JPH118768A - Image processor, image processing method and medium recording image processing control program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To automatically execute an optimum image processing by easily considering importance in real projection image data. SOLUTION: By summing up the distribution of luminance which is a feature amount for respective areas while uniformly selecting pixels (S110) and then performing reevaluation according to the weighting, which is determined for each area (S120), a computer 21 for forming the center of an image processing obtains the luminance distribution strongly affected by the luminance distribution of an original object even while uniformly performing sampling, and since the strength of the image processing or the like is decided, based on the luminance distribution and then image data are converted, executes the image processing by optimum strength while lightening processings (S160).

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus, an image processing method, and a medium in which an image processing control program for automatically executing optimum image processing on photographed image data such as digital photographic images. .

[0002]

2. Description of the Related Art Various types of image processing are performed on digital image data. For example, it is an image processing for expanding the contrast, correcting the color tone, or correcting the brightness. Normally, these image processings can be executed by a microcomputer, and an operator checks an image on a monitor and selects necessary image processing, or determines parameters of the image processing.

[0003]

In recent years, various image processing techniques have been proposed and have actually been effective. However, humans still have to be involved in how much processing to perform. This is because it is not possible to determine where the digital image data to be subjected to image processing is important.

[0004] For example, in consideration of image processing for correcting brightness, it is assumed that automatic processing is performed in which, if the average of the entire screen is dark, the image is corrected to be bright, and if the average is bright, the image is corrected to be dark. Here, it is assumed that there is real image data of a person image taken at night. It is assumed that although the background is almost completely dark, the person itself has been well photographed. When the real image data is automatically corrected, the average of the entire image is darkened because the background is completely dark, and the image is corrected to be bright, so that the image looks like a daytime image.

In this case, if a human is involved, the dark background is considered without giving too much weight, and attention is paid only to the part of the human image. Then, if the person image is dark, the image is corrected to be bright, and conversely, if the image is too bright due to the effect of the flash or the like, the image is darkened.

As described above, in the conventional image processing, it is not possible to determine the degree of importance corresponding to each part in the actual image data, so that there is a problem that a human must be involved.

On the other hand, even if the degree of importance of an image can be determined by some method, it is an operation to determine the degree of importance on a pixel-by-pixel basis. I will.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and it is possible to relatively easily easily consider the importance of actual photographed image data such as a digital photographic image and automatically execute optimal image processing. It is an object of the present invention to provide a medium storing an image processing apparatus, an image processing method, and an image processing control program.

[0009]

According to a first aspect of the present invention, there is provided an image processing apparatus for inputting real image data consisting of pixels in a dot matrix and performing predetermined image processing. A feature amount equalizing means for uniformly extracting the feature amount of each pixel necessary for determining the image processing intensity over the entire screen, and a feature for re-evaluating the feature amount extracted by the feature amount equalizing means by predetermined weighting. It is configured to include a quantity weighting reevaluation unit and a processing unit that determines an image processing intensity based on the reevaluated feature amount and performs image processing.

In the first aspect of the present invention, the actual photographed image data is composed of pixels in a dot matrix, and the characteristic amount uniform extraction means determines the characteristic amount of each pixel necessary for determining the image processing intensity. Is equally extracted over the entire screen. Then, the characteristic amount weighting re-evaluation means re-evaluates the characteristic amount extracted by the characteristic amount equalizing extraction means by predetermined weighting. And the processing means,
The image processing intensity is determined based on the feature amount obtained by the reevaluation in this way, and the image processing is performed.

That is, in the extraction stage, the data is uniformly distributed over the entire screen, and a predetermined weight is applied after the extraction.
The resulting feature will differ from that obtained uniformly over the entire image.

The feature value equalizing extraction means extracts the feature value of each pixel necessary for determining the image processing intensity, and extracts the feature value uniformly over the entire screen. In this case, it may be one that extracts all pixels of the entire screen,
In addition, even if not all pixels, it is sufficient to extract the pixels equally. As an example of the latter, in the invention according to claim 2, in the image processing apparatus according to claim 1, the feature amount uniform extraction means is configured to select pixels which are uniformly thinned out and selected based on a predetermined standard for all pixels. The feature amount is extracted.

[0013] In the invention according to claim 2 configured as described above, the number of pixels to be processed is reduced by uniformly thinning out all the pixels based on a predetermined criterion. Extract feature values.

In this case, the uniform thinning includes a method of thinning out and selecting at a fixed cycle, and a method of randomly selecting and thinning out.

The feature value weighting re-evaluation means re-evaluates the extracted feature value by predetermined weighting. However, the extracted feature value may be weighted in pixel units corresponding to the extracted feature value in pixel units. Alternatively, weighting may be performed for each appropriate group. As an example of the latter, the invention according to claim 3 is the image processing apparatus according to any one of claims 1 and 2, wherein the feature amount uniform extraction means includes:
The feature amount is extracted in units of regions obtained by dividing the image based on a predetermined standard, and the feature amount weighting re-evaluating means is configured to set a weight for each region and reevaluate the feature amount.

In the invention according to claim 3 configured as described above, it is premised that the image is divided on the basis of a predetermined criterion, and weighting is performed on a region basis. The extraction is performed, and the feature value weighting re-evaluation means re-evaluates the feature value for each region with the weight set for each region.

Such division of the area may be always constant, or may be changed for each image. In this case, the division method may be changed according to the content of the image.

Various weighting methods can be employed, and any weighting method may be used as long as re-evaluation is performed in addition to simple equal sampling.

As an example, the invention according to claim 4 is the image processing apparatus according to any one of claims 1 to 3, wherein the feature weighting re-evaluation means is determined by the position of each pixel with respect to the image. The weighting is changed according to the correspondence.

When considering the composition of a photograph, a human image is often positioned at the center. Therefore, if the feature amount is extracted from the whole image evenly, and the feature amount in the central portion is weighted more heavily, the feature amount extracted from the pixels of the human image is greatly evaluated.

In the invention according to claim 4 configured as described above, for example, when it is determined that the weight of the central portion of the image is increased and the weight of the surroundings is reduced, the feature weighting re-evaluation means Judge the position of each pixel with respect to the image, and re-evaluate using the weighting that changes according to this position.

As another example of the weighting method, the invention according to claim 5 is directed to the image processing apparatus according to any one of claims 1 to 4, wherein the feature amount weighting re-evaluation means includes: The degree of change is determined, and the weighting is increased in a portion where the degree of change of the image is large.

In the invention according to claim 5 configured as described above, the degree of change of the image is obtained before the feature weighting re-evaluation means performs re-evaluation. The degree of change of the image can be said to be the sharpness of the image, and the degree of change is large because the contour of an image that is in focus is clearer. Conversely, if the image is out of focus, the image gradually changes in the outline portion of the image, and the degree of change becomes small. In the case of a photograph or the like, a focused portion is an original subject, and an out-of-focus portion is considered to be equivalent to a background or the like. For this reason, a place where the degree of change of the image is large is considered to be an original subject, and the feature value weighting re-evaluation means evaluates the part with a large degree of change of the image by increasing the weight and evaluating it. The result is equivalent to extracting the amount.

Further, as still another example, claim 6
According to the invention, in the image processing apparatus according to any one of claims 1 to 5, the feature amount weighting re-evaluation means seeks the chromaticity of each pixel and extracts the feature amount having the same chromaticity. The number of pixels falling within the range of the chromaticity of the target to be calculated is obtained, and the weighting is increased in a portion where the number of pixels is large.

In the invention according to claim 6 configured as described above, the feature value weighting re-evaluation means obtains the chromaticity of each pixel. In image processing, an object may sometimes be specified by a specific color. For example, a person may be judged as a target by searching for a skin color portion.
However, it is difficult to specify the skin color in the case of ordinary color image data because it includes a brightness element. On the other hand, the chromaticity represents the absolute ratio of the color stimulus value, and is not affected by the brightness. Therefore, if it is within the range of chromaticity that can be taken for flesh color, it can be determined that the pixel is a person image.
Needless to say, the same applies to the range in which trees can take green color and the range in which blue sky takes blue color, in addition to skin color.

Under such a background, the feature value weighting re-evaluation means counts the number of pixels when the chromaticity obtained for each pixel falls within the range of the chromaticity of the target from which the feature value is to be extracted. The portion having a large number of pixels is determined to be the target, and the weight is increased, thereby obtaining the same result as that of extracting many feature amounts from the target.

Although the above-mentioned weighting method is not always an alternative, the invention according to claim 7 is a preferred example in the case of overlapping application.
In the image processing device according to any one of the above, the feature amount weighting re-evaluating means obtains temporary weighting factors individually based on a plurality of elements, and further adds these by weighting according to importance. It is configured to be applied as a final weighting coefficient.

In the invention according to claim 7 configured as described above, the feature value weighting re-evaluation means individually obtains temporary weighting coefficients based on a plurality of elements. Then, these are added by weighting according to the degree of importance, and the feature amount extracted as the final weighting coefficient is reevaluated. Therefore, even if a large weight is given at the stage evaluated by one weighting method, a large weight may not be given as a result if the importance of the weighting method is low. In addition, there is a case where, for a method having a large difference for each weighting method, a method in which the weight is evaluated above the average as a whole has a large final weight.

In the extraction stage, the method of performing the same weighting over the entire screen and performing the predetermined weighting after the extraction is not necessarily limited to a substantial device. As an example, the invention according to claim 8 An image processing method for inputting real image data consisting of pixels of a given image and performing predetermined image processing, wherein a feature amount of each pixel required to determine the image processing intensity is evenly extracted over the entire screen. It is configured to include a step of re-evaluating the extracted feature amount by predetermined weighting, and a step of determining an image processing intensity based on the re-evaluated feature amount and performing image processing.

That is, there is no difference that the present invention is not necessarily limited to a substantial device but is also effective as a method.

As described above, an image processing apparatus that re-evaluates a feature value by weighting and performs image processing may exist alone, or may be used while being incorporated in a certain device. The concept of the invention includes various aspects. Further, it can be appropriately changed, for example, by hardware or software.

When the software for controlling the image processing apparatus is realized as an embodiment of the idea of the present invention, the software naturally exists on a recording medium on which such software is recorded.
I have to say that it is used.

As one example, the invention according to claim 9 is a medium in which an image processing control program for performing a predetermined image processing by inputting real image data composed of dot matrix pixels by a computer is provided. The feature amount of each pixel necessary for determining the image processing intensity is extracted evenly over the entire screen, and the extracted feature amount is reevaluated by a predetermined weight, and image processing is performed based on the reevaluated feature amount. The image processing is performed by determining the intensity.

Of course, the recording medium may be a magnetic recording medium, a magneto-optical recording medium, or any recording medium to be developed in the future. Also, the duplication stages of the primary duplicated product, the secondary duplicated product, and the like are equivalent without any question. In addition, the present invention is still used even when the supply method is performed using a communication line, and the same applies to a case where the information is written on a semiconductor chip.

Further, even when a part is implemented by software and a part is implemented by hardware, there is no difference in the concept of the present invention, and it is necessary to store a part on a recording medium. It may be in a form that is appropriately read in accordance with it.

[0036]

As described above, according to the present invention, the amount of calculation is not increased because the extraction is performed uniformly over the entire screen, and the extraction is performed evenly simply by performing a predetermined weighting after the extraction. It is possible to provide an image processing apparatus capable of automatically performing optimal image processing without performing an inappropriate evaluation as in the case where the image processing is performed.

According to the second aspect of the present invention, since the pixels are thinned out at the time of extracting the feature amounts evenly,
The processing amount can be reduced.

Further, according to the invention of claim 3,
Since the weight is changed for each area, the calculation becomes relatively easy.

Further, according to the invention according to claim 4,
Since the weighting is determined by the position of the pixel, the calculation is relatively easy.

Further, according to the invention of claim 5,
Since the weighting is changed depending on the sharpness of the image, a different target can be accurately determined for each image to extract a feature amount.

Further, according to the invention of claim 6,
Since a specific target can be selected based on chromaticity, it is possible to accurately determine a different target depending on each image and extract a feature amount.

According to the seventh aspect of the present invention,
More suitable evaluation of the feature amount can be performed by appropriately combining a plurality of weighting methods.

Further, according to the invention of claim 8,
An image processing method capable of performing an image processing with a small amount of calculation and performing an optimal evaluation, and according to the invention according to claim 9, recording an image processing control program capable of obtaining the same effect Can be provided.

[0044]

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 is a block diagram showing an image processing system to which an image processing apparatus according to an embodiment of the present invention is applied, and FIG. 2 is a schematic block diagram showing an example of a specific hardware configuration.

In FIG. 1, an image input device 10 outputs actual image data representing a photograph or the like as pixels in a dot matrix form to an image processing device 20.
Performs the image processing after determining the degree of enhancement of the image processing through a predetermined process. The image processing device 20 outputs the image-processed image data to the image output device 30, and the image output device 30 outputs the image-processed image as pixels in a dot matrix. Here, the image data output by the image processing apparatus 20 is obtained by equally extracting a feature amount from each pixel based on a predetermined reference, and then re-evaluating the feature amount with a predetermined weight.
The image has been image-processed with the degree of enhancement determined according to the re-evaluated feature amount. Therefore, the image processing device 20
In this manner, a feature amount equal extraction means for evenly extracting the feature amount, a feature amount weighting re-evaluation means for re-evaluating the extracted feature amount with a predetermined weight, and an emphasis degree according to the re-evaluated feature amount And a processing means for performing image processing.

A specific example of the image input device 10 corresponds to the scanner 11, the digital still camera 12, or the video camera 14 in FIG. 2, and a specific example of the image processing device 20 is a computer 21, a hard disk 22, a keyboard 23, a CD-ROM. A computer system including a drive 24, a floppy disk drive 25, a modem 26, and the like corresponds to the computer system. Specific examples of the image output device 30 correspond to a printer 31, a display 32, and the like. In the case of the present embodiment, since an object is found as image processing and appropriate image processing is performed, actual image data such as a photograph is suitable as image data. The modem 26 is connected to a public communication line, is connected to an external network via the public communication line, and can download and install software and data.

In this embodiment, the image input device 10
The scanner 11 and the digital still camera 12 output RGB (green, blue, red) gradation data as image data, and the printer 3 as the image output device 30.
1 requires CMY (cyan, magenta, yellow) or CMYK binary data obtained by adding black to the input as gradation data, and the display 32 has RGB data.
Is required as an input. On the other hand, an operating system 21a is running in the computer 21, and a printer driver 21b and a display driver 21c corresponding to the printer 31 and the display 32 are provided.
Is incorporated. The image processing application 21d is controlled by the operating system 21a to execute processing, and executes predetermined image processing in cooperation with the printer driver 21b and the display driver 21c as necessary. Therefore, the specific role of the computer 21 as the image processing apparatus 20 is to input RGB gradation data, create RGB gradation data subjected to optimal image processing, and display the RGB data through the display driver 21c. And the printer driver 21
The data is converted into binary data of CMY (or CMYK) via b and printed by the printer 31.

As described above, in the present embodiment, a computer system is incorporated between image input / output devices to perform image processing. However, such a computer system is not necessarily required. Any system can be used as long as it performs various types of image processing. For example, as shown in FIG.
An image processing apparatus that determines an object and performs image processing on the object may be incorporated in 2a, and the converted image data may be used to display on the display 32a or print on the printer 31a. As shown in FIG. 4, in a printer 31b that inputs and prints image data without passing through a computer system, the printer 31b automatically receives image data input through a scanner 11b, a digital still camera 12b, a modem 26b, or the like. It is also possible to adopt a configuration in which an object is determined and image processing is performed.

The above-described determination of an object and the accompanying image processing are performed by the image processing program corresponding to the flowchart shown in FIG. In the flowchart shown in the drawing, image processing for adjusting the contrast of an image is performed. In step S110, luminance as a feature amount is extracted while uniformly thinning out pixels from the entire image, and then in step S120. The same feature amount is re-evaluated by performing predetermined weighting, and image processing for adjusting the luminance is performed in steps S130 to S160.

In step S110, as shown in FIG. 6, a histogram is generated by obtaining the luminance of each pixel for the dot matrix image data in the vertical and horizontal directions. In this case, it can be said that it is accurate if it is performed for all pixels, but as will be described later, since the aggregation result is weighted and re-evaluated,
It does not have to be accurate. Therefore, it is possible to thin out the pixels from which the luminance is extracted so as to fall within a certain error range, reduce the processing amount, and increase the speed. According to the statistical error, the error with respect to the number of samples N is approximately 1 / (N **
(1/2)). Here, ** indicates a power. Therefore, in order to perform processing with an error of about 1%, N =
10,000.

Here, the bit map screen shown in FIG. 6 has the number of pixels of (width) × (height), and the sampling period ratio is ratio = min (width, height) / A + 1 (1). Here, min (width, height)
ht) is the smaller of width and height, and A is a constant. Further, the sampling period ratio here indicates how many pixels are sampled. Pixels marked with a circle in FIG.
The case where tio = 2 is shown. In other words, one pixel is sampled every two pixels in the vertical direction and the horizontal direction, and sampling is performed every other pixel. The number of sampling pixels in one line when A = 200 is as shown in FIG.

As is apparent from FIG. 6, except for the case where the sampling period ratio = 1 where sampling is not performed, when the width is 200 pixels or more, at least the number of samples becomes 100 pixels or more. Therefore, when the number of pixels is 200 or more in the vertical and horizontal directions, (100 pixels) × (100 pixels) = (10000 pixels)
Is ensured, and the error can be reduced to 1% or less.

Here, min (width, hei)
(ght) is based on the following reason.
For example, as shown in a bitmap image shown in FIG.
Assuming that width >> height, if the sampling period ratio is determined by the longer width, as shown in FIG. 4B, only two lines, the upper and lower lines, are extracted in the vertical direction. That can happen. However, min (widt
h, height), if the sampling period ratio is determined based on the smaller one, FIG.
As shown in FIG. 7, thinning including the intermediate portion can be performed even in the smaller vertical direction. That is, it is possible to perform sampling while securing a predetermined number of extractions.

The luminance is extracted by thinning out the pixels as described above. As described above, in the present embodiment, the computer 21 handles RGB gradation data, and does not directly have a luminance value. L to find the brightness
Although it is possible to perform color conversion to the uv color space, this is not advisable due to problems such as the amount of calculation. For this reason, the following conversion formula for directly obtaining luminance from RGB used in the case of a television or the like is used.

Y = 0.30R + 0.59G + 0.11B (2) In addition, the luminance histogram is not totalized for one image, but as shown in FIG. The blocks are divided into a total of 15 blocks and totaled individually. In the present embodiment, such 15 blocks are used, but a block division method is of course arbitrary. In particular, a printer driver or the like receives image data for each block from an application, but area division for weighting may be performed using this block.

The reason for summing up each block is to reduce the amount of processing. In the sense that weighting is performed in step S120 and re-evaluation is performed, it is not always necessary to perform totalization for each block. It is also possible to perform totalization as a histogram in consideration of weighting for each selected pixel. In addition, since the weight of the tally result is changed for each block, it is possible to perform tallying with one histogram by using the weight according to the block. FIG. 11 is a diagram illustrating an example of the luminance distribution of the block Bi.

In the case of totaling for each block,
In step S120, weighting is performed for each area and reevaluation is performed. FIG. 12 and FIG. 13 show examples in which weights are given to each block. Assuming a general photographic image, the composition is usually such that the original subject is located at the center. In this sense, the feature amount should be evaluated with emphasis on the image in the central part of the image data. On the other hand, considering another example of taking a commemorative photo in front of a building,
The human image is photographed while being positioned below the center. Because the height of the ground is usually located at the bottom of the image. Therefore, in this case, it can be said that the feature value should be evaluated with a weight below the center of the image. The example of FIG. 12 corresponds to the former, and FIG. 13 corresponds to the latter.

Each block is weighted by Wi (i = 1 to 1).
5), and the weighted and reevaluated luminance distribution is DY,

[0060]

(Equation 1)

And Ki = Wi / SP (4)

[0062]

(Equation 2)

Is obtained as follows.

When the re-evaluated histogram of the luminance distribution is obtained in this way, the intensity of image processing is obtained from the feature amount. That is, the width for increasing the contrast is determined. In determining the enlargement width, consider obtaining both ends of the luminance distribution. As shown in FIG. 14, the luminance distribution of the photographic image generally appears in a mountain shape. Of course, the position and shape are various. The width of the luminance distribution is determined depending on where the both ends are determined. However, the point where the number of distributions becomes “0” by extending the base cannot be set as the both ends. This is because the number of distributions may change around “0” in the tail part, and the number of distributions changes while approaching “0” without limit statistically.

For this reason, the portions extending inward by a certain distribution ratio from the side with the highest luminance and the side with the lowest luminance in the distribution range are defined as both ends of the distribution. In the present embodiment, as shown in the figure, the distribution ratio is set to 0.5%. Of course, this ratio can be changed as appropriate. In this manner, by cutting the upper and lower ends by a certain distribution ratio, white points and black points caused by noise or the like can be ignored. That is, if such processing is not performed, even if there is even one point, a white point or a black point will be at both ends of the luminance distribution. "0"
And the uppermost end is the gradation “255”,
Such a problem is eliminated by setting a portion which is 0.5% of the number of pixels inside from the upper end portion as an end portion.

In the actual processing, 0.5% of the number of pixels is calculated based on the histogram obtained by re-evaluation, and the luminance value at the upper end and the luminance value at the lower end in the reproducible luminance distribution are sequentially turned inward. Then, the respective distribution numbers are accumulated, and a luminance value having a value of 0.5% is obtained. Hereinafter, this upper end is called ymax, and the lower end is called ymin.
Further, in the present embodiment, the brightness is corrected together with the expansion of the contrast, and the median ymed necessary for that is also determined based on the reevaluated histogram. The above processing is performed in step S130.

The reproducible luminance range is from “0” to “25”.
When “5” is set, the luminance Y of the conversion destination is obtained from the luminance y before the conversion and the maximum value ymax and the minimum value ymin of the luminance distribution range based on the following equation.

Y = ay + b (6) where a = 255 / (ymax−ymin) (7) b = −a · ymin or 255−a · ymax (8) In the above conversion formula, Y <0 Then, Y = 0 and Y> 2
If 55, Y = 255. Here, “a” is a slope, and “b” is an offset. According to this conversion formula, as shown in FIG. 15, a luminance distribution having a certain narrow width can be expanded to a reproducible range. However,
When the luminance distribution is expanded by maximizing the reproducible range, a highlight portion may be lost in white, or a high shadow portion may be lost in black. In order to prevent this, in the present embodiment, the reproducible range is limited. That is, the luminance value “5” is left as a range that does not expand to the upper and lower ends of the reproducible range. As a result, the parameters of the conversion equation are as follows.

A = 245 / (ymax−ymin) (9) b = 5-a · ymin or 250−a · ymax (10) In this case, in the range of y <ymin and y> ymax Causes no conversion.

However, if the enlargement ratio (corresponding to a) is applied as it is, a very large enlargement ratio may be obtained. For example, in a twilight state such as in the evening, the width of the contrast from the brightest part to the dark part is naturally narrow, but as a result of trying to greatly increase the contrast of this image, it is converted like a daytime image. I could end up. Since such conversion is not desired, a limit is set for the enlargement ratio, and a is set to 1.5 (to
2) Restrict it so that it does not exceed the above. Thereby, twilight comes to be expressed as twilight. In this case, processing is performed so that the center position of the luminance distribution does not change as much as possible. In step S140, the processing for obtaining the enlargement factor a and the inclination b in this manner is executed.

By the way, it is irrational to execute the above conversion formula (Y = ay + b) every time the luminance is converted.
That is, the possible range of the luminance y is “0” to “25”.
Since it can be only 5 ", the converted luminance Y can be obtained in advance for all possible values of the luminance y. Therefore, it is stored as a table as shown in FIG.

Since it is extremely effective not only to enhance the contrast by expanding the range of brightness but also to adjust the brightness together, it is also necessary to determine the brightness of the image and generate parameters for correction. I do.

For example, in the case where the peaks of the luminance distribution are entirely on the dark side as shown by the solid line in FIG. 17, it is preferable to move the peaks to the overall bright side as shown by the wavy line. Conversely, when the peaks of the luminance distribution are generally shifted to the bright side as shown by the solid line in FIG. 18, it is preferable to move the peaks to the dark side as a whole as indicated by the wavy line.

As a result of conducting various experiments, in this embodiment, the median ymed in the luminance distribution is obtained, and when the median ymed is less than “85”, the image is determined to be a dark image and corresponds to the following γ value. Brighten with gamma correction.

Γ = ymed / 85 (11) or γ = (ymed / 85) ** (1/2) (12)

In this case, even if γ <0.7, γ =
0.7. Unless such a limit is set, a night image looks like daytime. If the image is made too bright, the image becomes whitish as a whole and the image tends to have a low contrast. Therefore, a process such as emphasizing with saturation is preferable.

On the other hand, when the median ymed is larger than “128”, the image is determined to be a bright image and darkened by γ correction corresponding to the following γ value.

Γ = ymed / 128 (13) Alternatively, γ = (ymed / 128) ** (1/2) (14) In this case, even if γ> 1.3, γ = 1.3.
A limit is set so as not to be too dark.

Note that this γ correction may be performed on the luminance distribution before conversion or on the luminance distribution after conversion. FIG. 19 shows a correspondence relationship when the γ correction is performed. If γ <1, the curve expands upward, and if γ> 1, the curve expands downward. Of course, the result of the γ correction may be reflected in the table shown in FIG. 16, and the correction is performed on the table data. In step S150, processing for generating such a conversion table is executed.

Thereafter, conversion based on the equation (6) is performed.
The same conversion equation can be applied to the correspondence relationship with the RGB component values, and the component values before conversion (R0, G0
, B0), the converted component values (R, G, B) are: R = a · R0 + b (15) G = a · G0 + b (16) B = a · B0 + b (17) Can also be sought. Here, corresponding to the luminance y, Y being the gradation "0" to the gradation "255", the RGB component values (R0, G0, B0) and (R, G, B) are also in the same range. It can be said that the conversion table of the luminances y and Y described above may be used as it is.

Therefore, in step S160, the image data (R0, G0, B0) of all the pixels are (15) to (1).
The process of obtaining the converted image data (R, G, B) by referring to the conversion table corresponding to the expression (7) is repeated.

Of course, the processing means is constituted by the hardware configuration and software for executing steps S130 to S160. Note that, in the present embodiment, a contrast enlargement process and a brightness correction process are executed as image processing, but it is needless to say that the same can be applied to other image enhancement processes and the like.

In the above processing, the feature value is reevaluated by weighting according to the position in the image. However, the criterion for weighting is not limited to this, and various modes are possible. FIG. 20 shows an example in which the original subject is detected from the degree of change in the image,
5 shows a flowchart in the case of changing the weight.

Step S210 is the same as step S210 described above.
It is an alternative to 110 and counts the luminance for pixels that have been evenly thinned. However, instead of just counting the brightness,
The following edge amounts are also totaled.

The background of the input image can be said to have a gradual change in shading, and the original subject can be said to have a sharp change in luminance because it is sharp. Therefore, as shown in FIG. 21, a certain pixel is set as a target pixel, and a density difference between the target pixel and a peripheral pixel is determined, and this density difference is set as an edge amount of the target pixel. This density difference can be calculated by applying a filter, and FIGS. 22A to 22F show several examples of such a filter. The luminance of each pixel is calculated for the target pixel and the eight peripheral pixels. The weighting coefficient at the time of weighting addition is shown. Here, in the case of FIG. 11A, weighted addition is performed for nine pixels, and thus, in order to obtain the edge amount at each pixel, nine multiplications and eight additions are required. Since the amount of calculation cannot be ignored as the size of the image increases, only five multiplications and four additions are required in FIGS. 9B and 9C, and three multiplications are required in FIGS. 9D and 9E. And two additions, and in FIG. 3F, only two multiplications and one addition are required.

In these examples, the target pixel is compared only with the pixel surrounding the target pixel in a single manner. However, the sharpness of the target pixel is determined using a wider range of pixel data using a so-called unsharp mask. It is possible to ask for However, the edge amount in the present embodiment is only for evaluating the weight for each block, and therefore, the filters of these examples in which the calculation amount is reduced are sufficient.

The edge amount may be calculated by summing the edge amounts obtained for each pixel for each block, or when the absolute value of the edge amount is larger than a predetermined threshold value, the pixel is determined to be an edge pixel. Alternatively, the total number of edge pixels for each block may be counted. The edge amount in each block is E
If Ri (i = 1 to 15), the total amount SE is

[0088]

(Equation 3)

Thus, the weighting coefficient KEi itself is expressed by KEi = ERi / SE (19). Therefore, the weighted and re-evaluated luminance distribution DY in this case is

[0090]

(Equation 4)

Is obtained. If the total number of edge pixels in each block is ENi (i = 1 to 15), the total amount SE is

[0092]

(Equation 5)

Thus, the weighting coefficient KEi itself is expressed by KEi = ENi / SE (22), and the luminance distribution DY re-evaluated can be obtained by using the equation (20). In any case, in step S220, the luminance distribution DY is reevaluated based on the arithmetic expression of Expression (20).

In this example, the luminance of the pixel determined to be an edge pixel is not sampled and used, but the edge amount and the total number of edge pixels are merely used for determining the weighting coefficient of the block. That is, the feature amounts of only pixels having a specific property (edge) are not counted, and an average feature amount that is not biased in the block can be obtained.

When the luminance distribution is re-evaluated in this way, the contrast may be increased and the brightness may be corrected through the above-described processing in steps S130 to S160.

Furthermore, considering that the original subject is often a human image, it is possible to re-evaluate the block with a large number of skin color pixels. FIG. 23 shows a flowchart for determining a weighting coefficient of a block by focusing on such a specific color.

Step S3 corresponding to step S110
In step 10, the luminance is totaled by the same thinning-out processing, and it is determined whether or not the pixel is a skin color pixel based on the chromaticity of each pixel, and the number of skin color pixels is totaled. As for the chromaticity, the xy chromaticity of each pixel is calculated. Now, the RGB gradation data in the RGB color system of the target pixel is (R, G,
B), r = R / (R + G + B) (23) g = G / (R + G + B) (24) Then, chromaticity coordinates x, y in the XYZ color system
X = (1.1302 + 1.6387r + 0.6215g) / (6.7846-3.0157r-0.3857g) (25) y = (0.0601 + 0.9399r + 4.5306g) / (6. 7846-3.0157r-0.3857g) (26) Here, since the chromaticity represents the absolute ratio of the color stimulus value without being influenced by the brightness, it can be said that it is possible to determine what kind of object the pixel is based on the chromaticity. . Since the skin color is included in the range of 0.35 <x <0.40 (27) 0.33 <y <0.36 (28), the chromaticity of each pixel was obtained. Sometimes, if it is within this range, the pixel is considered as a pixel indicating human skin, and the number of skin color pixels in the block is increased by one.

When the number of skin color pixels is obtained in this way,
In the next step S320, a weighting coefficient is determined in the same manner as in the case of the number of edge pixels described above, and the luminance distribution DY is reevaluated. That is, the number of skin color pixels in each block is set to CN
If i (i = 1 to 15), the total amount SC is

[0099]

(Equation 6)

Thus, the weighting KCi itself is expressed by KCi = CNi / SC (30), and the weighted and reevaluated luminance distribution DY in this case is

[0101]

(Equation 7)

Is obtained. Also in this example, the luminance of the pixel determined to be a flesh-colored pixel is not sampled and used, but the total number of flesh-colored pixels is simply used for determining the weighting coefficient of the block. Therefore, it is possible to obtain an average feature amount that is not biased in the block. In this case as well, if the luminance distribution is re-evaluated in this way, the contrast may be expanded and the brightness may be corrected through the above-described processes of steps S130 to S160. In the case of the photo shown in FIG. 24, a girl is shown near the center, and pixels of the face and limbs are determined to be flesh-colored pixels. Of course, the chromaticity of other colors may be obtained and the number of pixels may be totaled.

By the way, the weighting coefficient has been determined by one factor, but it is also possible to apply the weighting factor redundantly in consideration of the importance of each factor. When the weighting coefficient of each block Bi (i = 1 to 15) for each factor j (1: position in the image, 2: edge amount, 3: skin color pixel number) is Tji, each block for each factor Are temporary weights, and the weights Tji distributed to

[0104]

(Equation 8)

And Kji = Tji / Sj (33), the true weighting coefficient Ki in the block Bi
Is

[0106]

(Equation 9)

Is represented by Here, Aj is a coefficient indicating the degree of importance of each factor, and is appropriately determined in a range where the total number is 1. As an example, if emphasis is placed on skin color, A1
= 0.2, A2 = 0.2, A3 = 0.6, etc.

Next, the operation of this embodiment having the above configuration will be described. First, a description will be given along the previous embodiment.

Assume that a photographic image is read by the scanner 11 and printed by the printer 31. Then, first,
Operating system 21a on computer 21
Is running, the image processing application 21
d is started, and the scanner 11 starts reading a photograph. When the read image data is captured by the image processing application 21d via the operating system 21a, the luminance of each pixel is totalized while thinning out in step S110. The aggregated luminance distribution dYi is obtained at step S120 in FIG.
Is re-evaluated based on the weight determined corresponding to the position of each block shown in FIG. 5, and in step S130, based on the re-evaluated luminance distribution DY, ymax, ymin, yme
Find d.

In the next step S140, the slope a and the offset b, which are the emphasis parameters, are calculated based on the equation (9) or (10), and the equations (11) to (11) are used.
The γ value of the γ correction required for the brightness correction is obtained based on the equation (14), and in step S150, the conversion table shown in FIG. 6 is created. Finally, in step S160, the image data for all pixels is converted with reference to the conversion table.

In the case where the weighting shown in FIG. 12 is used, the weighting is heavier as the block is closer to the center, so that the aggregated luminance distribution is evaluated higher as the block is closer to the center. For example, suppose that a person image was shot using a flash at night. Due to the flash effect, the luminance distribution of the person image is generally dark, as shown in FIG. 25B, even though a good luminance distribution is obtained as shown in FIG. A luminance distribution biased to the side is obtained. In this case, simply averaging results in a luminance distribution that is entirely biased toward the dark side as shown in FIG. Therefore, if the contrast or brightness is corrected as it is, a dark image is forcibly brightened, and a good image cannot be obtained.

However, as shown in FIG. 12, if the weight of the central block is increased,
As shown in FIG. 5D, a luminance distribution DY strongly influenced by the luminance distribution obtained in the central portion of the image is obtained. Therefore, the intensity of the image processing determined based on the luminance distribution does not excessively increase the contrast or modify the brightness.

On the other hand, when a person is photographed in a backlight state, the face becomes dark and the background becomes bright. However, when viewed as a whole image, a good luminance distribution may result. However, even in such a case, as shown in FIG. 12, by evaluating the luminance distribution in the central block where the dark face is shown with emphasis, the dark luminance distribution is reflected, and the contrast is enlarged or the image is enlarged. Image processing to make the image brighter.

With the above processing, the image data of the photograph read via the scanner 11 is automatically subjected to image processing at an optimum intensity, and is displayed on the display 32.
The image is printed by the printer 31.

As described above, the computer 21, which is the center of the image processing, sums up the distribution of the luminance, which is the characteristic amount, for each region while equally selecting the pixels in step S110.
In step S120, by performing re-evaluation with the weight determined for each region, it is possible to obtain a luminance distribution strongly influenced by the original luminance distribution of the subject while performing uniform sampling, and to perform steps S130 to S150. After determining the intensity of image processing and the like based on the luminance distribution, the image data is converted in step S160.
Image processing can be executed with optimal intensity while reducing processing.

[Brief description of the drawings]

FIG. 1 is a block diagram of an image processing system to which an image processing device according to an embodiment of the present invention is applied.

FIG. 2 is a block diagram of specific hardware of the image processing apparatus.

FIG. 3 is a schematic block diagram illustrating another application example of the image processing apparatus of the present invention.

FIG. 4 is a schematic block diagram illustrating another application example of the image processing apparatus of the present invention.

FIG. 5 is a flowchart illustrating image processing in the image processing apparatus of the present invention.

FIG. 6 is a diagram illustrating a state in which a processing target pixel is moved.

FIG. 7 is a diagram showing a sampling cycle.

FIG. 8 is a diagram showing the number of sampling pixels.

FIG. 9 is a diagram illustrating a relationship between a conversion source image and pixels to be sampled.

FIG. 10 is a diagram showing an arrangement of blocks obtained by dividing an image into regions.

FIG. 11 is a diagram illustrating an example of a luminance distribution in each block.

FIG. 12 is a diagram illustrating an example of weighting for each block.

FIG. 13 is a diagram illustrating another example of weighting for each block.

FIG. 14 is a diagram illustrating edge processing of a luminance distribution and an edge obtained by the edge processing.

FIG. 15 is a diagram showing an enlarged luminance distribution and a reproducible luminance range.

FIG. 16 is a diagram showing a conversion table when expanding a luminance distribution.

FIG. 17 is a diagram showing a concept of increasing brightness by γ correction.

FIG. 18 is a diagram showing a concept of darkening by γ correction.

FIG. 19 is a diagram showing a correspondence relationship of luminance changed by γ correction.

FIG. 20 is a flowchart in the case of re-evaluating a feature amount based on an edge amount.

FIG. 21 is a diagram illustrating a relationship between a target pixel and peripheral pixels for determining an edge amount.

FIG. 22 is a diagram illustrating an example of a filter for calculating an edge amount.

FIG. 23 is a flowchart in the case of re-evaluating a feature amount based on the number of pixels of a predetermined color.

FIG. 24 is a diagram illustrating an example of a photographic image.

FIG. 25 is a diagram showing a luminance distribution of a photographic image taken at night.

[Explanation of symbols]

 Reference Signs List 10 image input device 20 image processing device 21 computer 21a operating system 21b printer driver 21c display driver 21d image processing application 30 image output device

Claims (9)

[Claims] 1. An image processing apparatus for inputting real image data composed of pixels in a dot matrix and performing predetermined image processing, wherein a feature amount of each pixel required for determining an image processing intensity is determined over an entire screen. A feature value uniform extraction means for evenly extracting the feature value; a feature value weighted re-evaluation means for re-evaluating the feature value extracted by the feature value equal extraction means by predetermined weighting; Processing means for determining intensity and performing image processing. 2. The image processing apparatus according to claim 1, wherein the feature amount uniform extraction means extracts the feature amount for a pixel selected by uniformly thinning out all pixels on a predetermined basis. An image processing apparatus characterized by the above-mentioned. 3. The image processing apparatus according to claim 1, wherein the feature amount uniform extraction means extracts a feature amount in units of an area obtained by dividing the image based on a predetermined standard. The image processing apparatus, wherein the feature amount weighting re-evaluating means re-evaluates the feature amount by setting a weight for each area. 4. The image processing apparatus according to claim 1, wherein the feature amount weighting re-evaluating means changes the weighting in a correspondence determined by a position of each pixel with respect to the image. An image processing apparatus characterized by the above-mentioned. 5. The image processing apparatus according to claim 1, wherein the feature value weighted re-evaluation means obtains a degree of change in the image, and determines the degree of change in the image in a portion where the degree of change in the image is large. An image processing apparatus characterized in that weighting is increased. 6. The image processing apparatus according to claim 1, wherein said feature amount weighting re-evaluation means calculates a chromaticity of each pixel and extracts a feature amount having the same chromaticity. An image processing apparatus, wherein the number of pixels falling within the range of the chromaticity of a target to be calculated is obtained, and the weight is increased in a portion where the number of pixels is large. 7. The image processing apparatus according to claim 1, wherein said feature amount weighting re-evaluation means obtains temporary weighting coefficients individually based on a plurality of elements, and further comprises: ,
An image processing apparatus characterized in that these are added by weighting according to importance and applied as a final weighting coefficient. 8. An image processing method for inputting real image data consisting of pixels in a dot matrix form and performing predetermined image processing, wherein a feature amount of each pixel necessary for determining the image processing intensity is determined over the entire screen. A step of uniformly extracting, a step of re-evaluating the extracted feature amount by predetermined weighting, and a step of determining an image processing intensity based on the re-evaluated feature amount and performing image processing. Characteristic image processing method. 9. A medium storing an image processing control program for performing predetermined image processing by inputting actual image data composed of dot matrix pixels by a computer, wherein each medium is necessary for determining image processing intensity. While extracting the feature amount of the pixel uniformly over the entire screen, the extracted feature amount is reevaluated by predetermined weighting,
A medium in which an image processing control program is recorded, wherein the image processing intensity is determined based on the re-evaluated feature amount and image processing is performed.