JP2763221B2 - How to extract human face data - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for extracting data of a person's face, and more particularly to density data of a person's face used when copying a color original image onto a color copying material or a black and white copying material. A method of extracting face data of another person.

[0002]

2. Description of the Related Art The most noticeable part when viewing a photograph of a person is the face of the person. To create a high-quality photograph, the color of the face of the person must be adjusted appropriately. It is necessary to bake to a different color.

Conventionally, a face area in an original image of a color film is designated with a light pen to extract density data of a person's face, and the face color is appropriately printed based on the extracted density data. Exposure is determined. Such a technique is disclosed in JP-A-62-115430, JP-A-62-115431, and JP-A-62-1154.
No. 32, JP-A-62-189456, JP-A-62-189457, JP-A-63-138340
And JP-A-63-178222.

[0004] However, in the above-mentioned conventional technique, there is a problem that the printing operation takes a long time because the operator has to specify a face area with a light pen for each image. Further, since the operator must visually specify the face area, it is difficult to perform unmanned operation.

Further, Japanese Patent Application Laid-Open No. 52-156624,
JP-A-52-156625, JP-A-53-123
No. 30, JP-A-53-145620, JP-A-53-145621, JP-A-53-145622
The following publication describes a method of extracting human face data by extracting skin color data. That is, the color original image is divided into a large number of photometry points, and each photometry point is separated into three colors of R (red), G (green), and B (blue), and photometry is performed. Is determined to be within the skin color range. Then, clusters (groups) of photometric points determined to be in the skin color range are used as face density data.

However, in this method, since the color within the skin color range is assumed as the density data of the face, parts other than the face having the skin color or the color similar to the skin color, such as the ground, a tree trunk, and clothes, are also included in the face. It is extracted as density data.

[0007] Even if a skin color or a portion similar to the skin color, such as the ground or a tree trunk, can be extracted and extracted, even in an image of a sea bathing season, a pool, or the like, an area having the same color as the face with much exposed skin is a face. May be present around the face, and the surrounding area may be connected to the face area. Further, in the image of a person, there is an image with a cheek stick or the like, and an image of the same color as the face is combined with the face area. Therefore, if an attempt is made to extract a face region from the color characteristics of the original image, it is not possible to extract a face-only region, and a combined region of the same color is also extracted. As a result, the density data of only the face cannot be automatically extracted.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problem, and it is possible to automatically extract only the face data of a person, which is characteristic image data, from a color original image such as a negative film with high accuracy. An object of the present invention is to provide a method of extracting data of a person's face that can be performed.

[0009]

According to a first aspect of the present invention, a color original image is divided into a large number of pixels, and each pixel is separated into three colors of red light, green light and blue light. Photometry, based on the data obtained by photometry, determine the same or similar color area on the color original image, assume a circle or an ellipse inscribed at the boundary of the determined color area, and The color area determined by the area of the circle or the ellipse in order from the large circle or the ellipse is divided, at least one of the divided areas is selected, and the data of the selected area is extracted as the data of the face of the person.

According to a second aspect of the present invention, a color original image is divided into a large number of pixels, each pixel is separated into three colors of red light, green light and blue light, and photometry is performed, and based on data obtained by photometry. Te determined the original color hue same or similar color regions on the image Rutotomoni obtains the nucleus of said color area, assuming a circle or ellipse inscribed in a boundary portion of the color area, and the area is maximum obtains an area of a circle or oval, the color region odor
Te, said area obtains a convex area above where the constant area that protrudes outward from the outer peripheral region of the largest circle or ellipse, the convex region
Includes and inscribes the border region of the color region excluding the nucleus
Circle or ellipse with the largest area
The color region is divided by a circle region, at least one of the divided regions is selected, and data of the selected region is extracted as human face data.

[0011]

[Action] Since the most noticeable part when viewing a portrait is the face of a person, it is preferable to extract data of the area of the face of the person from the color original image and use that data as feature image data. . In addition, the shape of a person's face is almost a circle or an ellipse, and a person's face area may be extracted by preferentially extracting a circle area from similar color areas of a color original image. Is high.

According to the first aspect of the present invention, a color original image is divided into a large number of pixels, each pixel is separated into three colors of red light, green light and blue light, and photometry is performed. Based on this, a color region having the same or similar hue is obtained on the color original image. Next, assuming a circle or an ellipse inscribed at the boundary portion of the obtained color region, the obtained color region is divided by a circle or an ellipse in order from a circle or an ellipse having a large area. As a result, there is a high possibility that the finally divided area is an independent area including only the face. Therefore, each of the divided color regions of the color original image is further divided into regions that are likely to be extracted as face regions, and if at least one region representing the features of this image is selected, the selected color region is selected. Since the data of the region represents the characteristic image data, the characteristic image data can be extracted by selecting the region.

When the face area is in contact with a part other than the face (for example, when the face area is buried in the body when photographed diagonally from above in a pool), the inscribed circle of the color area If the face is divided first, the face region may be divided and extracted. Therefore, in the second aspect of the present invention, a color region having the same or similar hue is obtained on a color original image based on data obtained by photometry as described in the first aspect. At the same time, the nucleus of the color area is determined.
You. Next, a circle or an ellipse inscribed in the boundary portion of the obtained color region is assumed, and a circle or an ellipse having the largest area is obtained. Then, the calculated area, if the convex area of more than a predetermined area that protrudes from the outer periphery of a circle or oval on the outside Oh <br/> Ru, the colors except for containing and the nuclei convex region
Assuming a circle or oval inscribed at the boundary of the area, and
The color area is divided by a circle or an ellipse having the largest area . As a result, even if similar color regions are in contact with each other on the original color image, a circle or an oval region in which a person's face region is likely to be extracted can be preferentially divided as a face region. By selecting at least one of the divided areas, the data of this area can be extracted as feature image data.

[0014]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A first embodiment of the present invention will be described below in detail with reference to the drawings. In this embodiment, the present invention is applied to an auto printer. As shown in FIG. 1, the automatic printer according to the present embodiment includes a transport roller 12 that transports a color negative film 10. Below the color negative film 10 transported by the transport rollers 12, a light source 14, a color correction filter 16 such as a dimming filter, and a diffusion box 18 are sequentially arranged. Above the negative film 10, a distribution prism 20 for distributing the light transmitted through the negative film 10 in two directions is arranged. On one optical path distributed by the distribution prism 20, a projection optical system 22, a black shutter 23, and color paper (printing paper) 24 are sequentially arranged, and on the other optical path, a projection optical system 26 and a CCD image sensor. 28
Are arranged in order. This CCD image sensor 28
Divides the entire screen (one frame) of the negative film 10 into a number of pixels (for example, 256 × 256 pixels) and divides each pixel into three colors of R (red), G (green), and B (blue). Decompose and meter. The CCD image sensor 28 is connected to a 3 × 3 matrix circuit 34 for correcting the sensitivity of the CCD image sensor via an amplifier 30 for amplifying the output of the CCD image sensor and an analog-digital (A / D) converter 32. The 3 × 3 matrix circuit 34 is connected to an appropriate exposure amount calculation circuit 40 via a face extraction circuit 36 composed of a microcomputer storing a program of a routine described below, and calculates the average density of the entire screen. It is connected to an appropriate exposure calculation circuit 40 via an average density calculation circuit 38 for calculating. The appropriate exposure amount calculation circuit 40 is connected to the color correction filter 16 via a driver 42 for driving a color correction filter.

Next, the operation of this embodiment will be described. Light source 14
Are transmitted through the color correction filter 16, the diffusion box 18, and the color negative film 10, are distributed by the distribution prism 20, and are received by the CCD image sensor 28 via the projection optical system 26. At this time, the black shirt 23 is closed. By receiving the light, the CCD image sensor 28 divides the entire screen into a large number of pixels, decomposes each pixel into three colors of R, G, and B, performs photometry, and outputs a photometric data signal. The photometric data signal is amplified by an amplifier 30 and then converted into a digital signal by an A / D converter 32, the sensitivity of the image sensor is corrected by a 3 × 3 matrix circuit 34, and a face extraction circuit 36 and an average density calculation circuit 38 Is input to The average density calculation circuit 38 calculates the average density of one entire screen. The face extraction circuit 36 estimates the portion of the face of the person in one screen as described below, and outputs R, G, and B colorimetric data of the portion estimated as the face. The exposure calculation circuit 40 calculates the exposure using the three-color photometric data output from the face extraction circuit 36 and the average density calculated by the average density calculation circuit 38, and outputs the color correction filter 16 via the driver 42. And the black shutter 23 is opened and closed to perform printing. When the average density calculated by the average density calculation circuit 38 is used, an exposure correction amount for the average density can be calculated. If the exposure correction amount is not determined, the exposure amount may be determined directly from the three-color photometric data output from the face extraction circuit 36 without necessarily requiring the average density calculation circuit 38.

FIG. 2 shows a face extraction routine by the face extraction circuit 36. In step 100, noise removal, that is, smoothing of the three-color photometric data input at step 100 is performed. In the next step 102, the following (1) to (3)
The R, G, and B three-color photometric data are represented by H (hue value),
It is converted into L (brightness value) and S (saturation value).

L = (R + G + B) / 3 (1) S = 1-min (r ′, g ′, b ′) (2) H = H ′ / 2Pi (.) 3) However, R, G, and B are standardized such that the minimum value is 0 and the maximum value is 1 as shown in the three-dimensional color coordinates of FIG.
Colorimetric data, min () is the minimum value in parentheses, r ′, g ′, b ′ are r ′ = R / L, g ′ = G / L,
b ′ = B / L. H ′ is given by the following equation (4), and Pi (i is one of R, G, and B) is P
It is.

[0018]

(Equation 1)

However,

[0020]

(Equation 2)

In step 104, as shown in FIG. 4A, a two-dimensional histogram of the hue value and the saturation value is obtained by using a coordinate system including a hue value axis, a saturation value axis, and a pixel number axis which are orthogonal to each other. , And in the next step 106, the obtained two-dimensional histogram is divided into mountains, that is, clustering of the two-dimensional histogram is performed. In the next step 108, clustering of a large number of pixels is performed based on the peaks of the clustered two-dimensional histogram, the screen is divided based on the clustering, and a region that is a candidate for a human face is extracted from the divided region. . In the next step 110, the color region extracted as a face candidate is further divided into a circle or an oval region, so that at least the face region is divided into other regions, and based on the divided region, To estimate the face area, and output R, G, and B colorimetric data of the area estimated as the face. Then, it is determined in step 112 whether or not printing of all frames has been completed. When it is determined that printing has been completed, this routine is terminated.

Next, the details of steps 106 to 110 will be described. FIG. 5 shows details of step 106. In step 120, an area to be evaluated is cut out from the two-dimensional histogram of the hue value and the saturation value.
In FIG. 4, one frame is set as an evaluation area for simplifying the explanation. In step 122, it is determined whether or not there is an evaluation area. When the evaluation area cannot be cut out in step 120, that is, when the evaluation of all the areas is completed, there is no evaluation area, so this routine ends. If there is an evaluation area, the X and Y axes for creating a mountain cutout histogram are determined in step 124.
In other words, the evaluation area is rotated around an axis parallel to the pixel number axis, and when a mountain of the histogram is viewed from the side, a multimodal property is prioritized and a position where the mountain is the sharpest is obtained. Determine X and Y axes. If the processing time needs to be shortened, the accuracy is slightly reduced, but an axis with the maximum variance of the histogram may be used as the X and Y axes. In the example of FIG. 4 (1), when the four mountains numbered 1 to 4 are viewed from the side, multi-modality is prioritized, and the positions where the mountains are sharpest are positions where the three mountains can be seen. Therefore, the X axis is defined in a direction orthogonal to the viewing direction, and the Y axis is defined in a direction orthogonal to the X axis.

In the next step 126, a one-dimensional histogram is created by projecting the two-dimensional histogram on the X and Y axes. In the example of FIG. 4A, when viewed from a direction orthogonal to the X axis, the peaks denoted by reference numerals 1 and 2 appear to overlap each other. Three peaks, that is, peaks 1 and 2, and peaks 4 appear, and when viewed from a direction orthogonal to the Y axis, the peaks 1 to 4 appear to be overlapped, so that one dimension about the Y axis is obtained. One peak appears in the histogram. In the next step 128, the histogram is converted into an evaluation function H (a) by the following equation (5), and peaks are cut out from the histogram on the X axis based on this evaluation function.

[0024]

(Equation 3)

Where f (a) is the number of pixels when the value (feature amount) in the X-axis direction is a, and x is the displacement from the feature amount a.

That is, the average value T of the evaluation function H (a) is obtained, and the range (the existence range of the valleys and the skirts) which is equal to or less than the average value T of the evaluation function H (a) is obtained. Next, the minimum position of the histogram within this range is defined as a valley or a skirt of the histogram. Then, a histogram is cut out at the determined valley or foot.

Referring to FIG. 6, the above-mentioned cutting of the mountain will be described. When the evaluation function H (a) is obtained from the histogram represented by the solid line SI, it becomes as shown by the broken line in the figure. The range in which the evaluation function H (a) is equal to or less than the average value T for the negative part is a range in which the feature amounts are v0 to v1 and v2 to v3. The position where the frequency of the histogram within this range is the minimum is the range v
Av0 = v0 for 0 to v1, av1 for the range v2 to v3
And av0 is obtained as a foot and av2 is obtained as a valley, and a histogram is cut out at this position.

At step 130, the peak of the histogram on the Y axis is cut out in the same manner as the peak of the histogram on the X axis. Next Step 13
In step 2, a region where the peaks of the one-dimensional histogram on the X-axis and the Y-axis cut out on the two-dimensional histogram overlap as described above is obtained, and the peak is cut out from the two-dimensional histogram on the hue value and the saturation value. . An area E1 in FIG. 4A shows an example of a mountain cut out as described above.

In the next step 134, it is determined whether or not the mountain cut out from the two-dimensional histogram is a single peak. If not, steps 124 to 134 are performed until the mountain cut out from the two-dimensional histogram becomes a single peak. repeat. The area E2 in FIG. 4 (3) shows an example of a single-peak mountain cut out as described above.

In the next step 136, a process (labeling) for attaching a label for identifying the cut-out single peak is performed. In step 138, the labeled peak is masked, and the process returns to step 120. Then, the above steps are repeated to divide the entire area of the two-dimensional histogram for the hue value and the saturation value into a single peak.

FIG. 7 shows the details of step 108 in FIG. 2. In step 140, the X-axis range XR (FIG. 4 (3)) and Y of the single-peak mountain divided in the above-described manner. The axial range YR (FIG. 4 (3)) is obtained for each single peak, and it is determined whether the hue value and the saturation value of each pixel of the original image belong to these ranges, and the pixel clustering is performed. At the same time, pixels belonging to the range surrounded by the ranges XR and YR are collected, and the original image is divided such that the collected pixels form one area on the original image. Numbering is performed on the divided areas. FIG. 4 (2) shows an example in which the original image is divided, and the pixels in the respective regions denoted by reference numerals 1 to 4 are:
These correspond to the pixels included in the single peaks denoted by reference numerals 1 to 4 in FIG. In FIG. 4 (1), pixels belonging to the same single-peak mountain are divided into different regions in FIG. 4 (2). This is because in FIG. Although the pixel has a saturation value range, the region is divided in FIG. 4B.

In the next step 142, the small area is removed by determining the area of the divided area, and the numbering is performed again. In the next step 144, a contraction process of deleting all the boundary pixels of the region and removing it by one skin, and a dilation process of multiplying the boundary pixels in the direction of the background pixel and increasing the thickness of the skin by performing the expansion process in contrast to the contraction process are performed. Are separated from the large area. Next step 146
Then, as in step 142, small areas are removed and renumbering is performed. In step 148, the same contraction and expansion processing as described above is performed in order to separate the weakly coupled areas. Similarly, the removal and renumbering of the minute area are performed.

FIG. 8 shows details of step 110. In addition, in order to describe step 110 in detail, an explanation will be given using an image shown in FIG. 9A in which a color region of the same color or a similar color as the face extends over a wide range.

First, in step 162, step 1
08, that is, one region is selected as the region of interest from the regions extracted in the routine of FIG. 7 (see FIG. 9A). Next, a nucleus for decomposing the attention area by performing the contraction processing of the selected attention area is obtained. That is, the contraction processing for deleting the boundary pixels of the attention area is repeatedly performed, and the one remaining dot-shaped or linear area is finally set as a nucleus. And the linear region, as shown in FIG. 9 (2), (a set of pixels or more pixels) a plurality of consecutive points That refers to those made to the line L _1. The target image is the original image C
Since it is based on data obtained by photometry by the CD image sensor 28 and is not a continuous system but a discrete system,
The nucleus will have a certain area. Further, depending on the shape of the target image, there may be a plurality of nuclei that are finally left. In this case, a region having the minimum area is used as a nucleus. When a region having the same area remains, an arbitrary one is selected.

In the next step 164, a circle or oval having the largest area inscribed in the region of interest with the nucleus obtained as described above as the center is obtained. That is, by performing the expansion process around the nucleus by the number of times the erosion process is performed to obtain the nucleus as described above, the nucleus is an inscribed circle when the nucleus is point-like, and It can be obtained as an inscribed ellipse (morphologic filter).

After obtaining a circle or an ellipse having the largest area inscribed in the attention area, the flow advances to step 166, and the flow advances to step 166.
At 66, a process (labeling) of attaching a label for identifying the obtained circle having the largest area (or an ellipse formed by this circle) is performed. In the next Step 168, Step 1 is performed by masking the labeled circle or oval region BL1.
Proceed to 70. In the next step 170, it is determined whether or not division of all extracted regions by a circle or an oval region has been completed.
Steps 2 to 168 are repeated. As a result, FIG.
As shown in (2) to (6), the regions BL1 to BL10 are divided in the order of the large-area circles BL1 to BL10.

When the division of the attention area is completed, step 17 is executed.
Proceed to 2. In step 172, a face region is estimated by selecting at least one of the divided circles or ellipses, which will be described in detail later, and the R, G, B of the region estimated to be a face is selected.
The photometric data is output to the appropriate exposure calculation circuit 40.

As described above, even when the color region of the same color as the face extends over a wide range including a region other than the face, the color region is further divided into a circular region having a high probability as the face region. By selecting this circular area, it is possible to extract data of only the face area with high probability from an image in which faces, grounds, trees, and the like having similar hues and saturations are mixed.

The above-described kernel L _i and inscribed circle region X _i are obtained by the following set operation expressions (6) and (7).
Can be represented by

[0040]

(Equation 4)

Here, the shape B _i for shrinking the color area and finding the inscribed circle of the color area centering on the nucleus is given by the following equation (8).
Can be determined by

[0042]

(Equation 5)

[0043] However, B: circular components also the n _i can be determined by the following equation (9).

[0044]

(Equation 6)

Here, k = 1, 2,... M _i ² = Area (XX ′ _i−1 ) Area (X): area of X region By selecting this k value optimally, the size to be decomposed N _i can be determined. Note that the above equation (9)
May be the equation (10) shown below.

[0046]

(Equation 7)

Here, k = 1, 2,..., R ₀ : radius of the component B Further, the relationship between the circular component B and the X region is as follows.

[0048]

(Equation 8)

Can be represented by FIG. 15 shows step 1
In step 302, one of the regions divided into the circle or the ellipse as described above is selected as the characteristic region, and the horizontal fillet diameter and the vertical fillet diameter of the characteristic region are determined. The size of the characteristic region is standardized by performing the enlargement / reduction processing of the characteristic region so as to obtain the value, and the density value or the luminance value is also standardized according to the following equation (11).

[0050]

(Equation 9)

Here, dmax: maximum density value (or luminance value) in the area dmin: minimum density value (or luminance value) in the area ds: full scale density value (or luminance value) of the image sensor d: density value before standardization (Or luminance value) dr: density value after standardization (or luminance value) In step 304, a plurality of (ten in this embodiment) standard face images stored in advance (a face image viewed from the front, The correlation coefficient r of the characteristic region with respect to the face image (left / right), downward face image, upward face image, etc.
The correlation coefficient is calculated by the equation 2), and the correlation coefficient is used as a feature amount.
Even if this standard face image is data of only the contour of the face, the internal structure of the face (eye, nose, mouth, etc.) is included in the data of the contour of the face.
Data obtained by adding data may be used.

[0052]

(Equation 10)

However,

[0054]

[Equation 11]

T is the length of the horizontal and vertical fillet diameters of the image (here, the lengths of the fillet diameters are the same), f
(X, y) represents a feature region, and g (x, y) represents a standard face image.

Then, in step 306, it is determined whether or not the characteristic region is a person's face by linear discriminant analysis using the characteristic amount as a variable, and the R, G, B photometric data of the region determined to be the face is determined. Is output to the appropriate exposure amount calculation circuit 40. In step 308, it is determined whether or not the determination as to whether the face is a face has been completed for all the divided areas, and if not, steps 302 to 308 are repeated.

In the above description, the correlation coefficient is used as the feature value used to determine whether or not the face is a person. However, the invariant derived from the normalized central moment around the center of gravity described below, An autocorrelation function or a geometric invariant may be used.

The central moment μ _pq around the (p + q) th order center of gravity of the image f (x, y) is

[0059]

(Equation 12)

However,

[0061]

(Equation 13)

If so, the normalized central moment around the center of gravity is as follows.

[0063]

[Equation 14]

Here, y = (p + q + 2) / 2 p + q = 2, 3,... From the above, the following seven invariants ψ _{i are} obtained from the normalized central moment around the second and third centroids. _, (I
= 1, 2,..., 7) are derived.

[0065]

(Equation 15)

The autocorrelation function R _f is expressed as follows.

[0067]

(Equation 16)

The geometrically invariant feature is expressed by the following equation.

[0069]

[Equation 17]

The proper exposure amount calculating circuit 40 includes the face extracting circuit 3
6, the R, G, and B photometric data of the face area extracted as described above and the screen average density D _i (i = R, G, or B) of one frame calculated by the average density calculation circuit 38 ) and using the calculated the proper exposure amount E _i according to the following equation, and outputs to the driver 42. The driver 42 controls the light adjustment filter 16 calculates an exposure control value from the appropriate exposure amount E _i.

[0071] However _{l og E i = LM i ·} CS it · (DN i -D i) + PB i + LB i + MB i + NB i + K 1 + K 2 ... (11), each symbol is a thing of the next.

LM: Magnification slope coefficient, which is set in advance according to the enlargement magnification determined by the type of the negative and the print size.

CS: There are color slope coefficients prepared for each type of negative for underexposure and overexposure, and it is determined whether the average density of the frame to be printed is under or over the standard negative density value. Under exposure or over exposure is selected.

DN: Standard negative density value. D: Average density value of print frame.

PB: Correction balance value for standard color paper, which is determined according to the type of color paper.

LB: For a standard printing lens. The correction lens balance value is determined according to the type of the printing lens.

MB: a correction value (master balance value) for a change in the printing light source or a change in paper developing performance.

NB: Negative balance (color balance) value determined by the characteristics of the negative film.

K ₂ : color correction amount. K ₁ : a density correction amount represented by the following equation.

[0080]

(Equation 18)

[0081] Here, K _a, K _b are constants, FD is the face region average density. Further, as the correction value determined density correction amount K ₁ in equation (8) by the film detecting device may represent a color correction amount K ₂ using the face region average density as follows.

[0082]

[Equation 19]

Here, K _c is a constant. Furthermore, the density correction amount K ₁ in equation (8), the color correction amount K ₂ is a correction amount determined by the film detecting device, the average concentration FD of average density D _i a face region of the print frame in formula (8) _i
The exposure amount may be determined instead.

Next, a second embodiment of the present invention will be described with reference to the flowchart shown in FIG. In the present embodiment, a face region is optimally divided from a region in contact with a face region. That is, in most cases, the face region in the image of the person is around the body. Therefore, when the color region including the face region has a plurality of convex regions, the color region is divided from the circular region inscribed in the convex portion, and the divided circular region is selected. In this case, a region having a high possibility of estimating a circle region as a face region is preferentially divided.

First, in step 180, step 1
08, that is, one region is selected as a region of interest from the regions extracted in the routine of FIG. 7 ((1) of FIG. 11).
reference). And as in the first embodiment, obtaining the nuclear L _a region of interest by performing contraction processing of the selected region of interest (see FIG. 11 (2)).

[0086] In the next step 182, the area that is inscribed in the region of interest around the core L _a found as described above obtains the largest circle or ellipse B _a. Next step 184
Then, the area ER _i (i remaining around the inscribed circle of the region of interest is determined by comparing the area of the region of interest with the circle or oval inscribed in the region of interest obtained as described above.
= 1, 2, ...) is determined to be greater than or equal to a predetermined value.
When the area of the remaining region ER _i is above a predetermined value, because of the possible presence of the convex region in the remaining region ER _i, the process proceeds to step 186, step 1 in the case of less than the predetermined value
Go to 92.

In step 186, first, FIG.
As shown in, excluding nuclear L _a obtained as described above from the region of interest (the mask). In the next step 188, contraction and expansion processing are performed in the same manner as described above, and the kernel L
_a is an area that is inscribed to the mask region of interest to seek largest circle or ellipse B _b (see FIG. 11 (4)).

In the next step 190, each of the inscribed circles or ellipses B _a and B _b obtained as described above is determined by a predetermined (1
(3) The size of the convex portion on the outer side of the focused color region is determined by determining the size of the region that extends out of the region of interest out of the expanded region by expanding the region of about pixels. In other words, it is determined that the larger the area of the expanded area that protrudes from the attention area, the more the area is convex.
If a convex portion with a circle or ellipse B _b obtained is large, the process proceeds to step 194, the process proceeds to step 196 is performed a process of attaching a label to identify the circle or ellipse B _b inscribed obtained. Convex portions by circular or oval B _a
Is larger , step 1 is performed as in the first embodiment.
At 92, a process of attaching a label for identifying a circle having the largest area inscribed in the attention area (or an ellipse formed by the circle) is performed, and the flow advances to step 196.

In step 196, the area of the circle or oval labeled in step 192 or 194 is masked, and the flow advances to step 198. In step 198, it is determined whether or not the division into circles or ellipses has been completed for all the extracted regions, and if not, steps 180 to 198 are repeated. In the next step 200, at least one of the divided circles or ellipses is selected, the face region is determined in the same manner as in the first embodiment, and the R, R, and R of the region determined to be a face are determined. The G and B photometric data are output to the appropriate exposure amount calculation circuit 40.

As described above, in the present embodiment, attention is given to a circular region having a large area in the vicinity of the convex portion and inscribed in the convex portion around the color region, that is, a circular region having a high probability of being a face region. Since the region is divided from the region, even in the color region where the body and the face are in contact, it is possible to extract the face region data by dividing only the face region with higher accuracy.

Although the above embodiment has been described with respect to an example in which the image is divided into color regions based on the two-dimensional histogram of the hue value and the saturation value, the present embodiment is not limited to this. It may be divided into color regions based on a histogram using only values. Further, the present invention is not limited to the histogram, and the color region may be divided based on other feature amounts of the original image.

FIG. 12 shows a modified example in which the present invention is applied to an exposure determining device separate from a printer or a printer processor. In FIG. 11, parts corresponding to those in FIG. 1 are denoted by the same reference numerals, and description thereof is omitted. Although the average density calculation circuit 38 is not always necessary, an integrated transmission density detection circuit for detecting LATD of the entire screen may be used instead.

FIG. 13 shows a configuration in which the face extraction circuit of FIG. 12 is composed of a plurality of face extraction circuits 36 ₁ , 36 ₂ ... 36n, and the exposure amount is calculated by parallel processing. Face extraction circuit 36
_1, 36 ₂ ··· 36n reads an image according to the time chart of FIG. 14, calculates the exposure amount, and outputs the result. In FIG. 14, t ₁ is the image reading time of one frame, t
₂ one frame of an exposure amount calculating time, t ₃ is the one frame of an exposure amount computation result transfer time is t ₂ >> t _1, t _3. The face extraction circuit 36 ₁ reads an image of one frame at time t ₁ ,
It calculates the exposure amount in ₂ hours, and transfers the calculation result t ₃ hours. At the same time when the image reading of one frame by the face extraction circuit 36 ₁ is completed, the film is fed by one frame and the face extraction circuit 36
₂ starts reading a single frame image, and the face extraction circuit 3
6 ₁ of the image reading of the exposure operation and the face extraction circuit 36 ₂ is performed in parallel, and so the face extraction circuit 36 _3, 36
₄ ... 36n are processed in parallel.

The time Tp required for parallel processing of mxn frames is Tp = m (t ₁ + t ₂ + t ₃ ) + (n−1) t ₁ . On the other hand, the processing time T when parallel processing is not performed
s is Ts = m · n (t ₁ + t ₂ + t ₃ ). Therefore,

[0095]

(Equation 20)

It is possible to double the speed. This parallel processing device can be applied to the printer shown in FIG.

The present invention, besides determining the exposure amount of a photographic printing apparatus, determines the exposure amount of a digital color printer, determines the copy conditions of a copying machine, determines the exposure amount of a camera, determines the display conditions of a CRT screen, and performs hard copy from magnetic image data. Can also be applied to the determination of the amount of light when creating.

[0098]

As described above, according to the first aspect of the present invention, even if an image of the same color or a color similar to the characteristic image is mixed in the area divided by the color area division,
Since the color region is divided into circle regions that are likely to be a person's face, the effect is obtained that a person's face image can be separated with a high probability and only the data of the person's face can be extracted.

According to the second aspect of the present invention, since a region having a large area in contact with a circle inscribed in a color region is preferentially divided, a portion having the same or similar hue as a person's face is mixed. This has the effect that the face data of a person can be separated and extracted with a high probability.

[Brief description of the drawings]

FIG. 1 is a schematic view showing a printer according to an embodiment of the present invention.

FIG. 2 is a flowchart showing a face extraction routine of a face extraction circuit.

FIG. 3 is a diagram showing color coordinates.

FIG. 4A is a diagram illustrating a two-dimensional histogram of hue values and saturation values. (2) is a diagram showing a state in which the original image is divided. (3) is a diagram showing a state where a single peak is cut out from a two-dimensional histogram.

FIG. 5 is a diagram showing details of step 106 in FIG. 2;

FIG. 6 is a diagram showing a histogram and an evaluation function.

FIG. 7 is a diagram showing details of step 108 in FIG. 2;

FIG. 8 is a diagram showing details of step 110 in FIG. 2;

FIG. 9 is a diagram showing a process of dividing a color area according to the first embodiment.

FIG. 10 is a flowchart of a face estimation routine according to a second embodiment of the present invention.

FIG. 11 is a diagram showing a process of dividing a color area according to the second embodiment.

FIG. 12 is a schematic diagram of an exposure calculation device to which the present invention is applied.

FIG. 13 is a schematic diagram of an exposure calculation device that performs parallel processing by a plurality of face extraction circuits.

FIG. 14 is a diagram showing a time chart of parallel processing.

FIG. 15 is a diagram showing details of step 172 in FIG. 8;

[Explanation of symbols]

 28 CCD image sensor 30 Amplifier 36 Face extraction circuit

──────────────────────────────────────────────────続 き Continued on front page (58) Field surveyed (Int.Cl. ⁶ , DB name) G03B 27/72-27/80

Claims (2)

(57) [Claims] 1. A color original image is divided into a large number of pixels, each pixel is separated into three colors of red light, green light and blue light, and photometry is performed. Based on data obtained by photometry, the color original image is displayed on the color original image. A color area with the same or similar hue is determined, a circle or an ellipse inscribed at the boundary of the determined color area is assumed, and the color area is determined by a circle or an ellipse in order from a circle or an ellipse with a large area And extracting data of the selected area as data of the face of a person by selecting at least one of the divided areas and extracting data of the face of the person. 2. A color original image is divided into a large number of pixels, each pixel is separated into three colors of red light, green light and blue light, and photometry is performed. Based on data obtained by photometry, the color original image is displayed on the color original image. hue determined by the same or similar color regions Rutotomoni, the
Determine the nucleus of the color region, assuming a circle or an oval inscribed in the boundary region of the color region , and determine a region of a circle or an oval having the largest area, and within the color region, the circle having the largest area Or oval
Region periphery seeking convex area above where the constant area that protrudes outwardly from the said color region excluding the contain and the nucleus of convex regions
Assume a circle or oval inscribed in the boundary area of
Is divided by the area of the largest circle or oval.
A method for extracting face data of a person, wherein at least one of the divided areas is selected and data of the selected area is extracted as face data of the person.