JPH09197575A - Exposure deciding method and exposure controller - Google Patents

Abstract

PROBLEM TO BE SOLVED: To efficiently obtain an exposure capable of appropriately printing a main object, irrespective of the image contents of an original image to be printed. SOLUTION: After photo-measuring the image recorded on a negative film and fetching in the image data (100 and 102), a face area extraction processing is executed (104), the degree of complexity C of the image is calculated, based on the number of extracted face areas and the variation of the size, etc., (106), the original image is classified into either of n classes 1 to n previously set in accordance with the complexity of the image constitution (108). An exposure operation expression is decided at every class so that the participation degree of the image characteristics of the face area extracted from the image to the decision of the exposure may become larger as the class of lower complexity and that the participation degree may become smaller as the class of higher complexity, the exposure amount operation expression corresponding to the previously classified class is taken in so as to calculate the exposure then, the image is printed (110 to 114).

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an exposure amount determining method and an exposure control apparatus, and more particularly, to an exposure amount determining method for determining an exposure amount so that an area corresponding to a main subject is appropriately printed. The present invention relates to an exposure control device to which a quantity determination method can be applied.

[0002]

2. Description of the Related Art An image recorded on a color negative film transmits R, G, and B component color lights as a whole screen, but the majority of images statistically have the transmission ratios of the component color lights substantially equal to each other. It is known to be a fixed percentage.
Therefore, in the photo printing apparatus, the exposure amount is generally determined based on the following equation (1).

LogEj = Sj. (DNj-Dj) + Kj (1) where logE is the logarithm of the exposure amount, K is a constant, D is the cumulative transmission density (LATD) of the image measured by the photometric system, and DN is the photoprint. The density of a reference image (so-called eyeball negative) for setting the condition of the apparatus, S is a slope coefficient, and j is one of R, G, and B. By using the above exposure amount calculation formula, it is possible to obtain an appropriate exposure amount capable of properly printing the face of a person as a main subject on a large number of images.

However, the above exposure amount calculation formula has an extremely high density over a wide area in the background portion such as an image photographed using a strobe or an image photographed in a backlit scene.
Or an image in which a low portion exists (an image in which so-called density ferria occurs), or an image in which a background is biased to a specific color over a wide area (a so-called color ferria occurs) Image) which is affected by the density and color of the background portion, and there is a problem in that it is not possible to obtain an appropriate exposure amount capable of properly printing the portion corresponding to the face of the person as the main subject.

Therefore, the exposure amount E obtained by the equation (1)
Is corrected according to various image feature amounts (for example, the maximum and minimum values of the density in the image, the average density of the central portion of the screen of the image, the average density of the peripheral portion of the screen, etc.), The integrated transmission density D is corrected according to the various image feature amounts to calculate the exposure amount E, but it is appropriate for an image in which the above-described density ferria or color ferria occurs. The reality is that the yield of such a large amount of exposure is not sufficient. To obtain an appropriate exposure amount for an image with density feria or color feria, ignore the density of the background part and determine the exposure amount so that the density of the face area corresponding to the human face becomes appropriate. There is a need to.

Therefore, as an example of the technique for extracting the face area from the image and determining the exposure amount based on the density of the extracted face area, Japanese Patent Laid-Open No. 52-156624 discloses two-dimensional or three-dimensional.
The measurement points included in a predetermined color area on the three-dimensional color coordinates are defined as skin colors, and when there are 13 or more measurement points determined to be skin colors, it is determined that there is a skin color in the image, and the skin color part A technique for determining the amount of exposure using the density of is described.

As another example of a technique for extracting a face area from an image, Japanese Patent Laid-Open No. 4-346332 discloses a color original image divided into a large number of pixels, and each pixel is divided into three colors for photometry. ,
A histogram of hue values (and saturation values) is obtained based on the data obtained by photometry, the obtained histogram is divided into mountains, and it is determined to which of the divided mountains each pixel belongs. Divided into groups corresponding to the divided mountains,
The color original image is divided into a plurality of regions for each group, a region corresponding to a human face as a main part of the plurality of regions is estimated, and the exposure amount is determined based on the estimated photometric data of the region. Is proposed.

[0008]

However, the various face area extraction methods proposed hitherto cannot reliably extract the area corresponding to the face of a person in the image. A region other than the inside face may be erroneously extracted as a face region. For this reason, a method in which the operator specifies the face area in the image to determine the exposure amount (for example, Japanese Patent Laid-Open No.
62-115430, etc.), there is a problem that the yield of obtaining an appropriate exposure amount is low.

That is, the various face area extraction methods proposed hitherto have a low face area extraction accuracy particularly for an image in which a large number of subjects are present. For example, in a portrait shot in the background of a town, As a near view, a person as a main subject and a bag carried by the person, such as several persons as a middle view, a car, a store, an article displayed in the store, a display, a roadside tree, a ground, etc. Images of many people, buildings, sky, ground, cars, street trees, signs, etc., or images of party scenes at home, with several people, a table as the foreground, and It is very difficult to extract only the face of a person as the main subject from images such as food, figurines, furniture around the table, and objects with wall decorations. It is likely to be extracted.

The present invention has been made in consideration of the above facts, and it is possible to obtain an exposure amount capable of properly printing a main subject with a high yield regardless of the image content of an original image to be printed. The purpose is to obtain a decision method.

It is another object of the present invention to provide an exposure control apparatus capable of printing an original image with a high probability so that the main subject is properly printed regardless of the image content of the original image to be printed. Is.

[0012]

As described above, the various face area extraction methods proposed hitherto have complicated images (i.e., backgrounds) in which an image in which a large number of subjects are present is present. An image of a region estimated to correspond to the face of a person extracted by applying the face region extraction method to an image having a complicated structure because the extraction accuracy for an image having a complicated structure is low) Even if the exposure amount is determined based on the characteristic amount, there is a high probability that an appropriate exposure amount cannot be obtained.

The inventor of the present application has found that an image having a complicated structure as described above has a small correction amount with respect to an exposure amount based on the average density of the image, and an image feature amount of an area estimated to correspond to a human face. It is more likely that an appropriate exposure amount will be obtained if the exposure amount is determined so that it is less involved in the determination of the exposure amount. Since the extraction accuracy of extracting a region estimated to correspond to a person's face is high and these images have a large correction amount, the image feature amount of the region estimated to correspond to a person's face is involved in determining the exposure amount. The inventors have come to the conclusion that it is more likely that an appropriate exposure amount will be obtained if the exposure amount is determined so that the degree to be performed becomes larger, and the present invention has been completed.

Therefore, in the exposure amount determining method according to the first aspect of the present invention, the complexity of the structure of the original image is judged, and the original image is extracted from the original image as the structure of the judged original image becomes lower. An image of a region estimated to correspond to the main subject extracted from the original image as the image feature amount of the region estimated to correspond to the main subject becomes more involved in determining the exposure amount and the complexity increases. The exposure amount of the original image is determined so that the feature amount is less involved in the determination of the exposure amount.

According to the first aspect of the present invention, when the complexity of the structure of the original image is determined and, for example, when the complexity of the structure of the original image is determined to be low, it is estimated that it corresponds to the main subject extracted from the original image. The exposure amount is determined so that the degree of the image feature amount of the region to be involved in determining the exposure amount increases,
For example, when it is determined that the complexity of the original image is low, the exposure is performed so that the image feature amount of the area estimated to correspond to the main subject extracted from the original image is less involved in determining the exposure amount. The amount will be determined.

As described above, according to the first aspect of the present invention, the complexity of the structure of the original image is determined, and the probability that an appropriate exposure amount can be obtained increases according to the determined level of complexity of the original image. , The exposure amount is determined by changing the degree to which the image feature amount of the area estimated to correspond to the main subject extracted from the original image is involved in the determination of the exposure amount. In other words, it is possible to obtain an exposure amount with which a main subject can be properly printed at a high rate.

In the exposure amount determining method according to the second aspect of the present invention, a plurality of classes are determined in advance according to the complexity of the image structure, and the less complex class corresponds to the main subject extracted from the image. The image feature amount of the estimated region is more involved in the determination of the exposure amount, and the image feature amount of the region estimated to correspond to the main subject extracted from the image in the higher complexity class determines the exposure amount. In order to reduce the degree of involvement in the, exposure amount calculation formula is determined in advance for each class, the complexity of the original image is determined, and the original image is classified into one of the plurality of classes,
The exposure amount of the original image is determined using the exposure amount arithmetic expression corresponding to the classified class.

According to the second aspect of the invention, the lower the complexity of the image structure, the greater the degree that the image feature amount of the area estimated to correspond to the main subject extracted from the image is involved in determining the exposure amount. The exposure calculation formula is set for each class so that the image feature amount of the area estimated to correspond to the main subject extracted from the image in the higher complexity class is less related to the determination of the exposure amount. Therefore, for example, if the original image has a low complexity,
The original image is classified into a class of low complexity of composition, the exposure amount is determined by using the exposure amount arithmetic expression corresponding to the classified class, and the exposure amount is estimated to correspond to the main subject extracted from the original image. The exposure amount is determined such that the degree that the image feature amount contributes to the determination of the exposure amount increases.

Further, for example, when the original image has a high complexity, the original image is classified into a class having a low complexity, and the exposure amount is calculated by using the exposure amount arithmetic expression corresponding to the classified class. Is determined, and the exposure amount is determined such that the degree that the image feature amount of the region estimated to correspond to the main subject extracted from the original image is less involved in the determination of the exposure amount.

As described above, according to the second aspect of the present invention, the original image is classified into any of a plurality of classes according to the complexity of the structure, and the appropriate exposure amount is determined according to the complexity of the classified class. In order to increase the probability that the exposure amount is obtained, the exposure amount is determined by changing the degree to which the image feature amount of the region estimated to correspond to the main subject extracted from the original image is involved in determining the exposure amount. It is possible to obtain an exposure amount with which a main subject can be properly printed at a high rate regardless of the image content of the original image to be printed.

In the exposure amount determining method according to the third aspect of the present invention, the image feature amount of the area estimated to correspond to the main subject extracted from the image as the complexity of the image structure becomes lower determines the exposure amount. As the degree of involvement increases and the complexity increases, the degree of involvement is reduced so that the image feature amount of the region estimated to correspond to the main subject extracted from the image becomes less involved in determining the exposure amount. Defines the exposure amount calculation formula represented by a function of the complexity of the image configuration, and determines the complexity of the configuration of the original image,
The exposure amount of the original image is determined by using the exposure amount calculation formula based on the determination result of the complexity of the configuration of the original image.

According to the third aspect of the invention, as the complexity of the image structure decreases, the image feature amount of the area estimated to correspond to the main subject extracted from the image becomes more and more involved in the determination of the exposure amount. As the complexity becomes higher, the degree of involvement becomes more complicated in the configuration of the image so that the degree of involvement in the image feature amount of the area estimated to correspond to the main subject extracted from the image becomes smaller in determining the exposure amount. Since the exposure amount calculation formula represented by the function of the original image is defined, for example, when the complexity of the original image is low, the image feature amount of the area estimated to correspond to the main subject extracted from the original image is The exposure amount is determined so that the degree of contribution to the determination of the exposure amount becomes large, and when the structure of the original image has a high complexity, it corresponds to the main subject extracted from the original image. Image feature amount of estimated area is the exposure amount as the degree to participate in the determination of exposure amount is reduced is determined.

As described above, also in the invention of claim 3,
The exposure amount is determined by the image feature amount of the area estimated to correspond to the main subject extracted from the original image so that the probability of obtaining an appropriate exposure amount increases depending on the complexity of the original image. The exposure amount is determined by changing the degree of involvement in, so regardless of the image content of the original image to be printed,
It is possible to obtain an exposure amount with which a main subject can be properly printed with a high yield.

The determination of the complexity of the structure of the original image in the invention of any one of claims 1 to 3 is performed by dividing the original image into a large number as described in claim 4, for example. It can be performed based on the photometric data obtained by photometry. Further, for example, as described in claim 5, it may be performed based on the information recorded by the camera that recorded the original image. In this case, the recording of information by the camera can be performed magnetically or optically on the medium on which the original image is recorded. In addition, the information recorded by the camera may include information indicating shooting conditions such as a shooting magnification when shooting and recording an original image and a distance to a main subject at the time of shooting.

According to a sixth aspect of the present invention, in an exposure control apparatus, for each of a plurality of classes determined in advance in accordance with the complexity of the image structure, the main subject extracted from the image is the less complex class. The image feature amount of the area estimated to correspond to the exposure degree becomes more involved in determining the exposure amount, and the image feature amount of the area estimated to correspond to the main subject extracted from the image is exposed in the higher complexity class. Storage means for storing the respective exposure amount calculation formulas that are determined so that the degree of involvement in the determination of the amount becomes small, and the photometric data or the original image obtained by dividing the original image into a large number and measuring the light Stored in the storage means and a classification means for judging the complexity of the composition of the original image based on the information recorded by the camera and classifying the original image into one of the plurality of classes. An exposure amount determining means for determining an exposure amount of an original image by using an exposure amount arithmetic expression corresponding to a class classified by the classifying means, and a copy material for a copy material based on the exposure amount determined by the exposure amount determining means. Exposure control means for controlling the exposure of the original image.

According to the sixth aspect of the invention, similarly to the second aspect, the original image is classified into any of a plurality of classes according to the complexity of the structure, and the classified classes are classified according to the level of complexity. In order to increase the probability that an appropriate exposure amount can be obtained, the degree to which the image feature amount of the area estimated to correspond to the main subject extracted from the original image is involved in the determination of the exposure amount is changed to change the exposure amount. Since it is determined, it is possible to obtain an exposure amount with which a main subject can be properly printed at a high rate regardless of the image content of the original image to be printed. The exposure control means controls the exposure of the original image on the copy material on the basis of the exposure amount determined by the exposure amount determining means. Therefore, regardless of the image content of the original image to be printed, the main subject has a high probability. The original image can be printed so that the image is printed properly.

In the exposure control apparatus according to the seventh aspect of the present invention, the image feature amount of the area estimated to correspond to the main subject extracted from the image is involved in determining the exposure amount as the complexity of the image becomes lower. The image feature amount of the region estimated to correspond to the main subject extracted from the image increases as the complexity increases, and the degree that the image feature amount of the region estimated to correspond to the determination of the exposure amount decreases in advance. Storage means for storing an exposure amount expression whose degree of involvement is expressed as a function of the complexity of the image structure, and photometric data obtained by dividing the original image into a large number and measuring the original image Determining means for determining the complexity of the structure of the original image based on the information recorded by the camera, and the dew stored in the storing means based on the determination result by the determining means. An exposure amount determining means for determining the exposure amount of the original image using the amount calculation formula, and an exposure control means for controlling the exposure of the original image on the copy material based on the exposure amount determined by the exposure amount determining means. It is configured to include.

According to the invention described in claim 7, as in the case of the above-mentioned claim 3, according to the complexity of the structure of the original image, the probability that an appropriate exposure amount can be obtained is increased from the original image. The exposure amount is determined by changing the degree that the image feature amount of the area estimated to correspond to the extracted main subject is involved in determining the exposure amount, so that the main subject is irrespective of the image content of the original image to be printed. It is possible to obtain an exposure amount that can be properly printed with a high yield. The exposure control means controls the exposure of the original image on the copy material on the basis of the exposure amount determined by the exposure amount determining means. Therefore, regardless of the image content of the original image to be printed, the main subject has a high probability. The original image can be printed so that the image is printed properly.

[0029]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below in detail with reference to the drawings.

[First Embodiment] FIG. 1 shows a photographic printing apparatus 10 as an exposure control apparatus of the present invention. The photo printing apparatus 10 includes a light source 16 that emits exposure light for printing an image recorded on the negative film 12. On the light emission side of the light source 16, a color correction filter 18 such as a light control filter, a diffusion box 20, a distribution prism 22.
Are arranged in order.

The conveying path of the negative film 12 as a photographic film is formed between the diffusion box 20 and the distribution prism 22, and the distribution prism 22 distributes the light transmitted through the negative film 12 in two directions. Conveying roller pairs 14A and 14B are provided on both sides of the optical axis of the light source 16 along the conveying path of the negative film 12. The conveying roller pairs 14A and 14B are connected to the drive shafts of the motors 52A and 52B, respectively, and are rotated by the driving force of the motors 52A and 52B being transmitted to convey the negative film 12.

A projection optical system 24, a black shutter 26, and a color paper (printing paper) 28 as a copying material are sequentially arranged on one optical path of the light distributed in two directions by the distribution prism 22. The projection optical system 30 and the CCD image sensor 32 are sequentially arranged on the other optical path. The CCD image sensor 32 divides the entire image (one frame) recorded on the negative film 12 into a large number of pixels (for example, 256 × 256 pixels), and
The light is separated into three colors (red), G (green), and B (blue) for photometry.

At the signal output end of the CCD image sensor 32, an amplifier 34 for amplifying the signal output from the CCD image sensor 32, an analog-digital (A / D) converter 36, and a sensitivity correction for the CCD image sensor 32 are provided. 3x
Three matrix circuits 38 are connected in order. The 3 × 3 matrix circuit 38 is connected to the input / output port 40D of the control unit 40 including a microcomputer and its peripheral devices. The control unit 40 includes a CPU 40A and a ROM
40B, RAM40C, and the input / output port 40D are provided, and these are mutually connected through the bus.

The color correction filter 18 is connected to the input / output port 40D of the control section 40 via the driver 46 for driving the color correction filter 18, and the drivers 50A, 5
Motors 52A and 52B are connected to each other via 0B. The input / output port 40D includes a display 42 including an LCD or a CRT, a keyboard 44 such as a numeric keypad for an operator to input various information, and a light source 16
The screen detection sensors 48 arranged on both sides of the optical axis of the negative film 12 for detecting the amount of transmitted light of the negative film 12 are connected.

Next, as an operation of the first embodiment, the photographic printing process according to the first embodiment will be described with reference to the flowchart of FIG. The processing shown in FIG. 2 is repeatedly executed by the control unit 40 when the printing of the image recorded on the negative film 12 onto the photographic printing paper 28 is instructed. In step 100, while the negative film 12 is being conveyed, the signal output from the screen detection sensor 48 is monitored to determine the position of the image recorded on the negative film 12, and when it is determined that the image has reached the exposure position, the negative film 1
The image is positioned at the exposure position by stopping the conveyance of No. 2.

In step 102, the image positioned at the exposure position is measured by the CCD image sensor 32, and C
The image data (photometric data according to claim 4) for each of R, G, and B output from the CD image sensor 32 through the amplifier 34, the A / D converter 36, and the 3 × 3 matrix circuit 38 is captured, and further, RAM40C for the captured image data
Etc. in the memory. In the next step 104, face area extraction processing for extracting an area (hereinafter referred to as a face area) estimated to correspond to the face of a person as the main subject of the present invention is performed.

As the face area extraction processing, various extraction methods conventionally proposed can be applied. As an example, the applicant of the present application has already filed Japanese Patent Application Nos. 6-265850 and 6-2665.
As proposed in No. 98, based on the image data, the shape pattern peculiar to each part of the person present in the image (for example, the outline of the head, the outline of the face, the internal structure of the face, the outline of the body, etc.) Any one of the expressed shape patterns) is searched, and the size and orientation of the detected shape pattern, and the positional relationship between the predetermined portion of the person represented by the detected shape pattern and the face of the person are calculated.
A region that is estimated to correspond to a person's face is set, other shape patterns different from the detected shape pattern are searched, the consistency of the previously set region as a human face is determined, and the face region is extracted. The extraction method can be applied.

At the next step 106, based on the feature amount related to the face area extracted by the face area extraction processing,
The complexity C of the structure of the previously positioned image is obtained. This processing is equivalent to determining the complexity of the structure of the original image. In addition, as the feature amount regarding the face area, for example, the number of extracted face areas, the size distribution of the extracted face areas (size variation degree), the average density distribution of each extracted face area (average density Any of the degree of variation) can be used, and, for example, the number of face areas, the size of the face areas, or the variance of the average density can be directly used as the value of the complexity C of the configuration.

In step 108, based on the value of the complexity C obtained in step 106, the previously positioned image is divided into n pieces of class 1 to class n which are predetermined according to the complexity of the image structure. Classify as one of the classes. In the first embodiment, the complexity of the structure of each image of class 1 to class n is set as class 1> class 2>...> class n, and the range of the value of the complexity C is different for each class. It is set. In the previous classification, the value of the complexity C is within the range of the value of the complexity C defined for each class.
It is performed by determining which class the range belongs to. The step 106 and the step 108 correspond to the classifying means described in claim 6.

At the next step 110, the exposure amount calculation formula corresponding to the classified class is fetched from the ROM 40B.
In the first embodiment, n exposure amount calculation formulas such as the following formula (2) are predetermined corresponding to each of the classes 1 to n, and the n exposure amount calculation formulas are It is stored in the ROM 40B corresponding to the storage means described in claim 6.

[0041]

[Equation 1]

However, E is the exposure amount, Df is the image feature amount of the face area (for example, face area density), and Dx is the other image feature amount. The other image feature amounts Dx include m types of image feature amounts Dx _i (where i = 1 to m), and specifically, for example, the maximum value, the minimum value, the intermediate value of the density, and the screen portion. The average density, the density value at the peak of the density histogram, the density value when the cumulative frequency from the maximum value or the minimum value of the density is a predetermined value, and the like can be applied. As is clear from the equation (2), the exposure amount calculation formula 1 to the exposure amount calculation formula n are
Both of the formulas represent the exposure amount E as a function of the image feature amount Df of the face area and the other image feature amount Dx, but as the complexity of the corresponding class decreases, the other image feature amount Dx The exposure amount calculation formula 1 to the exposure amount calculation formula n are determined so that the degree of influence on the determination of the exposure amount E becomes low.

It should be noted that the lower the complexity of the corresponding class is, the lower the degree that the other image feature amount Dx contributes to the determination of the exposure amount E is, for example, as the complexity becomes lower, the other image feature amount Dx is reduced. The number of types of the image feature amount Dx _i used as the amount Dx is reduced, or the number of image feature amounts having a weighting factor of 0 is increased among the various image feature amounts Dx _i forming the other image feature amounts Dx. Can be realized by As a result, as the complexity decreases, the degree that the image feature amount Df of the face area participates in the determination of the exposure amount E relatively increases, and as the complexity increases, the image feature amount Df of the face area increases. Will be less involved in the decision. Further, the value of the weighting coefficient by which the image feature amount Df of the face area is multiplied may be changed according to the level of complexity.

In step 112, the previous step 110
The exposure amount E is calculated by using the exposure amount calculation formula captured in step S3 and substituting the image feature amount Df of the face area and other image feature amounts Dx _i into the exposure amount calculation formula. The above step 110 and this step 112 correspond to the exposure amount determining means described in claim 6.

In the next step 114, the exposure amount E calculated above is output to the driver 46. As a result, the driver 46 moves the color correction filter 18 to the position corresponding to the input exposure amount E based on the input exposure amount E. The control unit 40 also opens the black shutter 26 for a predetermined time determined by the exposure amount E. This allows
The image positioned at the exposure position is printed on the photographic paper 28 with the exposure amount E.
Is burned on. This step 114 corresponds to the exposure control means of the present invention.

As described above, in the first embodiment, the complexity C of the image structure is obtained, and the image is classified into any of n classes 1 to n based on the value of the complexity C. The exposure amount E is calculated using the exposure amount calculation formula corresponding to the classified class.
Therefore, as the class into which the images are classified is a less complex class, the exposure amount that emphasizes the image feature amount of the face area is calculated, and the class into which the images are classified is a highly complex class. The higher the value, the more the exposure amount that does not give importance to the image feature amount of the face area is calculated. Therefore, regardless of the image content of the image to be printed (complexity of the configuration), it is possible to obtain an exposure amount that can properly print a main subject such as a person's face with a high yield, and with a high yield, an appropriate finish can be obtained. A photographic print is obtained.

It should be noted that in the above, as the feature quantity relating to the extracted face area, one of the number of the extracted face areas, the size of the extracted face area, or the distribution (the degree of variation) of the average density is used to construct the image. I was judging the complexity of
The present invention is not limited to this, and a plurality of feature amounts related to the face area may be combined to determine the complexity of the image configuration. In this case, the complexity of the configuration can be determined by using a map as shown in FIG. 3, for example.

In FIG. 3, as an example, the horizontal axis represents the number of extracted face areas, and the vertical axis represents the distribution (variation degree) of the extracted face area sizes or average densities. Each range is defined two-dimensionally. This makes it possible to determine the complexity of the image configuration based on the number of extracted face areas and the size or average density distribution of the extracted face areas. Note that when the number of extracted face areas is small, there is a high probability that an area corresponding to a person's face can be properly extracted by the face extraction processing. Therefore, in FIG. 3, when the number of extracted face areas is small, the size or Each area on the map is determined so that the complexity is determined to be relatively low even if the average density distribution (variation degree) is large.

In FIG. 3, if the number of regions determined to have the same complexity is equal to the number n of classes, the map shown in FIG. 3 is used to determine the image complexity and class 1 to class n. Classification into either can be performed simultaneously.

[Second Embodiment] Next, a second embodiment of the present invention will be described. Since the second embodiment has the same configuration as the first embodiment, the same reference numerals are given to the respective parts and the description of the configuration will be omitted. The operation of the second embodiment will be described below with reference to the flowchart of FIG. With reference to FIG. 5, the photoprinting process according to the second embodiment will be described only regarding the differences from the first embodiment.

In the second embodiment, the image recorded on the negative film 12 is positioned at the exposure position in step 100, and the image positioned at the exposure position is measured in step 102 to store the image data, and then step 103. Then, the complexity C of the image configuration is obtained based on the stored image data, and the previously positioned image is determined according to the complexity of the image configuration based on the value of the complexity C obtained in the next step 108. Are classified into any of the n classes of the predetermined classes 1 to n. This step 103,
Specifically, step 108 can be performed by applying one of the methods listed below, for example.

(Determination of Complexity Based on Color Distribution) As an example, color coordinates as shown in FIG. 5 (in FIG. 5, the color difference between R and G is plotted on the horizontal axis and the color difference between G and B is plotted on the vertical axis). Coordinates are shown as an example), two axes 60A and 60B that intersect the coordinate axes at the origin of the color coordinates and divide each of the first to fourth quadrants of the color coordinates into two areas are set. 3 concentric circles 62 with different radii centered on the origin of
By setting A, 62B, and 62C, the area around the origin of the color coordinates is divided into a total of 24 areas of 8 colors × 3 types of saturation. Next, R of each pixel represented by the image data,
Based on the density values of G and B, the color of each pixel in the image is plotted on the color coordinates, and the number of regions in which one or more points are plotted in the 24 regions is counted. To do.

In this case, if the value of the complexity C is relatively high, it can be estimated that there are many kinds of color pixels in the image, and many objects are present in the image. It can be judged that the complexity of the configuration is high. On the other hand, the complexity C
If the value of is relatively low, the number of types of colors existing in the image is small, and it is unlikely that there are many subjects in the image, so it can be determined that the complexity of the image configuration is low. . Therefore, for example, the image is classified into one of Class 1 to Class n based on the value of the complexity C.

In the above, the complexity is determined by excluding the color having the saturation equal to or higher than the predetermined value (the color plotted outside the circle 62C in FIG. 5), but the area outside the circle 62C is also determined. By making the object of counting, the complexity may be determined by using the data of the color with high saturation.
However, the presence of a large number of high-saturation color subjects in the image generally does not easily cause a decrease in the face area extraction performance in the face extraction processing. Considering that the purpose of the complexity determination is to detect an image with low face area extraction performance by the face extraction processing, it is desirable to determine the complexity by excluding color data of high saturation.

(Determination of Complexity Based on Density Difference between Pixels)
Based on the density value of each pixel represented by the image data, the density difference between adjacent pixels in the image is sequentially calculated for each pixel on the line along a predetermined line. As shown in FIG. 6 (A), in the image having a low complexity of composition, the change in the density difference along the line is relatively smooth, and there are few places where the value greatly changes. In an image with a high degree of complexity, as shown in FIG. 6B, the density difference is large and complicatedly changes along the line.

Therefore, according to the above-mentioned calculation result of the density difference, whether the change of the density difference is close to the change shown in FIG.
A feature amount for identifying whether the change is close to the change shown in FIG. 6B (for example, variance of density difference, value obtained by integrating absolute values of density difference along the line, and difference obtained by differentiating the density difference along the line). A value obtained by integrating the absolute values of the obtained differential values along the line, a value obtained by counting along the line the number of locations where the sign of the differential value has changed, etc.) are obtained. The above-described processing is performed for all lines in the image or a plurality of lines selected at predetermined intervals, and the feature amount obtained for each line is integrated (for example, average value, integrated value, etc. are obtained) to obtain the complexity C. . Then, based on the value of the complexity C, the images are classified into classes 1 to n.
It is classified as one of.

(Determination of Complexity Based on Background Difference Extracted from Density Difference and Color Difference between Pixels) Based on the density values of R, G, and B of each pixel represented by image data, the density difference between adjacent pixels is obtained. The color difference is calculated, and when the density difference and the color difference are less than a predetermined value, it is determined that the similarity with the pixel is high, and the above process is repeated for the pixel adjacent to the pixel to repeat the density difference. If the color difference is equal to or larger than a predetermined value, it is determined that the similarity between adjacent pixels is low, and the processing is terminated, as shown in FIG. 7, in order from the peripheral portion of the image toward the central portion of the image. To do. The above determination is performed for at least two of the four directions shown by the arrows in FIG. 7, and preferably for all of the four directions. Then, the region that is in contact with the peripheral portion of the image and that is composed of pixels determined to have high similarity is extracted as the background portion corresponding to the background of the image.

The above determination is performed from the peripheral portion of the image toward the central portion based on the empirical rule that the peripheral portion of the image is likely to be a region corresponding to the background of the image. If the area of the background portion determined as described above is narrow, it is likely that the configuration of the portion corresponding to the background is a complicated image, and if the area of the background portion is large, the configuration of the portion corresponding to the background is Since it is highly likely that the image is a monotonous image, the area of the background portion extracted as the complexity C is obtained, and the image is classified into one of the classes 1 to n based on the value of the complexity C.

(Determination of Complexity Based on Image Division) Based on the R, G, and B density values of each pixel represented by the image data,
Divide the image into regions. In dividing an image, a histogram of hue values (and saturation values) is obtained based on the image data, the obtained histogram is divided into mountains, and it is determined which of the divided mountains each pixel belongs to. It is possible to apply so-called cluster analysis, in which each pixel is divided into groups corresponding to the divided mountains and the image is divided into a plurality of regions for each group. Alternatively, an edge (contour line) in the image may be detected by differentiating the density value and the image may be divided into a plurality of regions based on the detected contour line. Further, the determination described in the background extraction may be executed over the entire image, and the image may be divided into a plurality of regions including only pixels determined to have high similarity based on the determination result. Good.

When the number of regions obtained by the division as described above is large, or when the area of each region obtained by the division is small, the image is likely to have a simple structure, and the number of the regions is high. If the number is small or the area of each region is large, there is a high possibility that the image has a complicated configuration. Therefore, the value of the complexity C is determined based on the number of regions obtained by the division, the average value of the areas of the regions, and the like, and the image is classified into one of Class 1 to Class n based on the value of the complexity C. Classify into.

Instead of setting the value of the complexity C, the map shown in FIG. 3 may be used to determine the complexity of the image structure and classify it into one of the classes. Further, in the above image division, for example, with respect to an image in the background of the sky in which clouds are floating, there is a possibility that an area corresponding to the sky may be divided into a plurality of areas. For this reason, after performing the above image division, it is preferable to compare the average densities, colors, etc. of adjacent areas, and if there are areas with similar average densities, colors, etc., it is preferable to integrate them. .

(Determination of Complexity Based on Histogram Shape) A histogram of the density value of each pixel is obtained based on the density value of each pixel represented by the image data. In an image having a low configuration complexity, as shown in FIG. 8A, the density histogram has a shape with a small number of peaks and valleys, and the height (frequency) at the peak of the peak is high. On the other hand, in an image with a high degree of complexity in the structure, the density histogram has a shape with many peaks and troughs, as shown in FIG.
Moreover, the height at the peak of each mountain is low.

Therefore, from the obtained density histogram,
A feature amount for identifying whether the shape of the density histogram is close to the shape shown in FIG. 8A or the shape shown in FIG. 8B (for example, the number of peaks and valleys, the peak height of each peak). The average value (i.e., the average value) is defined as the complexity C. And
The image is classified into one of Class 1 to Class n based on the value of the complexity C. Instead of the density histogram described above, for example, a histogram of color difference between each pixel and an adjacent pixel may be used.

Incidentally, the above-mentioned step 103, step 1
08 is not limited to applying any of the above-described methods, and combines the above-described complexity determination methods, for example, a two-dimensional map as shown in FIG.
Using a multidimensional map of dimension or more, or determining the complexity of an image using a functional expression or the like including at least one feature amount among various feature amounts for determining the complexity described above, The images may be classified.

When the image classification in step 108 is completed, in the next step 110, the exposure amount arithmetic expression corresponding to the classified class is fetched from the ROM 40B, and step 11
In step 1, the face area extracting process is performed in the same manner as step 104 in the flowchart of FIG. 2 described in the first embodiment. Then, in the next step 112, the exposure amount arithmetic expression fetched in the previous step 110 is used, and the image characteristic amount Df of the face region and other image characteristic amounts Dx and the like are substituted into the exposure amount arithmetic expression to obtain the exposure amount E. Is calculated, and in step 114, the image is printed on the photographic printing paper 28 in the same manner as in the first embodiment in accordance with the calculated exposure amount E, and the process is ended.

As described above, in the second embodiment as well, as in the first embodiment, images are classified into classes 1 to 1 based on the value of the complexity C.
Since the exposure amount E is calculated by classifying into any of n classes of the class n and using the exposure amount calculation formula corresponding to the classified class, the class into which the image is classified is a class with low complexity. The exposure amount that emphasizes the image feature amount of the face area is calculated as much as possible, and the exposure amount that does not emphasize the image feature amount of the face area is calculated as the class into which the images are classified has higher complexity. become. Therefore, regardless of the image content of the image to be printed (complexity of the configuration), it is possible to obtain an exposure amount that can properly print a main subject such as a person's face with a high yield, and with a high yield, an appropriate finish can be obtained. A photographic print is obtained.

Further, the face area extracting process is generally a complicated process requiring a long processing time, but in the second embodiment, since the complexity C is obtained based on the image data,
The exposure amount arithmetic expression corresponding to the class classified by the complexity C is an arithmetic expression for obtaining the exposure amount without using the result of the face area extraction processing (for example, the weighting coefficient for the image characteristic amount Df of the face area is 0). If it is an arithmetic expression), the face area extraction processing in step 111 may be omitted. In this case, the average processing time per image can be shortened as compared with the first embodiment, and the photo printing apparatus 10 can be used.
Can be improved.

[Third Embodiment] Next, a third embodiment of the present invention will be described. Since the third embodiment has the same configuration as the first and second embodiments, the same reference numerals are given to the respective parts and the description of the configuration will be omitted. Hereinafter, the operation of the third embodiment will be described. As a first example, referring to the flowchart of FIG. 9, the first is the photoprinting process according to the third embodiment.
Only parts different from the embodiment will be described.

In the third embodiment, similarly to the first embodiment, the image recorded on the negative film 12 is positioned at the exposure position in step 100, and the image positioned at the exposure position is measured in step 102. The image data is stored, the face area extraction processing is performed in step 104, and the complexity C of the image configuration is calculated based on the feature amount related to the face area in step 106 (this step 106 is performed by the determination unit according to claim 7). After that, the next step 1
09, the RO as the storage means according to claim 7.
The exposure amount calculation formula (refer to the following formula (3)) stored in advance in M40B is taken in.

E = f (g (C) · Df, ΣK _i · Dx _i ) ... (3) where g (C) is a weighting function of the image feature amount Df of the face area,
K _i is a weighting coefficient (constant) of the other image feature amount Dx _i . The value of the weighting function g (C) becomes smaller (the weight of the image feature amount Df of the face area is smaller) as the complexity of the image represented by the complexity C becomes higher, and the weighting function g (C) becomes It is a monotone function in which the value increases as the complexity decreases (the weight of the image feature amount Df of the face area increases), and an arbitrary monotone function with which the appropriate exposure amount yield is equal to or higher than a predetermined value may be applied. it can.

In the equation (3), the exposure amount E is the weighting function g
Image feature amount D of the face area weighted by (C)
f and a plurality of other image feature amounts Dx _i weighted by the weighting factor K _i are expressed as a function, and thus the degree to which the image feature amount Df of the face area is involved in determining the exposure amount E is It changes depending on the value of the weighting function g (C), and as the complexity of the image increases, the degree that the image feature amount Df of the face area is less involved in determining the exposure amount E decreases, and the complexity of the image decreases. The degree that the image feature amount Df of the area is involved in determining the exposure amount E becomes large.

At the next step 113, the complexity C, the image feature amount Df of the face area,
The exposure amount E is calculated by substituting the other image feature amounts Dx and the like. The steps 109 and 113 correspond to the exposure amount determining means described in claim 7. Then, in step 114, according to the calculated exposure amount E, the image is printed on the photographic printing paper 28 in the same manner as in the first embodiment, and the process is ended.

As described above, in the third embodiment, the exposure amount is calculated by using the exposure amount arithmetic expression in which the degree of the image feature amount Df of the face area involved in the determination of the exposure amount is represented by the function of the complexity C. Since the calculation is performed, as the complexity of the structure of the image represented by the complexity C becomes lower, the exposure amount that emphasizes the image feature amount of the face area is calculated, and the complexity of the structure of the image represented by the complexity C becomes higher. As a result, the degree of emphasis on the image feature amount of the face area is lowered, and the exposure amount is calculated. Therefore, regardless of the image content of the image to be printed (complexity of the configuration), it is possible to obtain an exposure amount that can properly print a main subject such as a person's face with a high yield, and with a high yield, an appropriate finish can be obtained. A photographic print is obtained. Further, unlike the first and second embodiments, there is no need to perform a process of classifying an image into any of a plurality of predetermined classes.

In the third embodiment, an example has been described in which the complexity C is obtained based on the feature amount of the face area extracted by the face area extraction processing, but the present invention is not limited to this. Needless to say, the complexity C may be obtained based on the image data as described in the second embodiment.

[Fourth Embodiment] Next, a fourth embodiment of the present invention will be described. In the following, the same parts as those in the first embodiment will be designated by the same reference numerals, and the description thereof will be omitted.

Photographic printing apparatus 60 according to the fourth embodiment.
In FIG. 10, a negative film 12 having a transparent magnetic recording layer formed by coating a transparent magnetic material on the surface opposite to the surface on which the emulsion layer is formed is set. In the negative film 12, recording tracks for recording information are formed along the longitudinal direction of the negative film 12 outside the range where an image is recorded by the camera. The negative film 12 is loaded into a camera having a function of recording various kinds of information on the recording track, and an image is photographed / recorded, and each time the image is photographed / recorded, the negative film 12 is recorded by the camera.
Various information including information indicating photographing conditions such as a photographing magnification of a photographed and recorded image and a distance to a main subject measured at the time of photographing is magnetically recorded on the recording track.

The photoprinting device 60 includes a screen detection sensor 48.
A magnetic head 62 corresponding to the recording track of the negative film 12 is provided between the recording medium and the conveying roller pair 14B. The recording head 62 is connected to the input / output port 40D of the control unit 40 via an amplifier 64 and an A / D converter 66. The various information including the information indicating the photographing conditions recorded on the recording track of the negative film 12 is the negative film 1
When being conveyed, the magnetic head 62 reads the data, the amplifier 64 amplifies the data, the A / D converter 66 converts the data into digital data, and the digital data is input to the control unit 40.

Next, the operation of the fourth embodiment will be described with reference to the flowchart of FIG. In step 101, the negative film 12 is conveyed, the information recorded on the recording track of the negative film 12 is read by the magnetic head 62 and stored in the RAM 40C or the like, and the signal output from the screen detection sensor 48 is monitored. The position of the image recorded on the film 12 is judged, and when it is judged that the image has reached the exposure position, the conveyance of the negative film 12 is stopped to position the image at the exposure position.

After the image positioned at the exposure position is measured in the next step 102 and the image data is stored,
In step 105, the photographing condition of the image is determined based on the information indicating the photographing condition of the image positioned at the exposure position among the various information read from the recording track of the negative film 12 and stored in the RAM 40C, and the determined photographing condition The image complexity C is calculated based on This step 105 corresponds to the complexity determination described in claim 5. The determination of the complexity C based on the shooting condition can be performed, for example, as follows.

That is, when the photographing magnification at the time of photographing is large, the size of the main subject existing in the image is large,
It is highly possible that the area corresponding to the background in the image is small. This is also the case when the distance to the main subject at the time of shooting is short. Therefore, in the above case, it can be determined that the complexity of the image structure is low, and therefore the value of the complexity C is set to a relatively small value. On the other hand, when the shooting magnification at the time of shooting is small, the size of the main subject existing in the image is small, and the area of the portion corresponding to the background in the image is likely to be large. This also applies when the distance to the main subject at the time of shooting is long. Therefore, in the above case, it can be determined that the complexity of the image structure is high, and therefore the value of the complexity C is set to a relatively large value.

The photographing conditions for determining the complexity are not limited to the above, and may include, for example, information indicating the presence or absence of strobe light emission and information indicating the brightness of the subject. For example, under a shooting condition such as when the brightness of the subject is low and the flash was used to shoot at a high shooting magnification, the resulting negative image has a dark background, so the area of the unexposed areas in the image is large, and the image is present in the image. Since the size of the main subject is large, it can be judged that the complexity of the image structure is low.

When the complexity C is calculated as described above,
In the next step 108, the image is classified into one of class 1 to class n based on the value of the complexity C, and step 110
The exposure amount arithmetic expression corresponding to the class classified in step 3 is taken in, and face area extraction processing is performed in step 111. Further, in step 112, the exposure amount E is calculated by substituting the complexity C, the image feature amount Df of the face area, the other image feature amount Dx, and the like into the exposure amount calculation formula captured in step 110, and the calculation is performed in step 114. The image is printed on the photographic printing paper 28 according to the exposure amount E, and the process is completed.

In the fourth embodiment, the case where the complexity is judged by reading the information magnetically recorded on the negative film 12 by the camera has been described. However, the present invention is not limited to this and, for example, by the camera. The information may be optically recorded in the form of a barcode or the like, and the information may be optically read to determine the complexity. Further, in the fourth embodiment, the image is classified into any one of class 1 to class n,
Although the exposure amount is calculated using the exposure amount calculation formula corresponding to the classified class, instead of this, as described in the third embodiment, the image feature amount Df of the face area determines the exposure amount. The exposure amount may be calculated by using an exposure amount calculation formula whose degree of involvement is represented by a function of the complexity C.

The feature quantity for determining the complexity of the image structure is not limited to the feature quantity described in each of the above embodiments, and the present invention relates to the complexity of the image structure. It goes without saying that various types of feature amounts that can be applied are applicable. In addition, a rule for evaluating complexity is determined in advance from various feature amounts used to obtain the value of the complexity C, and the complexity is determined by a known fuzzy inference using the rule. May be.

Further, in the above, as the face area extraction processing, the extraction method of searching the shape pattern peculiar to each part of the person and extracting the face area has been described as an example, but the present invention is not limited to this. , For example, the applicant of the present application has disclosed that
24, JP-A-52-156625, JP-A-53-12330, JP-A-53-145620, JP-A-53-145621, JP-A-53-145622, etc. As suggested,
It is determined whether the color of each pixel is included in the skin color range on the color coordinates based on the image data, and the area where the cluster (group) of measurement points that is determined to be within the skin color range exists An extraction method of extracting as a region may be applied.

Further, as proposed by the applicant of the present application in Japanese Patent Laid-Open No. 4-346333, etc., a histogram of hue values (and saturation values) is obtained based on the image data, and the obtained histogram is obtained for each mountain. The measurement points are divided into groups corresponding to the divided mountains by determining which of the divided mountains each measurement point belongs to, the image is divided into a plurality of regions for each group, and An extraction method may be applied in which an area corresponding to a person's face is estimated from the areas and the estimated area is extracted as a face area.

Further, in the above, the region estimated to correspond to the person's face is extracted as the region estimated to correspond to the main subject, but the present invention is not limited to this, and the background in the image is not limited to this. It is also possible to determine an area (background area) that is estimated to correspond to (1) and extract an area other than the background area as an area that is estimated to correspond to the main subject. Specifically, the color of each pixel based on the image data is included within the range of a specific color that clearly belongs to the background in color coordinates (for example, blue of the sky or sea, green of grass or trees, etc.). It is determined whether or not there is a cluster (group) of pixels that is determined to be within the specific color range, the region is determined to be a background region, and the remaining region is removed, and the remaining region is a non-background region (corresponding to the main subject. (Estimated region).

Further, as proposed by the applicant of the present invention in Japanese Patent Application No. 6-265850 and Japanese Patent Application No. 6-266598, after dividing an image into a plurality of areas in the same manner as described above, A feature amount as a region corresponding to the background (ratio of straight line portions included in contour, line symmetry, number of irregularities, contact rate with outer edge of image, density contrast in area, presence / absence of density change pattern in area, etc.) ), Determine whether or not each area is a background area based on the obtained feature amount, remove the area determined to be the background portion, and set the remaining area as a non-background area (area estimated to correspond to the main subject). You may make it extract.

Furthermore, in the first, second, and fourth embodiments, the image is classified into any of the classes 1 to n, and the exposure amount is calculated using the exposure amount calculation formula corresponding to the classified class. In the third embodiment, the description has been given of the aspects in which the exposure amount is calculated using the exposure amount calculation formula in which the degree of the image feature amount Df of the face area involved in the determination of the exposure amount is expressed by the function of the complexity C. , A single arithmetic expression is used as the exposure arithmetic expression, and the values of various coefficients and constants included in the arithmetic expression are equivalent to the main subject extracted from the image as the complexity of the image becomes lower. Then, the degree of the image feature amount of the estimated region involved in determining the exposure amount increases, and the image feature amount of the region estimated to correspond to the main subject extracted from the image increases as the complexity of the image configuration increases. When determining the amount of exposure As the degree of decrease of, depending on the complexity of the image of the configuration is stored in the form of a table or the like predetermined plurality of types, in determining the amount of exposure,
The exposure amount may be determined by taking in the values of the various coefficients and constants corresponding to the determined complexity of the image structure and substituting the taken in values of the coefficients and constants into the exposure amount calculation formula.
Claim 1 of the present invention also includes the embodiment as described above.

Further, in the above-described embodiment, the aspect in which the complexity of the image structure is automatically determined on the side of the photo printing apparatus has been described. However, the operator examines the image to determine the complexity of the image structure, The judgment result is inputted through an input means such as a ten-key pad or a touch panel, and on the side of the photo printing apparatus, according to the judgment result of the complexity of the image inputted through the input means, it corresponds to the main subject extracted from the image. The exposure amount of the image may be determined by changing the degree that the image feature amount of the estimated region is involved in the determination of the exposure amount. The operator may determine the complexity of the image configuration when the image is printed by the photo printing device, or may be performed in a verification process performed by using a verification machine before the image printing. .. When the operator determines the complexity of the image configuration in the verification step, the determination result input by the operator is stored in the memory card or the recording track formed on the negative film 12 described in the fourth embodiment. It can be transmitted to the photo printing apparatus via a medium or online. Claim 1 of the present invention
Includes the embodiments as described above.

[0091]

As described above, according to the first aspect of the invention, as the complexity of the determined original image becomes lower, the image feature amount of the area estimated to correspond to the main subject extracted from the original image. Is more involved in determining the exposure amount, and as the complexity is higher, the image feature amount of the region estimated to correspond to the main subject extracted from the image is less involved in determining the exposure amount. As I decided to determine the exposure amount of the original image,
It has an excellent effect that an exposure amount capable of properly printing a main subject can be obtained at a high rate regardless of the image content of the original image to be printed.

According to the second aspect of the present invention, the lower the complexity of the image structure is, the greater the degree that the image feature amount of the region estimated to correspond to the main subject extracted from the image is related to the determination of the exposure amount. , The exposure calculation formula is determined in advance for each class so that the degree of involvement becomes smaller in a class having a higher image structure complexity, and a plurality of original images are determined by determining the complexity of the original image structure. The exposure amount of the original image is determined by using the exposure amount calculation formula corresponding to the classified class, so that the main subject is irrespective of the image content of the original image to be printed. It has an excellent effect that an exposure amount that can be properly printed can be obtained with a high yield.

According to the third aspect of the invention, as the complexity of the image becomes lower, the image feature amount of the area estimated to correspond to the main subject extracted from the image becomes more and more involved in the determination of the exposure amount. , So that the degree of involvement becomes smaller as the complexity becomes higher, the exposure amount arithmetic expression in which the degree of involvement is expressed by a function of the complexity of the image configuration is defined, and the complexity of the configuration of the original image is set. The exposure amount of the original image is determined using the exposure amount calculation formula based on the determination result of the complexity of the original image configuration, regardless of the image content of the original image to be printed. It has an excellent effect that an exposure amount capable of properly printing a main subject can be obtained at a high rate.

According to the sixth aspect of the invention, the image feature amount of the region estimated to correspond to the main subject extracted from the image has a greater degree of contribution to the determination of the exposure amount in a class having a lower complexity of the image structure. , The exposure calculation formulas defined for each class are stored so that the degree of involvement becomes smaller in a class with higher complexity, and a plurality of original images are determined by determining the complexity of the structure of the original image. The exposure amount of the original image is determined by using the exposure amount calculation formula corresponding to the classified class, and the exposure of the original image to the copy material is controlled based on the determined exposure amount. Therefore, regardless of the image content of the original image to be printed, the original image can be printed with a high probability so that the main subject is appropriately printed.

According to the seventh aspect of the invention, as the complexity of the image structure becomes lower, the degree of the image feature amount of the region estimated to correspond to the main subject extracted from the image, to be involved in the determination of the exposure amount becomes larger. A predetermined exposure amount calculation formula is stored such that the degree of involvement decreases as the complexity increases, and the degree of involvement represented by a function of the complexity of the image configuration is stored. The complexity of the image structure is determined, the exposure amount of the original image is determined based on the determination result using the exposure amount calculation formula, and the exposure of the original image to the copy material is controlled based on the determined exposure amount. Therefore, regardless of the image content of the original image to be printed, the original image can be printed with high probability so that the main subject is printed properly.

[Brief description of drawings]

FIG. 1 is a schematic configuration diagram of a photographic printing apparatus according to a first embodiment.

FIG. 2 is a flowchart showing a photo printing process according to the first embodiment.

FIG. 3 is the number of face areas extracted by face area extraction processing,
It is a conceptual diagram which shows an example of the map used when determining the complexity of the structure of an image based on the size of this face area, or distribution of average density.

FIG. 4 is a flowchart showing a photo printing process according to a second embodiment.

FIG. 5 is a diagram illustrating an example of color coordinates used to determine the complexity of the configuration of an image based on the color distribution of the image.

6A is an example of a result of sequentially calculating the density difference between adjacent pixels on a predetermined line for an image having a low configuration complexity, and FIG. 6B is an example of an image having a high configuration complexity. FIG. FIG.

FIG. 7 is a conceptual diagram showing a direction in which a background area determination process is performed when a background area is extracted to determine the complexity of an image configuration.

FIG. 8A is a diagram showing an example of a density histogram obtained for an image having a low configuration complexity and FIG. 8B is an example of a density histogram obtained for an image having a high configuration complexity.

FIG. 9 is a flowchart showing a photo printing process according to the third embodiment.

FIG. 10 is a schematic configuration diagram of a photographic printing apparatus according to a fourth embodiment.

FIG. 11 is a flowchart showing a photo printing process according to the fourth embodiment.

[Explanation of symbols]

 10 Photographic Printing Device 12 Negative Film 18 Color Correction Filter 28 Printing Paper 32 CCD Image Sensor 40 Control Unit 62 Magnetic Head

Claims (7)

[Claims] 1. An image feature amount of an area that is estimated to correspond to a main subject extracted from the original image is determined by determining the complexity of the configuration of the original image, and the complexity of the determined original image becomes lower. The degree of contribution to the determination of the exposure amount increases, and the degree of the contribution of the image feature amount of the region estimated to correspond to the main subject extracted from the original image to the determination of the exposure amount decreases as the complexity increases. A method for determining the exposure amount for determining the exposure amount of the original image. 2. A plurality of classes according to the complexity of the image structure are determined in advance, and the image feature amount of the region estimated to correspond to the main subject extracted from the image is the exposure amount, as the class with the lower complexity is the exposure amount. The degree of contribution to the decision becomes large, and the higher the complexity becomes, the less the degree of contribution of the image feature amount of the area estimated to correspond to the main subject extracted from the image to the determination of the exposure amount becomes. An exposure amount calculation formula is set in advance for each, the original image is classified into one of the plurality of classes by determining the complexity of the configuration of the original image, and the exposure amount calculation formula corresponding to the classified class is used. An exposure amount determining method for determining the exposure amount of the original image. 3. As the complexity of the image becomes lower, the image feature amount of the area estimated to correspond to the main subject extracted from the image becomes more involved in the determination of the exposure amount, and the complexity becomes higher. As the image feature amount of the area estimated to correspond to the main subject extracted from the image becomes smaller, the degree of contribution to the determination of the exposure amount becomes smaller.
The degree of involvement is defined as an exposure amount arithmetic expression represented by a function of the complexity of the image configuration, the complexity of the configuration of the original image is determined, and based on the determination result of the complexity of the configuration of the original image, An exposure amount determining method for determining an exposure amount of an original image using the exposure amount calculation formula. 4. The method according to claim 1, wherein the complexity of the structure of the original image is determined based on photometric data obtained by dividing the original image into a large number and measuring the light. The method for determining an exposure amount according to any one of 1. 5. The method according to claim 1, wherein the complexity of the structure of the original image is determined based on the information recorded by the camera that recorded the original image. Exposure determination method. 6. An image feature amount of an area estimated to correspond to a main subject extracted from an image in a class having a lower complexity with respect to each of a plurality of classes determined in advance according to the complexity of an image structure. Is more involved in the determination of the exposure amount, and the higher the complexity is, the less the degree that the image feature amount of the region estimated to correspond to the main subject extracted from the image is related to the determination of the exposure amount. The storage means for storing each of the exposure amount calculation formulas specified in 1., and the original data based on the photometric data obtained by dividing the original image into a large number and measuring the light or the information recorded by the camera that recorded the original image. A classifying unit that classifies the complexity of the image structure and classifies the original image into one of the plurality of classes, and a classifier that is stored in the storage unit and that is classified by the classifying unit. Exposure amount determining means for determining the exposure amount of the original image by using the exposure amount arithmetic expression corresponding to, and exposure control for controlling the exposure of the original image onto the copy material based on the exposure amount determined by the exposure amount determining means. An exposure control apparatus including: 7. As the complexity of the image becomes lower, the degree of contribution of the image feature amount of the area estimated to correspond to the main subject extracted from the image to the determination of the exposure amount increases, and the complexity becomes higher. The image feature amount of the region estimated to correspond to the main subject extracted from the image is predetermined so that the degree of involvement in the determination of the exposure amount becomes smaller. A storage unit that stores the exposure amount calculation formula expressed by a function, and the original data based on the photometric data obtained by dividing the original image into a large number and measuring the light or the information recorded by the camera that recorded the original image. A determination unit that determines the complexity of the image structure, and the exposure amount of the original image is determined based on the determination result by the determination unit using the exposure amount calculation formula stored in the storage unit. That an exposure amount determining means, an exposure control means for controlling the exposure of the original image to the copying material based on the exposure amount determined by the exposure amount determining means, an exposure control device comprising.