescribed pupil color.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for setting a red-eye correction target area for correcting a red-eye of an image which has become red-eye during photographing, and correcting the set red-eye correction target area to a predetermined pupil color. On how to fix red eye.

[0002]

2. Description of the Related Art When photographing with a camera, particularly when photographing a person from the front with a strobe at night, a so-called red-eye phenomenon in which the pupil appears in red or gold may occur. This red-eye phenomenon is a phenomenon that occurs when strobe light enters the eye with the pupil open in a dark place from the front, the strobe light is specularly reflected, and this state is reflected in the image. . The red-eye phenomenon includes a red-eye in which the pupil appears red and a gold-eye in which the pupil appears golden (hereinafter, both eyes are referred to as red-eye). On the other hand, in order to reduce the pupil opening that causes red eyes, a camera having a function of preliminarily firing a strobe before shooting and then performing strobe shooting has been developed. However, this does not completely prevent the occurrence of red eyes, and also has serious drawbacks, such as preliminary lighting that makes the expression of a person unnatural and requires a special mechanism for performing preliminary lighting. .

In recent years, various methods have been proposed for preventing the occurrence of red-eye by digital image processing. For example,
JP-A-5-19382 discloses a process of photometrically measuring each point of an original image to obtain image data, a process of designating a red-eye region, a process of converting a red-eye region into a desired pupil color, and a process of converting the converted data. And a step of printing the original image on color paper based on the photographic printer. Japanese Patent Application Laid-Open No. 11-73499 discloses that a pixel of a digital image having original color data corresponding to a predetermined color and shape characteristic is identified, and the original color data of the identified pixel is adjusted to a desired value. A method for adjusting color in a digital image that results in Also, Japanese Patent Application Laid-Open No. 10-75374 filed by the present applicant discloses that an eye area is extracted from an area including an eye designated by an operator, and a red eye is obtained based on the hue and saturation of the extracted eye area. More specifically, a red-eye extraction method for determining a region having a hue within a predetermined red range and a saturation not less than a predetermined value as a red-eye, and a red-eye for reducing the saturation of an eye region determined to be a red-eye A correction method is disclosed.

[0004]

However, in the technique disclosed in Japanese Patent Application Laid-Open No. H11-73499, if the red-eye area cannot be identified or is erroneously identified, the red-eye correction is not properly performed. JP-A-5-193
No. 82 discloses a method of performing red-eye determination and red-eye correction manually and a method of automatically performing red-eye correction instead of the method. However, these methods are not comprehensively used in combination, and are not used in terms of operational efficiency. There was still room for improvement. Also, Japanese Patent Application Laid-Open No. H10-75374 discloses a specific method of extracting and correcting red eyes, but it is premised that an eye region is automatically extracted. If the extraction of red-eye and the determination of red-eye are not perfect, it is necessary to redo the operation from the beginning, and there is a problem that the entire image processing operation and the photo print operation are not always efficient.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-described conventional problems, and it is an object of the present invention to efficiently perform a setting operation of a red-eye correction target area for performing red-eye correction and improve the quality of a red-eye correction image. It is an object of the present invention to provide a method for setting a red-eye correction target area and a method for correcting red-eye which can be performed.

[0006]

In order to solve the above problems, a first aspect of the present invention is to correct the red eyes of an image in which red eyes have occurred during photographing to a predetermined pupil color by an operator or automatically. From the region including the red eye specified in advance, automatically extract only the red eye, and set a red eye correction target region for correcting to the predetermined pupil color,
An object of the present invention is to provide a method for setting a red-eye correction target area, wherein an operator manually designates only the red-eye and sets the red-eye correction target area when only the red-eye cannot be automatically extracted.

Here, it is preferable that the area including the red eye is at least one of an image frame, a face, an eye, and a periphery of the eye.

It is preferable that, when an image frame is designated as the region including the red eye, the image frame is designated by using photographing information.

When the eye or the periphery of the eye is specified as the area including the red eye, one eye may be designated by pointing to one eye or enclosing the eye in a rectangular area, or both eyes may be segmented. It is preferable that at least one of either one eye or both eyes can be specified by tying each other or enclosing both eyes with a rectangular area to specify both eyes.

It is preferable that the setting of the red-eye correction target area is performed on image data on which at least one of color adjustment and density correction has been performed.

When setting the red-eye correction target area, the position of the red-eye is substantially specified on a test screen for determining image processing conditions including at least one of color and density, and then the screen is displayed. It is preferable to set the red-eye correction target area by switching to the output image.

Further, according to a second aspect of the present invention, the red-eye correction target area is set by the method for setting a red-eye correction target area according to the first aspect of the present invention, and the set red-eye correction target area is set to the predetermined area. And a red-eye correction method for performing red-eye correction for converting into a pupil color.

Here, it is preferable that the setting of the red-eye correction target area and the red-eye correction are performed on image data on which at least one of color adjustment and density correction has been performed.
Further, when setting the red-eye correction target area, after substantially specifying the position of the red-eye on the test screen for determining the image processing condition including at least one of the color and the density, the screen is displayed on the output image. Preferably, the setting of the red-eye correction target area and the red-eye correction are performed.

Further, in the case where an image photographed in color is output as a monochrome image, the setting of the red-eye correction target area and the red-eye correction for the color image are performed on the color image. Is preferably converted to a monochrome image.

The setting of the red-eye correction target area (that is, the designation of red-eye) is performed on the first image data, and the red-eye correction is performed by setting the red-eye correction target area on the first image data (that is, the red-eye correction target area). It is preferable to perform this for the second image data based on the result of (red eye designation). At this time, it is preferable that at least one of the number of bits, the resolution, and the image size of the first image data is smaller than that of the second image data.

Further, the first image data is preferably image data of a partial image of the image represented by the second image data, and is preferably generated from the second image data. Preferably, the first image data is pre-scan image data, and the second image data is fine scan image data.

When red-eye designation is performed on the first image data and red-eye correction is performed on the second image data, the result of the red-eye designation is held separately from the first image data. Preferably, the red-eye designation information is applied to the second image data, and the red-eye designation information used as the red-eye designation result is at least one of red-eye position information and red-eye area information.

In this specification, "red eye designation" includes designation of the red eye itself and designation of a region including the red eye, and "setting of the red eye correction region" refers to the region of the pupil having the red eye. "Red-eye extraction" refers to automatically or manually extracting the pupil region that has become red-eye, and "red-eye correction" means that the pupil region that has become red-eye, that is, "red-eye extraction" Automatically or manually corrects the pupil region that has become the red eye extracted in step (1).

[0019]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A method for setting a red-eye correction target area and a method for correcting red-eye according to the present invention will be described below in detail based on preferred embodiments shown in the accompanying drawings.

FIG. 1 is a block diagram showing an embodiment of a method for setting a red-eye correction target area according to the present invention and a digital photo printer for implementing the red-eye correction method according to the present invention. A digital photo printer (hereinafter referred to as a photo printer) 10 shown in FIG. 1 includes a scanner (image reading device) 12 that photoelectrically reads an image photographed on a film F, and image data (image information) read by the scanner 12. ), A method for setting a red-eye correction target area according to the present invention, implementation of a red-eye correction method, various image processing, and a photo printer 1
0, an image processing device 14 for performing operations and control of the whole,
An image recording device 16 that image-exposes a photosensitive material (printing paper) with a light beam modulated according to the image data output from the image processing device 14, develops the image, and outputs a (finished) image as a print; Have. Further, the image processing apparatus 14 has a keyboard for inputting various conditions such as inputting, setting, selecting and instructing processing, and inputting an instruction such as a setting method of a red-eye correction target area for red-eye correction and a red-eye correction method. An operation system 18 having a mouse 18b and a mouse 18b;
A monitor 20 that displays an image read by the scanner 12, various operation instructions, a setting / registration screen for various conditions, and the like is connected.

The scanner 12 is a device for photoelectrically reading an image photographed on a film F or the like one frame at a time.
A variable aperture 24, a diffusion box 26 for making the reading light incident on the film F uniform in the surface direction of the film F, a carrier 28 of the film F, and an imaging lens unit 30
, An image sensor 32 having a three-line CCD sensor corresponding to reading of image densities of R (red), G (green), and B (blue), an amplifier (amplifier) 33, and an A / D (analog / digital). ) A converter 34.

In the photo printer 10, a dedicated carrier 28 which can be mounted on the main body of the scanner 12 is provided with a film F such as a new photographic system (Advanced Photo System) or a 135 size negative (or reversal) film.
Are prepared in accordance with the type and size of the film, the form of the film such as strips and slides, and the like, and can be adapted to various films and processes by replacing the carrier 28. An image (frame) photographed on a film and provided for printing is conveyed by the carrier 28 to a predetermined reading position. Also, as is well known, a magnetic recording medium is formed on the film of the new photographic system, and a cartridge ID, a film type, etc. are recorded. And various data such as the model of the developing machine can be recorded. The carrier 28 corresponding to the film (cartridge) of the new photo system includes:
The magnetic information reading means is arranged, reads the magnetic information when the film is transported to the reading position, and sends these various kinds of information to the image processing device 14.

When reading an image photographed on the film F in such a scanner 12, uniform reading light emitted from the light source 22 and adjusted in light amount by the variable aperture 24 and the diffusion box 26 is transmitted by the carrier 28. Incident on the film F located at the predetermined reading position,
By transmitting the light, projection light carrying an image photographed on the film F is obtained. The color image signal is not limited to a signal input by reading the light transmitted through the film as described above, and may be a reflection original or an image captured by a digital camera.

In the illustrated example, the carrier 28 is a 24
It corresponds to a long film F (strips) such as a 35-size film or a cartridge of a new photo system. The carrier 28 holds the film F at a predetermined reading position while, for example, RG
The film F is conveyed in such a manner that the longitudinal direction of the film F coincides with the sub-scanning direction orthogonal to the main scanning direction, which is the extending direction of the three-line CCD sensor B. The film F is positioned at the reading position by the carrier 28 and is transported in the sub-scanning direction.
The reading light is incident. Thereby, as a result, the film F
Are two-dimensionally slit-scanned by a slit (not shown) extending in the main scanning direction, and an image of each frame captured on the film F is read.

The projection light of the film F is imaged on the light receiving surface of the image sensor 32 by the imaging lens unit 30. The image sensor 32 includes, for example, a line CCD sensor for reading an R image, a line CCD sensor for reading a G image, and a line C for reading a B image.
A so-called 3-line color CCD with a CD sensor
In the sensor, each line CCD sensor extends in the main scanning direction as described above. The projection light of the film F is separated into three primary colors of R, G and B by the image sensor 32 and read photoelectrically. Image sensor 32
R, G and B output signals output from the A / D converter 34 are amplified by an amplifier 33 and sent to an A / D converter 34.
In the converter 34, for example, each of 12-bit R
After being converted into GB digital image data, it is output to the image processing device 14.

In the scanner 12, when an image photographed on the film F is read, a pre-scan (first image reading) for reading at a low resolution and a fine scan (first image reading) for obtaining image data of an output image are performed. (2nd image reading). Here, the pre-scan is performed under preset pre-scan reading conditions so that the image sensor 32 can read all images of the film F to be scanned by the scanner 12 without saturation. On the other hand, the fine scan is performed under the fine scan reading conditions set for each frame from the pre-scan data so that the image sensor 32 is saturated at a density slightly lower than the minimum density of the image (frame). The prescan and fine scan output image signals are basically the same image data except that the resolution and the output image signal level are different.

Note that the scanner 12 used in the photo printer 10 is not limited to one that performs such slit scanning reading, and may be one that performs planar reading that reads the entire surface of one frame of film image at a time. Good. In this case, for example, an area sensor such as an area CCD sensor is used, and means for inserting R, G, and B color filters are provided between the light source 22 and the film F, and inserted into the optical path of the light emitted from the light source 22. The reading light transmitted through the color filters is irradiated onto the entire surface of the film F, and the transmitted light is imaged on the area CCD sensor to read the entire image of the film. By doing so, the image photographed on the film F is separated into three primary colors and read.

As described above, the digital image data signal output from the scanner 12 is output to the image processing device 14. FIG. 2 is a block diagram of the image processing apparatus (hereinafter, referred to as a processing apparatus) 14. Here, the processing device 14 is a part that implements the method for setting a red-eye correction target area and the method for correcting red-eye according to the present invention.
LOG converter 38, prescan (frame) memory 4
0, a fine scan (frame) memory 42, a pre-scan data processing unit 44, a fine scan data processing unit 46 for performing various image processing, and a condition setting unit 48. FIG. 2 mainly shows a portion related to the image processing.
For controlling and managing the entire photo printer 10 including the printer
U, a memory for recording information necessary for operation of the photo printer 10 and the like are provided.
Are connected to each part via the CPU or the like (CPU bus).

The R, G, and B image signals input from the scanner 12 to the processing device 14, for example, 12-bit digital image data, are input to the scanner correction unit 36.
The scanner correction unit 36 performs DC offset correction, dark correction, and defective pixel correction to correct the sensitivity variation and dark current of each pixel of RGB digital image data caused by the three-line CCD sensor of the image sensor 32 of the scanner 12. And data correction of the read image data such as shading correction. The digital image signal that has been subjected to the correction processing of the sensitivity variation and dark current for each pixel by the scanner correction unit 36 is output to the LOG converter 38. The LOG converter 38 converts the digital image data into gradation data by performing logarithmic conversion processing, and converts the digital image data into digital image density data. For example, the LOG converter 38 corrects the digital image data using the lookup table (LUT) by the scanner correction unit 36. The obtained 12-bit digital image data is, for example, 10 bits (0 to 1023)
To digital image density data.

The digital image density data converted by the LOG converter 38 is stored (stored) in the pre-scan memory 40 if it is pre-scan image data and in the fine scan memory 42 if it is fine scan image data. . The pre-scan memory 40 is obtained by pre-scanning the film F by the scanner 12,
This is a frame memory for storing low-resolution image density data of the entire frame of the film F subjected to various data corrections and logarithmic conversion processes for each of the RGB colors. The prescan memory 40 needs to have a capacity capable of storing image density data of at least one frame of the film F in three colors of RGB, but may have a capacity capable of storing image density data of a plurality of frames. It may have a large number of memories each having a capacity of one frame. The pre-scan image data stored in the pre-scan memory 40 is read by the pre-scan data processing unit 44.

On the other hand, the fine scan memory 42 stores the high-resolution image density data of the entire frame of the film F obtained by the fine scan of the film F by the scanner 12 and subjected to various data correction and logarithmic conversion processing. This is a frame memory for storing each color. The fine scan memory 42 has a capacity to store at least image density data of three colors of RGB of two images of the film F, and while writing image density data of one frame, image density of another one frame is written. It is preferable that the data is read out and various image processes are simultaneously performed in the fine scan data processing unit 46.
It may have a capacity to store the image density data for each frame, and may be for processing one frame at a time. Further, a memory having a large number of memories for one frame may be used, for example, a toggle memory. The fine scan image data stored in the fine scan memory 42 is read out by the fine scan data processing unit 46.

A prescan data processing unit 44 that performs various image processes required for displaying on the monitor 20 on the prescan image data stored in the prescan memory 40
An image processing unit 50 having a red-eye processing unit 51 for performing a method for setting a red-eye correction target area and a red-eye correction method according to the present invention;
And an image data conversion unit 52. Here, the image processing unit 50 reads the image data read by the scanner 12 according to the image processing conditions set by the condition setting unit 48 described later and stores the image data stored in the pre-scan memory 40 with a desired image quality into the monitor 20 described later. A lookup table (hereinafter referred to as L) so that a color image can be reproduced on a CRT display screen of
By performing predetermined image processing such as gradation correction, color conversion, density conversion, and the like by a calculation using a UT (represented by UT) or a matrix (represented by MTX), a red-eye correction unit 51 performs a red-eye correction process described later. , For generating image data having a desired display quality in which the pupil portion is corrected to a natural color.

The image data conversion unit 52 includes an image processing unit 50
The image data processed according to the above is thinned out as necessary to match the resolution of the monitor 20,
The image data is converted into image data corresponding to the display on the monitor 20 using a (three-dimensional) LUT or the like, and is displayed on the monitor 20. The processing conditions in the image processing unit 50 are set by a condition setting unit 48 described later.

On the other hand, the fine scan data processing section 46 for executing various image processing necessary for outputting the fine scan image data stored in the fine scan memory 42 from the image recording device 16 as a color print is An image processing unit 54 having a red-eye processing unit 55 for performing the method for setting a red-eye correction target region and the method for correcting a red-eye according to the invention
And an image data conversion unit 56. Here, the image processing unit 54 performs predetermined image processing on the image data read by the scanner 12 and stored in the fine scan memory 42 in accordance with the image processing conditions set by the condition setting unit 48, which will be described later. Concentration,
An image can be reproduced on color paper with gradation and color tone. Therefore, the image processing unit 54 performs color balance adjustment, gradation adjustment, color adjustment, density adjustment, saturation adjustment, and electronic scaling on the image data by using an LUT, an MTX arithmetic unit, a low-pass filter, an adder / subtractor, and the like. Image processing such as image enhancement and sharpness enhancement (edge enhancement; sharpening), the details of which will be described later, the red-eye processing unit 55 corrects the red-eye pupil into a natural color, and converts the output image data. Generate.

The image data conversion unit 56 includes an image processing unit 54
Is converted into image data corresponding to image recording by the image recording device 16 using a standard gradation lookup table such as a 3DLUT and supplied to the image recording device 16. Image recording device 16
Is for outputting as a finished print in which a color image is reproduced based on the image data output from the fine scan data processing section 46.

The processing conditions in the image processing section 54 are set in the condition setting section 48. The condition setting unit 48
Various processing conditions in the fine scan data processing unit 46 are set. The condition setting unit 48 includes a setup unit 58, a key correction unit 60, and a parameter integration unit 62. The setup unit 58 sets the fine scan reading conditions using the prescan image data and supplies the conditions to the scanner 12, and creates the image processing conditions for the prescan data processing unit 44 and the fine scan data processing unit 46. (Calculation) and supplies the result to the parameter integration unit 62.

More specifically, the set-up section 58 reads out the pre-scan image data from the pre-scan memory 40 and creates a density histogram, average density, LATD (large area transmission density), and highlight from the pre-scan image data. Calculation of image feature amounts such as (lowest density) and shadow (highest density) is performed. From the calculated image feature amount, the scanning conditions of the fine scan, such as the light amount of the light source 22, the aperture value of the variable aperture 24, the image sensor 32, and the like, are set so that the image sensor 32 is saturated at a density slightly lower than the minimum density of the image. Set the accumulation time and so on. The fine scan reading condition may change all the elements corresponding to the output level of the image sensor with respect to the prescan reading condition, or change only one element such as the aperture value. Alternatively, only a plurality of factors such as the aperture value and the accumulation time may be changed. Further, the setup unit 58 responds to the density histogram and the image feature amount and an instruction from an operator performed as necessary.
Image processing conditions such as the above-described color balance adjustment and gradation adjustment are set. The image processing conditions preferably include at least one of color and density.

The key correction unit 60 includes an adjustment amount such as density (brightness), color, contrast, sharpness, and saturation set by a key (not shown) provided on the keyboard 18a and the operation system 18, and a mouse 18b. The amount of adjustment of image processing conditions (for example, LU
A correction amount of T) is calculated, parameters are set, and the parameters are supplied to the parameter integration unit 62. The parameter integration unit 62 receives the image processing conditions set by the setup unit 58, and transmits the supplied image processing conditions to the image processing unit 50 of the pre-scan data processing unit 44 and the image processing unit 54 of the fine scan data processing unit 46. After setting, the image processing condition set for each part is corrected (adjusted) or the image processing condition is reset according to the adjustment amount calculated by the key correction unit 60.

The image processing unit 50 and the fine scan data processing unit 46 of the pre-scan data processing unit 44
The image processing unit 54 is provided with red-eye processing units 51 and 55 that correct the red-eye pupil portion to a natural color after each of the various processes described above. Hereinafter, the red-eye correction processing performed by the red-eye correction units 51 and 55, that is, the method of setting a red-eye correction target area and the method of correcting red eye according to the present invention will be described in detail.

First, regarding the first red-eye correction processing, FIG.
This will be described with reference to the flowchart of FIG. Step 100
In this case, a test is performed on the image displayed on the monitor 20, and a region including a red eye is designated from the test screen image on which various adjustments and correction processes such as color adjustment and density correction have been performed. FIG. 4 shows an example of the test screen, but the test screen is not limited to such a display of six frames, and may be one frame display or another plural frame display. In the present embodiment, the designation of the area including the red eye is performed by an operator's input from the keyboard 18a or the mouse 18b of the operation system 18, a touch panel (not shown), or the like. As a method of specifying a region including a red-eye, as shown in FIG.
There are a method of designating the image 70, a method of designating the face or face region 72 in the frame, and a method of designating the eye or eye region 74 or the region around the eye in the face.

As a method of specifying a frame (scene) or a frame, the frame can be specified by selecting a frame number as shown in FIG. 4 or by directly indicating the area of the frame. . When a strobe light is emitted, there is a high possibility that red-eye has occurred. Therefore, this frame can be designated using shooting information such as whether or not a strobe light is emitted. As described above, for example, various types of shooting information can be recorded in the magnetic information of the film of the new photo system. it can. As a method of designating a face region, a region including the face can be designated as a region 72 in the frame 72a by surrounding it with a rectangular frame 72a. Or, mouse 1
8b or the like. As a method of designating the eye region, as shown in FIG. 4, a region 74 including both eyes and a peripheral region of both eyes is surrounded by a rectangular frame 74a.
Can be designated as an area 74 within the area. When designating a face or eye area, an area including the face or eyes may be directly indicated. It should be noted that the frame of the red-eye correction target image is not limited to the frame of the film, but may be the frame (scene) of an image captured by a digital still camera or the like.

Next, in step 102, red-eye extraction is automatically performed to set a red-eye correction target area. This red eye extraction method is not particularly limited, and various known methods can be applied as follows. For example, a predetermined feature amount for each pixel in each region specified above is calculated, the image is divided into regions for each region where the feature amount forms a mountain, and the shape and other regions are respectively determined for each of the divided regions. , The area ratio, the density, and the average color are checked, and the one having the characteristic of the pupil part is selected and set as the red-eye correction target area. In addition,
When two or more areas are selected as red-eye correction target areas in one eye image, the shape, the arrangement relation (position) with other areas, the area ratio, the density, and the average color are evaluated. Then, the region with the highest evaluation is selected as the red-eye correction target region.

As an evaluation method, for example, for each of the divided areas, a first point is obtained in which the higher the circularity is, the higher the point is, and the one having the highest point is the one having the characteristic of the pupil part, that is, There is a method of setting a red-eye correction target area. In addition, for each of the divided areas, the distance between the position of the center of gravity and the center position of the designated area is calculated, and the second point is obtained, in which the shorter the distance is, the larger the score is. There is a method that has the feature of the portion most, that is, a red-eye correction target region.

Further, for each of the divided areas, the ratio between the area of the divided area and the area of the designated area is obtained, and the obtained ratio is a predetermined value such as the range of the ratio between the area of the pupil and the area of the designated area. There is a method in which a third score is obtained in which the score becomes smaller as the value goes out of the range, and the score with the highest score is the one having the characteristic of the pupil portion, that is, the red-eye correction target region.

Further, statistical values measured in advance using one or more of the average value, the maximum value, the minimum value, the contrast, and the histogram shape in any one or more of hue, saturation, and lightness From the comparison with the typical poor tone area information, the fourth point having a higher score as the one having a feature closer to the feature of the poor tone area is obtained, and the one having the highest score is the one having the characteristic of the pupil part, that is, There is a method of setting a red-eye correction target area.

Next, in step 104, it is determined whether or not the red-eye extraction, that is, the setting of the red-eye correction target area has been completed. As a result, if the red-eye extraction is successful, the process proceeds to step 108;
In step 106, the operator manually designates only the red eye and sets the red eye correction target area.
Proceed to 08. At this time, if it is considered that the red-eye extraction could not be performed or the red-eye extraction result is not correct, it is more preferable to automatically switch to the manual mode. Also, if you know that flash photography has taken place, there is a high possibility that red-eye has occurred.Therefore, the camera or the film with a lens records information with flash emission magnetically or optically. May search for red eyes.

The setting of the red-eye correction target area by designating only the red-eye by the operator is performed as follows.
For example, as shown in FIG. 5A, the center of the pupil of both eyes is specified by the keyboard 18a or the mouse 18b of the operation unit 18, and both eyes are specified by connecting the eyes with a line segment 76. In this case, the length at a predetermined ratio from both ends of the line segment 76 connecting the center portions of the designated pupils of both eyes is defined as 1 of the major axis.
An elliptical area having a length of / 2 is defined as an individual eye area,
Set as a red-eye correction target area to be processed. Alternatively, as shown in FIG. 5B, an area including both eyes and a peripheral area of both eyes is surrounded by a rectangular frame 78 by a keyboard 18a or a mouse 18b of the operation unit 18, and an area in the frame 78 is designated. Is set as a red-eye correction target area to be processed. At this time, in any of the above cases, the region between the eyebrows is excluded by using the ratio of the eye size statistically calculated. When both eyes are designated, both eyes can be designated at one time, so that the efficiency of the setting work of the red-eye correction target area, that is, the efficiency of the red-eye correcting work can be improved.

The designation of the red-eye and the setting of the red-eye correction target area may be performed not only for both eyes at once but also for one eye. For example, as shown in FIG. 6A, an area including the peripheral area of one eye is designated by surrounding it with a rectangular frame 80 using the keyboard 18a or the mouse 18b of the operation unit 18, and the area in the frame 80 is specified. Is set as a processing target and a red-eye correction target area is set. Or, FIG.
As shown in (b), a red-eye correction target area is set and designated by pointing to the center 82 of one eye.
Note that the designation method and the setting method are not limited to these, and it goes without saying that other designation methods and setting methods may be used. For example, the area around the eye including the eye is the operation unit 1
8, keyboard 18a or mouse 18b, etc.
The red-eye correction target area may be set by specifying the processing target area by enclosing it in a handwritten manner.

Next, in step 108, red eye correction processing is performed. Red-eye correction is performed on the fine scan image. For the fine scan image that has been subjected to various adjustments and corrections by the image processing conditions set by the setup unit 58 by the test on the prescan image,
The setting of the red-eye correction target area and the red-eye correction are performed as described below. FIG. 7 shows an example of the red-eye correction screen. The red-eye correction screen 84 displays the pre-red-eye correction image 86 and the red-eye correction image 88 side by side, and the operator performs the red-eye correction while watching them.

The operator clicks the enlarge button 90a on the image 86 before red-eye correction, enlarges the image, and designates the red-eye portion 86a. Next, by clicking the test button 90b, the red-eye portion 86a that has just been specified is clicked.
, A red-eye correction process is performed. That is, when the test button 90b is clicked, the color of the red-eye portion 86a is converted into a predetermined color (for example, black) and displayed as the red-eye corrected image 88. The operator looks at the screen display, and if the correction result is good, the confirm button 90
Click c. When the red-eye correction is completed and the operator clicks the print button 90d, the image with the red-eye correction is output as a print. At this time, if there are a plurality of red eyes, the processing from red eye specification to determination is repeated for each red eye. Also in this case, it is needless to say that a plurality of red eyes may be specified and then finally collected and fixed.

The red-eye correction processing used in the present invention is not limited to the above-described one, and a conventionally known red-eye correction processing can be used. For example, the method disclosed in Japanese Patent Application Laid-Open No. H10-75374 filed by the present inventor can be used. This method
The eye region is extracted from the region including the eye specified by the operator, and only the digital image data of the eye region is extracted from the digital image data of the region including the eye based on, for example, the connectivity of low brightness pixels. After accurate extraction, perform red-eye determination of the eye area, perform processing to remove red eye when it is determined to be red eye, for example, if originally black eye, reduce the saturation of the eye area, Black eyes are corrected by approaching an achromatic color. For example, in the case of blue eyes, a desired blue hue is designated and stored in advance, and the blue eye is corrected by performing hue conversion.

In this method, it is determined whether or not the eye area is red-eye, for example, when the eye area has a red hue within a predetermined range and has a saturation not less than a predetermined value. It is determined to be red eye. That is, in the red-eye determination, the hue range and the saturation threshold of the eye region may be set. For example, RGB digital image data is converted into L ^* a ^* b ^* colorimetric colorimetric values, and the following formula is used to calculate the average value of the hue and saturation of the eye region.
In ₁ ≦ H ≦ H _2, and determines that red-eye when C ≧ C _th. H (hue) = tan ^-1 (b ^* / a ^* ) C (saturation) = √ (a ^{* 2} + b ^{* 2} ) where H ₁ and H ₂ are red hue ranges, and C _th is saturation. The threshold is used.

Next, the second red-eye correction processing will be described with reference to FIG.
This will be described with reference to the flowchart of FIG. First, in step 200, a pre-scan is performed, and in the next step 202
Then, the pre-scanned image is displayed on the monitor 20, a test is performed, and various adjustments and corrections are performed to set image processing conditions. In the next step 204, the red-eye position is substantially specified for the prescanned image after this test in the same manner as described above. In the next step 206, a fine scan is performed, a high-resolution fine scan image is read,
In step 208, instead of the pre-scan image displayed on the monitor 20, the fine scan image on which the various adjustments and correction processes set above have been performed is displayed on the monitor 20 as a red-eye correction image. In step 210, the image is enlarged and displayed, and a red-eye correction target area for both eyes or one eye is set. At this time, since the red-eye position is substantially specified in the pre-scan image, if the fine-scan image is enlarged and displayed around the specified position, the red-eye correction target area can be more easily set. In the next step 212, red-eye correction is performed in the same manner as in the above-described first red-eye correction processing.

At this time, in the example described above, the red-eye position is substantially specified by the pre-scan image, but a fine scan image may be used from the beginning. As a result, although the processing speed is slightly reduced, the setting of the red-eye correction target area and the accuracy of the red-eye correction are improved. In the case of a digital still camera, an image for output (print, media) is used from the beginning. In this case, an image in which the output image (data) is reduced or thinned out may be used. Further, when a red-eye position is designated, it is preferable that the red-eye position is enlarged around that position.

Next, the third red-eye correction processing will be described with reference to FIG.
This will be described with reference to the flowchart of FIG. This is a case where a monochrome (black and white or sepia) image is created from a color negative film. Therefore, it is substantially the same as the above-described second red-eye correction processing, except that the color image is converted into a monochrome image after the red-eye correction is performed. First, in step 300, a pre-scan is performed, and in the next step 302, various adjustments and corrections are performed on the pre-scan image, and a verification screen is displayed on the monitor 20. In the next step 304, the red-eye position is substantially specified in the same manner as described above. In the next step 306, fine scan is performed. In step 308, the fine scan image is displayed on the red-eye correction screen instead of the pre-scan image on the monitor 20. In step 310, the image is enlarged and displayed, and a red-eye correction target area for both eyes or one eye is set.
As described above, the red-eye designation operation and the setting operation of the red-eye correction target area are performed with a color image because the red-eye can be more easily extracted with a color image. In step 312, the color image is subjected to red-eye correction in the same manner as the second red-eye correction process described above, and in step 314, the color image is converted to a monochrome image.

Next, the fourth red-eye correction processing will be described with reference to FIG.
This will be described with reference to the flowchart of FIG. This is based on a method of setting a red-eye correction target area other than the above-described method of setting a red-eye correction target area by designating a frame (scene), face, or eye. Step 400
In FIG. 11, as shown in FIG. 11, the image is divided and a divided area is designated. In step 402, the divided areas are enlarged and displayed, and the divided areas 92 and 94 including red eyes are designated.
At this time, if the eye straddles two or more divided blocks, all the straddling blocks (92a and 92b and 94a and 94b in FIG. 11) are designated. In step 404, a red-eye correction target area is set from the specified divided area including red-eye, and step 4
At 06, the above-described red-eye correction processing is performed on the set red-eye correction target area.

In the present invention, as described above, red-eye designation is performed on the first image data such as pre-scan image data, and red-eye extraction, setting of a red-eye correction target area, and red-eye correction Based on the result of the red-eye designation and designation information performed on the first image data, it is preferable to perform the second image data such as finer scan image data with higher resolution, but both are the same. This may be performed using image data.

The first image data used for red-eye designation is not limited to the case where the resolution is smaller than the second image data used for red-eye extraction, setting of a red-eye correction target area, and red-eye correction. The size may be small. For example, when the first image data is 8-bit image data, the second image data may be 10-bit image data. Further, the first image data may be image data of a partial image of the image represented by the second image data, or may be generated from the second image data.
For example, when the second image data is fine scan image data, the first image data may be reduced image data, thinned image data, or partially enlarged image data of the fine scan image data, or For example, when the second image data is captured image data of a digital still camera, the first image data is reduced image data, thinned image data, or partially enlarged image data of the captured image data of the digital still camera. Also good

In the present invention, it is preferable that the red-eye designation, the red-eye extraction, the setting of the red-eye correction target area, and the red-eye correction are performed on the image data on which at least one of the color adjustment and the density correction is performed. In order to more appropriately perform red-eye designation, red-eye extraction, setting of a red-eye correction target area, red-eye correction, and the like, it is better to perform color adjustment because accuracy is improved.

In the present invention, as shown in FIG. 12, the photographed image is displayed on the verification screen of the monitor 20 using the first image data 500 (step 51).
0), red-eye designation is performed on the display image in the test screen (step 512), and the result (red-eye designation result) is stored separately from the first image data 500, for example, in an internal memory (shown in FIG. (Step 51).
4). At this time, it is preferable that the red-eye designation information held separately from the first image data 500 as the red-eye designation result is at least one of red-eye position information and red-eye area information (its size and size). In this way, the red-eye designation result held separately from the first image data 500 is applied to the second image data 501, and red-eye extraction and red-eye correction are performed on the second image data 501 based on the red-eye designation result. (Step 516), it is output as output image data 502. Although not shown in FIG. 12, before output as the output image data 502, the second image data 501 includes various image processing and data processing other than the red-eye correction processing. It goes without saying that it is applied before and after.

According to the method for setting the red-eye correction target area according to the present embodiment and the red-eye correction method based thereon, not only the actual print but also the index print, the file print, or the media output (CD)
-R, ZIP, JAZ, etc.) also have red-eye corrected. For index print, file print, and media output (CD-R, ZIP, JAZ, etc.), whether or not to perform red-eye correction can be selected in advance, and the results can be reflected. And even better. In addition, a red-eye scene with only one eye is designated with one eye, and with both eyes, both eyes are designated, so that red-eye correction can be performed at once. Further, even when red eyes cannot be automatically extracted due to gold eyes, half eyes, fine eyes, etc., the operator sets red eye correction and sets a red eye correction target area, so that red eyes can always be corrected. As a result, the operation efficiency is greatly improved, and the quality of the red-eye corrected image is improved. The setting of the red-eye correction target area according to the present invention can be applied not only to the negative film but also to the setting of the red-eye correction target area when correcting a red-eye image taken by a reversal film, a digital camera, or the like. In addition, a common GUI (Grafic User Inte
rface) environment, it can be applied not only to red eyes but also to correction of wrinkles, scratches, acne, etc.

Although the method for setting the red-eye correction target area and the method for correcting red-eye according to the present invention have been described in detail above, the present invention is not limited to the above examples, and various methods may be used without departing from the gist of the present invention. It goes without saying that improvements and changes may be made.

[0063]

As described above, according to the method for setting a red-eye correction target area and the method for correcting red-eye according to the present invention, the operation efficiency can be greatly improved, and the quality of the red-eye corrected image is improved. be able to. Also, according to the present invention, in a common GUI environment, not only red eyes,
It has an excellent effect that it can be applied to correction of wrinkles, scratches, acne, and the like.

[Brief description of the drawings]

FIG. 1 is a block diagram schematically illustrating a digital photo printer that performs image processing including a method for setting a red-eye correction target area and a method for correcting red-eye according to the present invention.

FIG. 2 is a block diagram schematically illustrating the image processing apparatus of FIG. 1;

FIG. 3 is a flowchart showing an outline of a first red-eye correction method.

FIG. 4 is an explanatory diagram showing an example of a test screen for designating a region including a red eye.

FIGS. 5A and 5B are explanatory diagrams each showing an example of a method of designating both eyes.

FIGS. 6A and 6B are explanatory diagrams each showing an example of a designation method for one eye. FIG.

FIG. 7 is an explanatory diagram showing an example of a red-eye correction screen.

FIG. 8 is a flowchart showing an outline of a second red-eye correction method.

FIG. 9 is a flowchart showing an outline of a third red-eye correction method.

FIG. 10 is a flowchart showing an outline of a fourth red-eye correction method.

FIG. 11 is an explanatory diagram showing an example of a method of specifying red eyes by specifying a divided area.

FIG. 12 is an explanatory view schematically showing another example of the red-eye correction method of the present invention.

[Explanation of symbols]

Reference Signs List 10 digital photo printer 12 scanner 14 (image) processing device 16 image recording device 18 operation system 18a keyboard 18b mouse 20 monitor 22 light source 24 variable aperture 26 diffusion box 28 carrier 30 imaging lens unit 32 image sensor 34 A / D converter 36 Scanner correction unit 38 LOG converter 40 Prescan (frame) memory 42 Fine scan (frame) memory 44 Prescan data processing unit 46 Finescan data processing unit 48 Condition setting unit 50, 54 Image data conversion unit 51, 55 Red-eye processing unit 58 Setup unit 60 Key correction unit 62 Parameter integration unit 70 Frames 72 Face area 74 Eye area 76 Line segment 72a, 74a, 78, 80 that connects both eyes Rectangular frame 82 Central part of eye 84 Red eye correction screen After 6 red eye corrected image before 88 redeye corrected image 90a enlargement button 90b test button 90c enter button 90d print button 92 (92a, 92b), 94 (94a, 94b) divided region including a red

Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat II (Reference) H04N 1/46 C

Claims (19)

[Claims] When correcting the red eye of an image in which red eye has occurred during photographing to a predetermined pupil color, only the red eye is automatically extracted from a region including the red eye specified in advance by an operator. In addition to setting the red-eye correction target area for correcting to the color of red, and when it is not possible to automatically extract only the red eye, the operator manually specifies only the red eye and sets the red-eye correction target area. Setting method of the red-eye correction target area to be set. 2. The method according to claim 1, wherein the area including the red eye is at least one of an image frame, a face, an eye, and a periphery of the eye. 3. The method of setting a red-eye correction target area according to claim 2, wherein, when an image frame is designated as the area including the red-eye, photographing information is used. 4. When the eye or the periphery of the eye is designated as the area including the red eye, one eye is pointed, or one eye is designated by surrounding the one eye with a rectangular area, or both eyes are lined. 3. The method for setting a red-eye correction target area according to claim 2, wherein at least one of either one eye or both eyes can be specified by connecting both eyes or enclosing both eyes with a rectangular area to specify both eyes. . 5. The method for setting a red-eye correction target area according to claim 1, wherein the setting of the red-eye correction target area is performed on image data on which at least one of color adjustment and density correction has been performed. . 6. When setting the red-eye correction target area, after substantially specifying the position of red-eye on a test screen for determining image processing conditions including at least one of color and density, the screen is displayed. The method of setting a red-eye correction target area according to claim 1, wherein the red-eye correction target area is set by switching to an output image. 7. The red-eye correction target area is set by the method for setting a red-eye correction target area according to claim 1, and the set red-eye correction target area is converted into the predetermined pupil color. A red-eye correction method comprising performing red-eye correction. 8. The red-eye correction method according to claim 7, wherein the setting of the red-eye correction target area and the red-eye correction are performed on image data on which at least one of color adjustment and density correction has been performed. 9. When the red-eye correction target area is set, the position of the red-eye is substantially specified on a test screen for determining image processing conditions including at least one of color and density, and then the screen is displayed. 8. Switching to an output image and setting the red-eye correction target area and correcting the red-eye.
Or the red-eye correction method according to 8. 10. When outputting an image captured in color as a monochrome image, after setting the red-eye correction target area and performing the red-eye correction on the color image, the color image is converted to a monochrome image. The red-eye correction method according to claim 7. 11. The red-eye designation is performed on first image data, and the red-eye correction is performed on second image data based on a result of the red-eye designation on the first image data. Item 10. The red-eye correction method according to any one of Items 7 to 10. 12. The red-eye correction method according to claim 11, wherein said first image data has a smaller number of bits than said second image data. 13. The red-eye correction method according to claim 11, wherein the first image data has a smaller resolution than the second image data. 14. The red-eye correction method according to claim 11, wherein the first image data has a smaller image size than the second image data. 15. The red-eye correction method according to claim 11, wherein the first image data is image data of a partial image of an image represented by the second image data. 16. The red-eye correction method according to claim 11, wherein said first image data is generated from said second image data. 17. The method according to claim 11, wherein the first image data is pre-scan image data, and the second image data is fine scan image data. 18. A red-eye designation for the first image data and a red-eye designation result for the red-eye correction for the second image data, wherein the result of the red-eye designation is stored separately from the first image data. 18. The method according to claim 11, wherein the method is applied to the second image data. 19. The red-eye correction method according to claim 11, wherein the red-eye specification information used as the red-eye specification result is at least one of red-eye position information and red-eye area information.