JPH06160993A - Method for extracting feature image data - Google Patents

Abstract

PURPOSE:To accurately and automatically extract only feature image data such as the data of the face of a person from the color original image of a negative film or the like. CONSTITUTION:The original image is divided into the plural pieces and the photometry thereof is executed. The noise of the data whose photometry is executed is eliminated and converted into a hue value H, a saturation value S and a lightness value L (100-102). The similar picture elements of the original image are integrated based on the distance of the HSL space of the respective values of H, S and L (104) and an area brought into contact with the outer frame of the original image is eliminated as for the integrated areas (106). Then, the candidate area is extracted from the almost central area of the left original image (108). Besides, it is judged whether the data of the candidate area is the face of a person or not and the photometry data of the area judged to be the face of the person is outputted (110).

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 characteristic image data, and more particularly to a characteristic image data such as density data of a person's face, which is used when a color original image is copied on a color copying material or black-and-white copying material. The present invention relates to a method of extracting image data.

[0002]

2. Description of the Related Art When viewing a portrait photograph, the most noticeable part is the person's face, and in order to create a high quality photograph, the person's face color should be adjusted appropriately. It is necessary to burn it in a different color.

Conventionally, a face area in an original image on a color film is designated by a light pen to extract density data of a person's face, and the color of the face is properly printed based on the extracted density data. The amount of exposure is determined. Examples of such a technique include JP-A-62-115430, JP-A-62-115431, and JP-A-62-1154.
32, JP-A-62-189456, JP-A-62-189457, and JP-A-63-138340.
JP-A-63-178222.

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

Therefore, a method of automatically extracting face data of a person can be considered. As an example of this, Japanese Patent Laid-Open No. 52-1
56624, JP-A-52-156625,
JP-A-53-12330, JP-A-53-1456
No. 20, JP-A-53-145621, and JP-A-53-145622 describe the following methods for extracting the face data of a person by extracting the skin color data. That is, the color original image is divided into a large number of photometric points, and each photometric point is divided into R (red), G (green), and B.
It is divided into three colors (blue) and photometry is performed, and it is determined whether the color of each photometry point calculated from the photometry data is within the skin color range. And
A cluster (group) of photometric points determined to be in the skin color range is used as face density data.

However, in this method, since the color within the skin color range is assumed to be the density data of the face, the parts other than the face having the skin color such as the ground, the trunk of the tree, and the clothes or the color close to the skin color of the face are also included. It is extracted as density data. Even if the same subject is shot under the same conditions, the tint of the shot image differs depending on the film type, and therefore the density data of the face may not be automatically extracted if the film type is different. Furthermore, when the color of the light source that illuminates the subject is different, the tint of the shot image is different (for example, the image shot with a fluorescent lamp as the light source is greenish), so if the light source color is different, the face density data May not be automatically extracted.

In order to solve the problem caused by the difference in the light source color, the light source color correction is performed and then the photometric data in the skin color range is extracted. As a light source,
It can be roughly classified into sunlight, fluorescent light, and tungsten light, but sunlight has different tints depending on the season and time zone, and even if the season and time zone are the same, the tint differs depending on whether it is direct light or indirect light. In addition, artificial light such as a fluorescent lamp has various colors with the diversification of products. Therefore, it is difficult to perform the light source correction by specifying the light source type for each of the light sources. Further, even if the light source correction is perfectly performed, it is not possible to prevent extraction of the skin color such as the ground or a tree trunk or a portion similar to the skin color. Can not.

The present invention has been made to solve the above problems, and it is possible to automatically extract only characteristic image data such as human face data from a color original image such as a negative film with high accuracy. An object of the present invention is to provide a feature image data extraction method that can be performed.

[0009]

In order to achieve the above object, the invention according to claim 1 divides a color original image into a large number of pixels and decomposes each pixel into three colors of red light, green light and blue light. The color original image is divided into color regions having the same or similar hue values based on the data obtained by the photometry, and the divided color regions are in contact with the outer edge of the color original image. At least one color area other than the color area is selected, and the data of the selected divided area is extracted as the characteristic image data.

According to the invention described in claim 2, the color original image is divided into a large number of pixels, each pixel is decomposed into three colors of red light, green light and blue light, and photometry is performed. The color original image is divided into color regions having the same or similar hue value and saturation value based on the above, and the color regions other than the color regions in contact with the outer edge of the color original image are divided. At least one color area is selected, and the data of the selected divided area is extracted as characteristic image data.

In each of the above inventions, when selecting an area, it is determined whether or not the divided area is a person's face, and the area determined to be the person's face is selected to obtain density data of the person's face. It can be extracted as characteristic image data.

[0012]

According to the first aspect of the invention, the color original image is divided into a large number of pixels, each pixel is decomposed into three colors of red light, green light and blue light, and photometry is performed, and the hue is calculated based on the data obtained by the photometry. The color original image is divided for each color region having the same or similar value. Therefore, one color area on the original color image includes pixels within a predetermined range having the same or similar hue values. The part of interest that represents the characteristics of the color original image is mainly near the center of the color original image. Therefore, for each divided color area of the color original image, except for the color areas that are in contact with the outer edge of the color original image. If at least one color area is selected from the color areas of, the data of the selected color area represents the characteristic image data. Therefore, by selecting a color area other than the color area in contact with the outer edge of the color original image, Characteristic image data can be extracted.

When there is a change in film type or light source type, a change over time, a difference in film development, etc., the tint of the original color image changes uniformly over the entire screen, but such a change in tint occurs over the entire screen. Therefore, the range of the color region in which the hue value of the color original image is the same or similar does not change even if the tint changes. Therefore, in the present invention, the data of the characteristic image can be extracted even if the tint of the color original image changes due to changes in film type and light source type, changes over time, differences in film development, and the like.

When the hue of the characteristic image, which is the characteristic portion of the image, is the same as or similar to the hues of other parts, if the color original image is divided based on the similarity of only the hue value, the characteristic image and other It may not be possible to distinguish it from the part. Therefore,
According to the second aspect of the invention, the saturation value is further introduced in addition to the hue value, and the color original image is divided for each color area having the same or similar hue value and saturation value. Characteristic image data is extracted by selecting at least one color region other than the color regions in contact with the outer edge of the color original image of the divided color regions. In the present invention, since the hue value and the saturation value are used, the characteristic image data can be extracted even if the characteristic image and the portion having the same or similar hue are mixed.

Since the face of a person is the most noticeable part when watching a portrait photograph, it is judged whether or not the divided area of the color original image is the person's face, and it is judged to be the person's face. It is preferable to extract the area data as the characteristic image data. For example, the hue of the face of an Asian person is similar to the skin color part of the ground, trees, etc., but in most cases the saturation is different, so the hue value or hue value that touches the outer edge of the color original image. If the data is extracted from the color area excluding the color areas having the same or similar saturation values, the image is in contact with the outer edge such as the background of the color original image even from the image in which the face, the ground, and the tree are mixed. It is possible to extract the face data of a person by excluding the ground, trees, and the like.

The data extracted as the characteristic image data may be data other than the face data of a person.

[0017]

Embodiments of the present invention will now be described 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 auto printer of this embodiment includes a conveyance roller 12 that conveys a color negative film 10. Below the color negative film 10 transported by the transport roller 12, the light source 1
4. A color correction filter 16 such as a light control filter and a diffusion box 18 are arranged in order. In addition, above the negative film 10, the light rays transmitted through the negative film 10 are
Distributing prisms 20 that distribute in directions are arranged.
A projection optical system 22, a black shutter 23 and a color paper (printing paper) 24 are sequentially arranged on one optical path distributed by the distribution prism 20, and a projection optical system 26 and a CCD image sensor are arranged on the other optical path. 28 are arranged in order. This CCD image sensor 28 is
One screen (one frame) of the negative film 10 is divided into a large number of pixels (for example, 256 × 256 pixels), and each pixel is R.
(Red), G (green), and B (blue) are separated into three colors for photometry. The CCD image sensor 28 is connected to a 3 × 3 matrix circuit 34 for sensitivity correction of the CCD image sensor via an amplifier 30 that amplifies 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 that stores a program of a routine described below, and at the same time, an average density of one entire screen is displayed. It is connected to an appropriate exposure amount calculation circuit 40 via an average density calculation circuit 38 for calculation. The appropriate exposure amount calculation circuit 40 is connected to the color correction filter 16 via a driver 42 that drives the color correction filter.

Next, the operation of this embodiment will be described. Light source 14
The light beam emitted from the laser beam passes through the color correction filter 16, the diffusion box 18, and the color negative film 10, is distributed by the distribution prism 20, and is received by the CCD image sensor 28 via the projection optical system 26. At this time, the black shirt 23 is closed. By this light reception, the CCD image sensor 28 divides the entire screen into a large number of pixels, decomposes each pixel into R, G, and B colors, and performs photometry, and outputs a photometric data signal. The photometric data signal is amplified by the amplifier 30 and then converted into a digital signal by the A / D converter 32, the sensitivity of the image sensor is corrected by the 3 × 3 matrix circuit 34, and the face extraction circuit 36 and the average density calculation circuit 38. Entered in. This average concentration calculation circuit 3
In 8, the average density of the entire one screen is calculated. The face extraction circuit 36 estimates the human face part in one screen as described below, and outputs R, G, B three-color photometric data of the part estimated to be the face. The exposure amount calculation circuit 40 calculates the exposure amount 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 the color correction filter 16 is calculated via the driver 42. Is controlled and the black shutter 23 is opened and closed for printing. When the average density calculated by the average density calculation circuit 38 is used, the exposure correction amount for the average density can be calculated. When the exposure correction amount is not calculated, the average density calculation circuit 38 is not necessarily required, and the exposure amount may be calculated directly from the three-color photometric data output from the face extraction circuit 36.

FIG. 2 shows a face extraction routine by the face extraction circuit 36. The noise removal, that is, smoothing, of the three-color photometric data input in step 100 is performed. In the next step 102, the R, G, and B three-color photometric data are converted into H (hue value) and L (L) according to the following equations (1) to (3).
(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 so that the minimum value is 0 and the maximum value is 1 as shown in the three-dimensional color coordinates in FIG.
Color photometric data, min () is the minimum value of the numerical values in (), r ', g', b'is r '= R / L, g' = G / L,
It represents b '= B / L. Further, H ′ is given by the following expression (4), and Pi (i is one of R, G, and B) is P in FIG.
Is.

[0021]

[Equation 1]

However,

[0023]

[Equation 2]

In step 104, for each pixel on the original image, as shown in FIG. 4 (2), a color space (hereinafter, referred to as a coordinate space) of a coordinate system composed of a hue value axis, a saturation value axis and a lightness value axis that are orthogonal to each other. Integration processing (details will be described later) is performed by the iterative area expansion method based on the distance V obtained in the HLS color space. In the next step 106, the area in contact with the outer edge of the original image is removed for each integrated area. In the next step 108, a region other than the removed region, that is, a region near the center of the original image, which is a feature image of a person's face candidate, is extracted. In the next step 110, the face area is estimated from the area extracted as the face candidate, and R, G, B three-color photometric data of the area estimated as the face is output. Then, in step 112, it is judged whether or not the printing of all the frames is completed, and when it is judged that the printing is completed, this routine is ended.

Next, details of steps 104 to 110 will be described. FIG. 5 shows details of step 104. In step 120, any one pixel Ji (i = 1 to n: total number of pixels) is selected from the original image by raster scanning or the like. For example, the pixel J ₁ shown in FIG.
Select. In the next step 121, it is determined whether or not the selected pixel is already included in the area to which the label described later is given. If affirmative, step 122
At, it is determined whether or not selection of all pixels of the original image is completed, and the process is repeated until selection of all pixels is completed.

When the selected pixel Ji is not included in the labeled area, the routine proceeds to step 123,
1 pixel around the selected pixel Ji (so-called 1 in 8 neighborhoods)
Pixel). For example, the pixel J shown in FIG.
Select ₂ . It is determined whether or not the selected pixel is included in the area to which any label is already given in step 1
24, and if negative, step 12
Go to 5. In step 125, the distance V in the HLS color space is calculated for these two selected pixels J ₁ and J _{2 based} on the following equation (5). That is, FIG.
As shown in (2), the pixel J ₁ in the HLS color space
The distance V between the point Z ₁ corresponding to the pixel Z ₂ and the point Z ₂ corresponding to the pixel J ₂ is obtained. This distance V represents the similarity of the lightness, saturation and hue of the _two pixels J ₁ and J ₂ . That is, if the distance V is long, the similarity is low, and if the distance V is short, the similarity is high.

[0027]

[Equation 3]

However, dH: the difference between the hue values of the pixels J ₁ and J ₂ .

DL: Difference in brightness value of pixels J ₁ and J ₂ . dS: Difference in saturation value between the pixels J ₁ and J ₂ .

In the next step 126, it is judged whether or not the two pixels are similar by judging whether or not the obtained distance V is less than the predetermined value θ, and if they are similar, step 127 is judged. In step 128, the same label is assigned to the two pixels (labeling).
Go to. On the other hand, if they are not similar, the process proceeds to step 128 without labeling.

In step 128, it is determined whether or not the above processing has been performed on all the pixels in the 8 neighborhoods, and if there are unprocessed pixels in the 8 neighborhoods, the process returns to step 123. When all the pixels in the vicinity of 8 are completed, the process proceeds to step 129, and the outermost one pixel of the region (in the original image) to which the same label is given is selected. Subsequently, in step 130, it is determined whether or not the selection of all the pixels on the outermost periphery has been completed, and in the case of a negative determination, the process returns to step 123 and the above process is executed again. If yes, return to step 120
The next pixel Ji is selected and the above process is repeated. In this way, by sequentially applying the same label to the peripheral pixels with high similarity from the outermost peripheral pixel of the area to which the same label is applied, the pixels with similar hue, brightness and saturation on the original image are An integrated process can be performed.

When the integration process for the screen of the original image is completed, an affirmative decision is made in step 122, and step 13
Go to 1. In step 131, the average value of the hue value, the saturation value, and the lightness value is obtained for the pixel groups to which the same label is given, and the obtained average value is used as the hue value, the saturation value, and the lightness value of each pixel. replace. Next Step 13
In step 2, the predetermined value θ used in step 126 is increased by the increment value θk and the process proceeds to step 133. The increment value θk corresponds to the degree of area expansion of the integration processing, and a predetermined value (for example, 1) is set. In step 133, step 131 and step 132
The number of repetitions of the integration process is determined by determining the number of times of execution (for example, 4 times). If the number is less than the predetermined number, all labels given in step 134 are released, and then the process returns to step 120. When the number of repetitions reaches the predetermined number, this routine is finished. In the example of FIG. 4 (1), after the completion of this routine, as shown in FIG. 12 (1), the labels A to G are added.

As described above, in step 104, since the adjacent pixels of the original image are integrated based on the similarity in hue, lightness, and saturation, the original image is classified into regions that are more visually sensible. You can

FIG. 6 shows the details of step 106 in FIG. 2. In step 136, one region on the original image of the pixel group labeled as described above is selected.

Here, as can be understood from the fact that the focusing position of the photographing device such as a camera is located at the substantially center, most of the characteristic images such as human faces in the original image are the central parts of the original image. Exists in. Therefore, the area of the image that is in contact with the outer edge (image frame) of the original image is not a characteristic image such as the background in most cases. Therefore, in the next step 137, it is determined whether or not the pixel included in the selected area is located at the outermost periphery of the original image to determine whether the selected area is in contact with the outer edge of the original image. To judge. When it is determined that the selected area is in contact with the outer edge of the original image, the selected area is removed in step 138 and then the process proceeds to step 139. In this step 138, the label of only the selected area is released, so that it can be treated equivalently to the removal of the area. On the other hand, when it is determined that they are not in contact with each other, the process directly proceeds to step 139.

In the next step 139, it is judged whether or not the above processing is completed for all the areas of the labeled pixel group in the original image, and if there is an unprocessed area, the process returns to step 136 and is repeated. Run. When the above processing is completed for all areas, this routine is completed. Therefore, after the end of this routine, the characteristic image, for example, the area including the face remains with high accuracy. Figure 4
In the example of (1), after the completion of this routine, the labels C and D remain as shown in FIG. 12 (2).

FIG. 7 shows the details of step 108 in FIG. 2. In step 140, the original image is divided into regions of the original image labeled as described above. Also,
Numbering is performed on each of the divided areas. In this case, the area in contact with the outer edge of the original image is removed.

At the next step 142, the small area is removed by judging the area of the divided area, and the numbering is performed again. In the next step 144, a contraction process for deleting all the boundary pixels of the region to remove one skin, and an expansion process for expanding the boundary pixels in the direction of the background pixels to enlarge the skin by one conversely to the contraction process are performed. It separates a small area that grows up from a large area. In the next step 146, small areas are removed and renumbering is performed in the same manner as in step 142, and in order to separate the weakly bonded areas in step 148, the same contraction and expansion processing is performed, In step 150, the small area is removed and renumbering is performed as described above. In the example of FIG. 4 (1),
After the end of this routine, as shown in FIG. 12C, the reference numerals 1 and 2 are numbered.

FIG. 8 shows the details of step 110. In step 162, one area is selected from the areas extracted in step 108, that is, the routine of FIG. 7, as the area of interest, and the horizontal fillet diameter of the area of interest is selected. And the size of the attention area is standardized by performing the enlargement / reduction processing of the attention area so that the vertical fillet diameter becomes a predetermined value.
The density value or the brightness value is standardized according to the following equation (6).

[0040]

[Equation 4]

Where dmax: maximum density value (or brightness value) in the area dmin: minimum density value (or brightness value) in the area ds: full-scale density value (or brightness value) of the image sensor d: density value before normalization (Or luminance value) dr: normalized density value (or luminance value)

In step 164, a plurality of types (10 types in this embodiment) of standard face images stored in advance (face image viewed from the front, face image viewed from the side (left and right), downward face image, upward face image) A correlation coefficient r of the attention area with respect to a face image or the like) is calculated by the following expression (7), and this correlation coefficient is used as a feature amount. In this standard face image, even if the data is only the outline of the face, the internal structure of the face (eye, nose,
Oral data) may be added.

[0043]

[Equation 5]

However,

[0045]

[Equation 6]

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

Then, in step 166, it is determined whether or not the region of interest is a human face by linear discriminant analysis using the above-mentioned characteristic amount as a variable, and R, G, B photometric data of the region determined to be a face. Is output to the proper exposure amount calculation circuit 40. In step 168, it is determined whether or not the determination as to whether the face is a face has been completed for all the extracted regions. If not, steps 162 to 168 are repeated.

In the above, the correlation coefficient is used as the feature amount used for determining whether or not the face is a person's face. However, the invariant derived from the normalized central moment around the center of gravity, the autocorrelation function, or Geometric invariants may be used.

The central moment μ _pq about the (p + q) th centroid of the image f (x, y) is

[0050]

[Equation 7]

However,

[0052]

[Equation 8]

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

[0054]

[Equation 9]

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

[0056]

[Equation 10]

Further, the autocorrelation function R _f is expressed as follows.

[0058]

[Equation 11]

Then, the geometric invariant feature amount is expressed by the following equation.

[0060]

[Equation 12]

By doing so, the background area in contact with the outer edge of the original image is removed, and the contour and the internal structure of the area are used for determination, so that the face, ground, and Face data can be extracted with high accuracy even from an image in which trees and the like are mixed.

It should be noted that it may be possible to additionally determine whether or not the area is within a predetermined skin color range in the determination as to whether or not the person is the face. That is, one area is selected from the areas extracted by the routine of FIG. 7 as the attention area, the average value of each of the hue value, the lightness value, and the saturation value of the attention area is calculated, and the obtained hue value and lightness value are calculated. It is determined whether each of the average value and the average value of the saturation value is included in a predetermined range indicating the skin color. If it is within the predetermined range indicating the skin color, it is estimated that the attention area is the person's face. In this case, it may be possible to determine whether or not there is a pixel included in the predetermined range without obtaining the average value of each of the hue value, the lightness value, and the saturation value of the attention area.

The appropriate exposure amount calculation circuit 40 is composed of the face extraction circuit 3
6. The R, G, B photometric data of the face area extracted as described above in 6 and the screen average density D _i of one frame calculated by the average density calculation circuit 38 (i = R, G, or B) ) And are used to calculate an appropriate exposure amount E _i according to the following equation, and output to the driver 42. The driver 42 controls the dimming filter 16 by calculating an exposure control value from the appropriate exposure amount E _i .

L _og E _i = LM _i · CS _i · (DN _i −D _i ) + PB _i + LB _i + MB _i + NB _i + K ₁ + K ₂ (8) However, each symbol represents the following.

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

CS: Color slope coefficient prepared for each type of negative, there are 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. Either underexposure or overexposure is selected.

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

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

LB: For standard print lens. It is a correction lens balance value, and is determined according to the type of printing lens.

MB: Correction value (master balance value) for variations in print light source and changes 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 formula.

[0073]

[Equation 13]

Here, K _a and K _b are constants, and FD is the face area average density. Further, the density correction amount K ₁ in the above equation (8) may be used as the correction value obtained by the film inspection apparatus, and the color correction amount K ₂ may be expressed using the face area average density as follows.

[0075]

[Equation 14]

However, K _c is a constant. Further, the density correction amount K ₁ and the color correction amount K ₂ in the above equation (8) are used as the correction amounts obtained by the film inspection device, and the average density D _i of the print frame in the equation (8) is the average density FD of the face area. _i
Alternatively, the exposure amount may be obtained instead.

In the present embodiment, since it is determined whether or not the area extracted after the background area in contact with the outer edge of the original image is removed is a human face, a face, a ground,
Face data can be extracted with high accuracy even from an image in which trees and the like are mixed.

For each of the candidate areas extracted in the above step 108, it is determined whether or not the attention area is a face based on the shape and color information of the attention area and the shape and color information of the neighboring area which is an area around the attention area. You can judge. That is, it has the same hue value, saturation value, or approximate hue value and saturation value as the area of interest around the area of interest, and has a size (for example, a horizontal fillet diameter or a vertical fillet diameter can be adopted). Is the size of the attention area, 25
It may be determined whether or not the region corresponding to the hand or foot of the person is extracted by determining whether or not the region in the range of 100% to 100% is extracted.

It is also possible to make the extracted area into a line figure and determine whether or not the attention area is a face based on the shape of the neighboring area and the shape of the attention area around the attention area. In this case, each area is converted into a line figure by performing line information extraction processing on the area extracted as described above. Here, it is determined whether or not the line figure representing the shoulder is present by comparing the standard line figure representing the shoulder of the person stored in advance with the line figure of one screen, and the line figure representing the shoulder is present. In this case, if there is a line figure on the upper side of the line figure, is this line figure used as the attention line figure, and is there a line figure representing the head (eg, hat, hair, helmet, etc.) above this attention line figure? to decide. Since the line drawing representing the head exists above the line drawing of interest and the line drawing representing the shoulder exists below the line of interest drawing, the line drawing of interest is highly likely to be a facial line drawing. Therefore, it is determined whether or not the contour of the line figure of interest approximates the contour of the standard line figure of the face. It is determined that the line-of-interest graphic is a face, and R, G, B photometric data of the area corresponding to the line-of-interest pattern is output. As described above, by determining whether or not the face is a face based on the shape of the attention area or the like, face data can be extracted from an image in which a face, a ground, a tree, and the like having similar hues are mixed. Further, since the face is not determined using the fine structure of the face, it is possible to determine whether or not the face is a small calculation time even if the resolution of the determination target image is low.

FIG. 9 shows a modification in which the present invention is applied to an exposure amount determining device separate from the printer or the printer processor. In addition, in FIG. 9, portions corresponding to those in FIG. Further, the average density calculation circuit 38 is not always necessary, but instead of this, an integrated transmission density detection circuit for detecting LATD of the entire screen may be used.

FIG. 10 shows the face extraction circuit of FIG.
Output circuit 36₁, 36₂・ ・ ・ Configured with 36n, parallel processing
Is used to calculate the exposure amount. Face extraction circuit 3
6₁, 36₂・ ・ ・ 36n is shown in the time chart of FIG.
Therefore, the image is read, the exposure amount is calculated, and the result is output.
To do. In FIG. 11, t₁Is the time to read the image of one frame,
t ₂Is the exposure amount calculation time for one frame, t₃Is the exposure of one frame
Calculation result transfer time, t₂>> t₁, T₃Is.
Face extraction circuit 36₁Is t₁Read one frame of image in time,
t₂The exposure amount is calculated by time, and t₃Transfer calculation result by time
To do. Face extraction circuit 36₁The image reading of one frame by
At the same time, the film is sent for one frame and the face extraction circuit 3
6₂One frame image reading is started by the face extraction circuit
36₁Exposure amount calculation and face extraction circuit 36₂Image reading
Are performed in parallel, and the face extraction circuit 36₃, 36
_Four... 36n is processed in parallel.

The time Tp required to process mxn frames in parallel is Tp = m (t ₁ + t ₂ + t ₃ ) + (n-1) t ₁ . On the other hand, the processing time Ts when parallel processing is not performed
Is Ts = m · n (t ₁ + t ₂ + t ₃ ). Therefore,

[0083]

[Equation 15]

Double speeding is possible. This parallel processing device can also be applied to the printer of FIG.

In addition to determining the exposure amount of the photographic printing apparatus, the present invention determines the exposure amount of the digital color printer, the copying condition of the copying machine, the exposure amount of the camera, the display condition of the CRT screen, and the hard copy from the magnetic image data. It can also be applied to the determination of the amount of light when creating.

In the above embodiment, the similarity of each pixel is judged by the distance in the color space based on the hue value, the saturation value and the lightness value, but the present invention is not limited to this color space, and the hue is not limited to this. You may make it judge the similarity of a value, the similarity of a hue value, and a saturation value.

For example, in order to obtain the similarity of the hue values, a histogram of the hue values of the color original image is obtained, and the obtained histogram is divided for each mountain with a valley or a skirt of the histogram as a boundary. , Determine the hue value range of each mountain. Next, by determining which hue value range the hue value of each pixel belongs to, it is determined which of the divided mountains each pixel belongs to, and a group (corresponding to a mountain in which a large number of pixels are divided ( Cluster). Then, the color original image is divided into areas corresponding to the divided groups. As a result, the color original image is divided into regions each including a pixel having a hue value within the hue value range divided by the histogram. Therefore, one area on the color original image includes pixels whose hue value is within a predetermined range, and the image features are extracted from the area other than the area in contact with the outer edge of the color original image as described above. By selecting at least one area to be represented, the area in which the data of the selected area includes the data of the characteristic image such as the face of the person can be selected.

To obtain the similarity between the hue value and the saturation value, a two-dimensional histogram of the hue value and the saturation value is obtained,
This two-dimensional histogram is divided for each mountain and the color original image is divided in the same manner as described above, and at least one area other than the area in contact with the outer edge of the color original image is selected from among the divided areas to obtain the data. Extract. The hue of a person's face is similar to the skin color part of the ground, trees, etc., but in most cases it has different saturation and is in contact with the outer edge of the original image. By extracting the data from the color area except for the areas having the same or similar hue value and saturation value, the data of the characteristic image such as the face of the person can be extracted.

[0089]

As described above, according to the present invention, the data is extracted from the color area other than the color area in contact with the outer edge of the original image based on the hue value. Can be extracted with high accuracy.

Further, since the data is extracted from the color area other than the color area in contact with the outer edge of the original image on the basis of the hue value and the saturation value, even if the areas having the same or similar hue values are mixed. The effect that the data of the characteristic image of the original image can be extracted with high accuracy is obtained.

[Brief description of drawings]

FIG. 1 is a schematic diagram showing a printer according to a first 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. 4 (1) is a diagram showing an original image. (2) is a diagram showing a color space whose axes are a lightness value, a hue value, and a saturation value.

5 is a flow chart showing details of step 104 of FIG. 2. FIG.

FIG. 6 is a flowchart showing details of step 106 of FIG.

FIG. 7 is a flowchart showing details of step 108 in FIG.

FIG. 8 is a flow chart showing details of step 110 of FIG.

FIG. 9 is a schematic diagram of an exposure amount calculation device to which the present invention is applied.

FIG. 10 is a schematic diagram of an exposure amount calculation device that performs parallel processing by a plurality of face extraction circuits.

FIG. 11 is a diagram showing a time chart of parallel processing.

FIG. 12 is an image diagram for explaining a process of extracting a face candidate area of an original image.

[Explanation of symbols]

 28 CCD image sensor 30 amplifier 36 face extraction circuit

Claims (3)

[Claims] 1. A color original image is divided into a large number of pixels, each pixel is decomposed into three colors of red light, green light and blue light and photometry is performed, and the color original image is hued based on data obtained by photometry. The selected division is performed by dividing each color area having the same or similar value, and selecting at least one color area of the divided color areas other than the color area in contact with the outer edge of the color original image. A method of extracting characteristic image data, which extracts the area data as characteristic image data. 2. A color original image is divided into a large number of pixels, each pixel is decomposed into three colors of red light, green light and blue light, and photometry is performed, and the color original image is hued based on the data obtained by the photometry. Values are divided into color areas having the same or similar saturation values, and at least one color area other than the color areas that are in contact with the outer edge of the color original image is selected. A method of extracting characteristic image data, which extracts the data of the selected divided area as characteristic image data. 3. The method of extracting characteristic image data according to claim 1, wherein, when selecting an area, it is determined whether or not the divided area is a person's face, and the area determined to be the person's face is selected. .