JP2007086940A - Image processing device and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing device and an image processing method that can appropriately determine the effectiveness of density and other corrections based on face areas included in an image. <P>SOLUTION: The image processing device comprises a density correction curve generation part 11 for generating a density correction curve according to a reference density correction value set according to all image characteristics of original image data, a face area detection part 12 for detecting face areas of subjects included in the original image data, and a density correction value setting part 130 for correcting the reference density correction value according to the face area information detected by the face area detection part 12; and generates the density correction curve for density correction to the original image data according to an appropriate density correction value set by the density correction value setting part. The density correction value setting part 130 corrects the reference density correction value according to the average density and face area size of the face areas detected by the face area detection part 12. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention provides a density correction curve generation unit that generates a density correction curve based on a reference density correction value that is set based on all image characteristics corresponding to original image data, and a face of a subject included in the original image data A face area detection unit that detects an area; and a density correction value setting unit that corrects the reference density correction value based on the face area information detected by the face area detection unit, and is set by the density correction value setting unit The present invention relates to an image processing apparatus and an image processing method for generating a density correction curve for correcting the density of the original image data based on the appropriate density correction value.

  In general, a photographic image processing apparatus is an image provided with a media drive or the like for inputting image data taken by a digital photographing device such as a film scanner or a digital still camera that digitizes a photographed image formed on a photographic film as original image data. An input unit, an image processing unit that performs various image processing such as density correction and color correction on the original image data, and exposing a photosensitive material (photographic paper) based on print data converted after the image processing A print processing unit for generating a photographic print is provided.

  The above-mentioned image processing unit is suitable for human visual characteristics in consideration of differences in gradation characteristics of input image data and gradation characteristics of photosensitive materials in order to obtain photographic prints with good image quality. Density correction processing for matching is performed.

  As such density correction processing, correction processing is generally performed so that input image data and output image data have a density characteristic curve exhibiting a predetermined gamma characteristic, and a density histogram of the entire target input image is obtained. A density correction curve is generated based on the reference density correction value obtained from the above, and the input image data is converted based on the density correction curve.

  However, even if correction processing is performed based on the above-described density correction curve, not all image data shot under various shooting conditions are corrected satisfactorily. For example, image data taken from photographic film taken with overexposure or underexposure has a high luminance side and low luminance side inclination rate because the luminance of each pixel is too biased toward the high luminance side or low luminance side. Even if density correction is performed based on a basic density correction curve showing a gentle characteristic, it is difficult to ensure gradation.

On the other hand, when the main subject of the photographed image is a person, as a technique for obtaining a high-quality photo print by correcting the face area of the person to have an appropriate brightness, for example, Patent Document 3 A reference density characteristic curve generation unit that generates a reference density characteristic curve based on a reference density correction value calculated based on captured image data, and a face-dependent density characteristic based on the detected face average density value of the face area A face-dependent density characteristic curve generation unit that generates a curve; a first correction value determination unit that determines a first correction value from a difference between the reference density characteristic curve and the face-dependent density characteristic curve; and the face average density value A second correction value determining unit that determines an adjustment rate from a difference from an image average density value that is an average density value of the entire image, and that determines a second correction value from the first correction value and the adjustment rate; Based on the correction value The image processing apparatus provided with a density characteristic curve setting unit for setting a density characteristic curve used in the correction unit is proposed.
JP-A-6-59353 Japanese Patent Laid-Open No. 2001-218047 JP 2005-159387 A

  However, there are many techniques for detecting human faces from target image data, including pattern recognition technology that recognizes the shape and arrangement pattern of eyes, nose, mouth, etc., and recognizes them in combination with skin color. Although it has been proposed, it is still not easy to detect a person's face with high accuracy, and if it is not determined as a face even though the person's face is reflected, or if it is not a person's face, It may be judged erroneously.

  For example, when a person wearing sunglasses is a subject, it cannot be detected accurately because the eyes are not recognized, etc., and even if the face is overlapped, it is recognized because it does not match the predetermined pattern. In some cases, a pattern such as the face of a person attached to clothes is mistakenly detected as a face. Conversely, the face of the person who is the main subject may not be recognized, and the face reflected in a small area of the background may be recognized.

  In such a case, if the density correction curve is uniformly corrected based on the detected face area of the person, there is a possibility that the image quality may be deteriorated, and there is a problem that the evaluation cannot be easily performed. For example, if the main subject is not detected and correction is made based on a dark face that is clearly not the main subject detected in a small area, the face of the main subject is corrected to an inappropriate image that is white. Become.

  SUMMARY OF THE INVENTION In view of the above-described conventional problems, the present invention provides an image processing apparatus and an image processing method that can determine the effectiveness of correction of density and the like based on a face area included in an image and can correct the density appropriately. .

  In order to achieve the above object, the first characteristic configuration of the image processing apparatus according to the present invention is based on the whole image characteristics corresponding to the original image data as described in claim 1 of the document of the claims. A density correction curve generation unit that generates a density correction curve based on a set reference density correction value, a face region detection unit that detects a face region of a subject included in the original image data, and detection by the face region detection unit A density correction value setting unit that corrects the reference density correction value based on the face area information that has been set, and performs density correction on the original image data based on the appropriate density correction value set by the density correction value setting unit. An image processing apparatus for generating a density correction curve for the image processing apparatus, wherein the density correction value setting unit includes the reference density correction value based on an average density and a face area size of the face area detected by the face area detection unit. It lies in correcting the proper density correction value.

When a result of performing density correction on a large number of sample images using a density correction curve generated by an appropriate density correction value obtained by correcting the reference density correction value based on face area information, It has been newly found that the average density and the face area size of the face area have a great relationship with the image quality obtained as a result of the correction process of the reference density correction value. Therefore, as described above, when the reference density correction value is corrected based on the average density and the face area size of the face area detected by the face area detection unit, all the face areas of the main subject are properly detected without error. Regardless of whether it was done or not, the image can be corrected to a good density.
In the second feature configuration, as described in claim 2, in addition to the first feature configuration described above, the density correction value setting unit includes a face-dependent density correction using an average density of the face region as a variable. Deriving a face-dependent density correction value based on a value model equation, weighting the reference density correction value and the face-dependent density correction value with a weighting factor based on the average density and the face area size, and the appropriate density correction value The point is to correct it.

  According to the above-described configuration, the reference density correction value obtained from the characteristics of the entire original image and the face-dependent density correction value based on the average density of the face area are fused, so that not only the entire image but also the face of the person who is the subject. When obtaining an appropriate density correction value also taking into account the area, the reference density correction value and the face-dependent density correction value are weighted by a weighting factor based on the average density of the face area and the face area size, and the appropriate density is calculated. Since the correction value is corrected, the degree of fusion can be adjusted based on the ratio of the face area in the original image and the average density thereof, and appropriate density correction can be performed for the entire image and the face area of the subject. It becomes like this. For example, it is possible to reduce the probability that an unfavorable correction is made such that the density of the entire image is largely corrected based on a face area 140 that is clearly not the main subject detected in a small area as shown in FIG. It will be possible.

  The weighting coefficient is obtained by a product of a density coefficient set based on the average density, an average value of size coefficients set based on the face area size, and a preset reference weighting coefficient.

When obtaining a weighting factor for weighting calculation, the weighting factor is obtained by multiplying the density coefficient set based on the average density by the average value of the size coefficient set based on the face area size and a preset reference weighting coefficient. As a result, the density correction value can be obtained appropriately.
In order to achieve the above object, the first characteristic configuration of the image processing method according to the present invention is the reference density correction set based on the entire image characteristics corresponding to the original image data as described in claim 4. A density correction curve generating step for generating a density correction curve based on the value; a face area detecting step for detecting a face area of a subject included in the original image data; and the face area information detected in the face area detecting step. A density correction value setting step for correcting the reference density correction value based on the density correction curve for correcting the density of the original image data based on the appropriate density correction value set by the density correction value setting step. In the image processing method to be generated, in the density correction value setting step, the face area size detected based on the average density and face area size detected in the face area detection step. It lies in correcting the quasi density correction value to the proper density correction value.

  As described above, according to the present invention, it is possible to provide an image processing apparatus and an image processing method that can appropriately determine the effectiveness of correction of density or the like based on a face region included in an image.

  Embodiments of a photographic image processing apparatus incorporating an image processing apparatus according to the present invention will be described below. As shown in FIG. 2, the photographic image processing apparatus 1 includes a photographic printer 2 that performs an exposure process on the photographic paper P based on output image data and develops the exposed photographic paper, and a developed photographic film F. A media driver 32 that reads image data from an image data storage medium M such as a memory card that stores image data taken by a film scanner 31 or a digital still camera that reads an image from the camera, a general-purpose computer as a controller 33, and the like The print data is set and inputted with the print order information for the inputted photographic image as the original image, and includes an operation station 3 for performing various image correction processes, and the print data edited from the original image by the operation station 3 Is output to the photographic printer 2 to produce a desired photographic print. That.

  As shown in FIGS. 2 and 3, the photographic printer 2 has two systems of photographic paper magazines 21 containing roll-shaped photographic paper P, and photographic paper P drawn from the photographic paper magazine 21 with a predetermined print. A sheet cutter 22 that cuts into a size; a back print unit 23 that prints print information such as a frame number on the back of the cut photographic paper P; an exposure unit 24 that exposes the photographic paper P based on the print data; A development processing unit 25 including a plurality of processing tanks 25a, 25b, and 25c filled with processing solutions for developing, bleaching, and fixing the exposed photographic paper P is disposed along the transport path of the photographic paper P. The laterally-feeding conveyor 26 that discharges the photographic paper P that has been dried after the development process, and the sheet-paper (photo print) P that is stacked on the laterally-feeding conveyor 26 is sorted in order units. Configured to include the data 27.

  The exposure unit 24 receives a laser beam bundle of RGB three colors modulated based on the print data in the main scanning direction orthogonal to the conveyance direction with respect to the photographic paper P conveyed in the sub-scanning direction by the conveyance mechanism 28. An exposure head 24a for outputting and exposing is accommodated.

  A transport mechanism 28 including a plurality of roller pairs that transport the photographic printing paper P at a process speed corresponding to the exposure unit 24 and the development processing unit 25 disposed along the transport path is disposed before and after the exposure unit 24. Is provided with a chucker-type transport mechanism 28a capable of transporting photographic paper P in multiple rows.

  The controller 33 provided in the operation station 3 is installed with an application program that operates under the control of a general-purpose operating system and executes various controls of the photographic processing apparatus 1, and a monitor 34 as an operation interface with the operator. A keyboard 35, a mouse 36, and the like are connected.

  The photographic processing process executed by the cooperation of the hardware and software of the controller 33 will be described in functional blocks. As shown in FIG. 4, photographic image data read by the film scanner 31 and the media driver 32 is received. An image input unit 40 that performs predetermined preprocessing and transfers it to a memory 41, which will be described later, and print order information and image editing information are displayed on the screen of the monitor 34, and an operation for inputting necessary data for them. A graphic user interface unit 42 that generates a graphic operation screen for displaying an icon or generates various control commands based on an input operation from the keyboard 35 or mouse 36 to the displayed graphic operation screen, and the image input Photos transferred from the section 40 A memory 41 in which image data and photographic image data after correction processing by an image processing unit 47 (to be described later), correction parameters at that time, and set print order information are stored in a predetermined area, and print order information An order processing unit 43 for generating image data, an image processing unit 47 for performing density correction processing and contrast correction processing for each photographic image data stored in the memory 41, and display commands from the graphic user interface unit 42. A display control unit 46 having a video RAM for displaying the image data and various input / output graphic data developed in the memory 41 on the monitor 34 and the final correction after the various correction processes are completed. Print data for generating print data for outputting an image to the photo printer 2 A generating unit 44, and the like formatter 45 which converts the final corrected image according to customer orders to a file format for writing in a storage medium such as a CD-R.

  The film scanner 31 is configured to operate in two modes: a pre-scan mode that reads an image recorded on the film F at a high speed although it is a low resolution, and a main scan mode that reads a high resolution at a low speed. Various correction processes are performed on the low-resolution image read in the can mode, and the final resolution for the high-resolution image read in the main scan mode based on the correction parameters stored in the memory 41 at that time. Correction processing is executed and output to the printer 2.

  Similarly, the image file read from the media driver 32 includes a high-resolution captured image and its thumbnail image, and various correction processes described later are performed on the thumbnail image. Based on the stored correction parameters, a final correction process is performed on the high-resolution captured image. When the image file does not include a thumbnail image, the image input unit 40 generates a thumbnail image from the high-resolution captured image and transfers it to the memory 41. In this way, the calculation load of the controller 33 is reduced by executing various editing processes that are frequently trial and error on low-resolution images.

  As shown in FIG. 1, the image processing unit 47 includes a density correction processing unit 10 that performs density correction processing on input original image data, and a distortion correction unit 15 that corrects distortion caused by the photographing lens. And a sharpening processing unit 16 that enhances the edges of the image and reduces noise, a color correction processing unit 17, and an enlargement / reduction processing unit 18 that converts the image size to the size of the photo print. .

  The density correction processing unit 10 includes a density correction curve generation unit 11 that generates a density correction curve based on a reference density correction value set based on all image characteristics corresponding to the original image data, and the original image data. A face area detection unit 12 that detects a face area of the included subject, a density correction value setting unit 13 that corrects the reference density correction value based on the face area information detected by the face area detection unit 12, and the density A contrast correction unit 14 that performs contrast correction on the density correction curve generated by the correction curve generation unit 11 is provided.

  The density correction value setting unit 13 performs face-dependent density correction based on a reference density correction value setting unit 130 that sets the reference density correction value and a face-dependent density correction value model expression that uses the average density of the face area as a variable. A face-dependent density correction value setting unit 131 for deriving a value; the reference density correction value and the face-dependent density correction value are weighted by a weighting factor based on the average density and the face area size to obtain the appropriate density correction value; It is configured to include a weighting calculation unit 134 and the like for correcting, and configured to correct the reference density correction value to ensure better gradation when the original image data includes a human face area. ing.

  The reference density correction value setting unit 130 sets a reference density correction value Gamma of the original image data in accordance with a function stored in advance [Equation 1].

Here, as shown in FIG. 5, the Maxg is the maximum density value of the original image data, that is, the density value of the brightest pixel, and the Ming is the density value of the original image data. The minimum value, that is, the darkest pixel density value, and the Mass is a density value that is an average density of the original image data. The Maxk is the maximum value of the density setting value in the original image data. For example, when the density value is set between 0 gradation and 255 gradation in 8 bits, Maxk is set to 255. The Mink is the minimum density setting value in the original image data. For example, the Mink is set to 0 when the density value is set between 0 gradation and 255 gradation in 8 bits.
The reference density correction value Gamma can be configured to be appropriately set via the keyboard 35 or mouse 36 by an operator who visually determines the original image displayed on the monitor 43.
The density correction curve generation unit 11 stores in advance based on the reference density correction value Gamma when the face area detection unit 12 determines that a human face area is not detected in the subject. In accordance with the function shown in [Equation 2], the density is embodied as a look-up table for converting the input density value Nin (i) into an output density value Nout (i) corresponding to the reference density correction value Gamma. A correction curve is generated (i = 0, 1, 2,... 255 (for 8-bit data)).

Here, the constant L is a target gradation setting width after density correction processing of the original image data. For example, when the output image data is set by 8-bit data, the target gradation setting width is 255. The output density value Nout (i) is output as a value from 0 to 255.
That is, as shown in FIG. 6, when the reference density correction value Gamma is set to a value larger than 1 by the reference density correction value setting unit 130, the density correction curve generation unit 11 brightens the original image data. A density correction curve for performing density correction processing is generated so that, when the reference density correction value Gamma is set to a value smaller than 1, a density correction curve for performing density correction processing is generated so that the original image data becomes dark. It is configured as follows.

  Returning to the description of the density correction value setting unit 13, the face region detecting unit 12 includes a face region extracting unit 120 that extracts a human face region as a subject from the original image data, and pixel data of the extracted face region. An average density calculation unit 121 that calculates an average density based on the above and a face area size calculation unit 122 that calculates a face area size based on the number of pixels of the extracted face area.

  For example, the face area extraction unit 120 determines whether or not a contour based on a density edge or a color edge extracted from the original image data is a face area. It is realized using a known technique such as detection based on a pattern recognition technique by evaluating the degree of coincidence with a plurality of element arrangement patterns such as ears. It should be noted that the extraction process in the face area extraction unit 120 is not only configured to be automatically performed as described above, but the operator manually operates the original image displayed on the screen of the monitor 34 with the mouse 36 or the like. It may be configured to extract the area designated by the input as a face area.

  The average density calculation unit 121 derives a component average value (R + G + B) / 3 of each RGB pixel data constituting the face region extracted by the face region extraction unit 120, and further, based on the derived pixel average value. An average value of all pixels constituting the face area is obtained as an average density of the face area. The average density in the present invention is not limited to a value obtained based on such RGB pixel data component average value (R + G + B) / 3. For example, the RGB color system is converted into a YCC color system. The luminance average obtained based on the obtained luminance Y is also a concept that is widely included in the average density.

  In obtaining the average density, the average density of the skin area may be obtained as the average density of the face area after removing areas other than the skin area from the extracted face area based on the hue or the like. Calculates the average density for the extracted face region.

  The face area size calculation unit 122 calculates the number of pixels of the face area data extracted by the face area extraction unit 120 as a face area size. Also in this case, as shown in FIG. 7, when a plurality of face areas are extracted from the original image obtained by photographing a plurality of persons by the face area extraction unit 120, areas C to C are extracted from all the extracted face areas A. Is calculated as the face area size.

  As described above, the face-dependent density correction value setting unit 131 is a face-dependent density correction value based on a face-dependent density correction value model equation using the average density of the face area detected by the face area detection unit 12 as a variable. Gamma (F) is derived. The model formula visually evaluated a correction image based on a density correction curve based on a density correction value obtained by changing the reference density correction value for a large number of sample images obtained by shooting various subjects under various shooting conditions. As a result, the correction function F1 is obtained by statistically processing the distribution of density correction values determined to have corrected the average density of the face area and the face area at that time to an appropriate density.

Shown in FIG. 8, the correction function is an example of F1, the face face dependent density correction value any average density with respect to _{D Favr} area Gamma (F) _{is, Gamma (F) = F1 (} D Favr ). Here, the average density of the face region is shown as a value normalized with an 8-bit image.

  As can be understood from FIGS. 6 and 8, when the average density of the face region becomes small, that is, darkens, the face-dependent density correction value Gamma (F) becomes larger than 1, and such face-dependent density correction value Gamma. According to the density correction curve generated based on (F), the density correction processing is performed so that the original image data becomes brighter, and the average density of the face area increases, that is, the face-dependent density correction value Gamma (F ) Becomes a value smaller than 1, and according to the density correction curve generated based on such face-dependent density correction value Gamma (F), density correction processing is performed so that the original image data becomes dark. It becomes a characteristic.

  The weighting calculation unit 134 corrects the reference density correction value Gamma by performing a weighting calculation on the reference density correction value Gamma and the face-dependent density correction value Gamma (F) described above with a predetermined weighting factor, thereby adjusting the appropriate density correction value. Gamma (R) is calculated, and the main subject is corrected by correcting the original image with the density correction curve generated by the density correction curve generation unit 11 based on the appropriate density correction value Gamma (R). The face area of a person is corrected so as to show a preferable gradation.

  Any value may be adopted as the appropriate density correction value when the reference density correction value Gamma and the face-dependent density correction value Gamma (F) are substantially equal. For example, when the brightness of the face area is high, The face area and background of the original image when the density correction value Gamma is corrected in a brighter direction or when the brightness of the face area is low and the reference density correction value Gamma is corrected in a darker direction. It is necessary to adjust the density correction value so that both areas have a relatively appropriate density.

  As the predetermined weighting factor described above, a fixed value evaluated as an appropriate value for fusing both density correction values in a balanced manner based on various image samples in such a case is adopted. When correction is performed based on the appropriate density correction value obtained by weighting both density correction values, appropriate density correction is performed on many original images.

  However, when the correction based on the average density of the face area obtained from the original image is performed, there is no guarantee that the face area of the main subject is always accurately detected by the face area detection unit 12, for example, wearing sunglasses When a person is a subject, it cannot be detected accurately because the eyes are not recognized, etc., and even when the face is overlapped, it may not be recognized because it does not match the predetermined pattern, etc. In some cases, a pattern such as a person's face attached to clothes is mistakenly detected as a face. Conversely, when the face of a person who is the main subject is not recognized, the face reflected in a small area of the background may be recognized.

  In such a case, when the original image is corrected with a density correction curve based on the appropriate density correction value Gamma (R) corrected based on the fixed weighting factor, the density of the face area of the main subject is inappropriate. There is also a possibility that it will be corrected.

  Therefore, in the present invention, the density correction value setting unit 13 corrects the reference density correction value based on the average density and face area size of the face area detected by the face area detection unit 12, that is, The appropriate density correction value Gamma (R) is obtained by weighting the reference density correction value Gamma and the face-dependent density correction value Gamma (F) with a weighting factor set based on the average density and the face area size of the face area. It is comprised so that it may correct | amend.

  This will be described in detail below. The density correction value setting unit 13 has a density coefficient setting unit 132 that sets a density coefficient that is a degree of effectiveness based on the average density of the face area, and a size that sets a size coefficient that is the degree of effectiveness based on the face area size. A coefficient setting unit 133; a reference weight coefficient storage unit 136 for storing a preset reference weight coefficient; and a weighting coefficient for calculating an appropriate weighting coefficient r from the density coefficient, the size coefficient, and the reference weighting coefficient A calculation unit 135 is further provided, and an appropriate density correction value Gamma (R) is obtained by the weighting calculation unit 134 based on the appropriate weighting factor r calculated by the weighting factor calculation unit 135.

  The density coefficient setting unit 132 calculates an average density of various face regions obtained for a large number of sample images obtained by photographing various subjects under various photographing conditions, and the reference density correction value based on the average density. A look-up table representing a density weight function F2 as shown in FIG. 9 obtained by statistically processing the relationship with the visual evaluation of the corrected image by the density correction curve generated based on the corrected value is provided and corrected. When the average density of the face area of the target original image is input, the density coefficient corresponding to the average density is output.

  The density weight function F2 is defined as a value obtained by normalizing the average density of the face area with an 8-bit image, and the effectiveness from the minimum value 0 to the maximum value 1 with respect to the average density of the input face area. This is a function for outputting a density coefficient indicating the degree, and shows 1 when the average density of the face area is larger than the upper limit (about 0.2 in this embodiment), but gradually decreases when the average is lower than the upper limit. The lower limit value (about 0.1 in this embodiment) is 0. This means that the smaller the value of the density coefficient, the smaller the weight of the face-dependent density correction value Gamma (F) in the weighting calculation process described later. That is, the influence of the face area on the original image is reduced. Note that the characteristics of the density weight function F2 are not limited to those described above, and can be changed and set as appropriate based on the characteristics of a plurality of original images as samples. A density weight function F2 may be set.

  The size coefficient setting unit 133 determines the reference based on various face area sizes obtained from a large number of sample images obtained by photographing various subjects under various photographing conditions and the average density of the face areas at that time. A look-up table representing a size weight function F3 as shown in FIG. 10 obtained by statistically processing the relationship between the corrected image and the visual evaluation of the corrected image based on the density correction curve generated based on the value obtained by correcting the density correction value. When the size of the face area of the original image to be corrected is input, a size coefficient corresponding to the size is output.

  The size weight function F3 is defined as a value normalized by the ratio of the pixel size of the face area to the original image size of about 100,000 pixels (384 × 256 pixels), and for an original image having an arbitrary number of pixels. The size weighting coefficient can be obtained from the size weighting function F3 based on the ratio of the number of pixels in the face area to the total number of pixels, and the minimum value 0 for the pixel size of the input face area Is a function that outputs a size coefficient indicating the degree of effectiveness from 1 to the maximum value 1.

  As shown in FIG. 10, when the pixel size of the face area is larger than the upper limit value (about 0.7% in the present embodiment), it shows 1, but when it falls below the upper limit value, it gradually becomes smaller and the lower limit value (this In the embodiment, it becomes 0 at about 0.6%). This means that the weight of the face-dependent density correction value Gamma (F) decreases in the weighting calculation process described later as the size coefficient value is smaller in the upper and lower limit range. That is, the influence of the face area on the original image is reduced. Note that the characteristics of the size weight function F3 are not limited to those described above, and can be changed and set as appropriate based on the characteristics of a plurality of sample original images. A plurality of size weighting functions F3 may be set based on populations having different light types, intensities, directions, exposure amounts, and the like. However, it goes without saying that the density weight function F2 and the size weight function F3 need to be generated based on a common population (sample image).

  As a result of trial and error, the value 0.6 is stored as the reference weight coefficient stored in the reference weight coefficient storage unit 136 as a result of trial and error. However, the present invention is not limited to this value. , The type, intensity, orientation, exposure amount, etc.) of the photographing light are values set appropriately based on different populations. The reference weight coefficient is a fixed value evaluated as an appropriate value for fusing both density correction values in a well-balanced manner based on various image samples as described above.

  The weight coefficient calculation unit 135 calculates the average value of the density coefficient and the size coefficient obtained for the original image to be corrected (hereinafter referred to as “coefficient average value”), and calculates the coefficient average value. The product of the reference weight coefficients is calculated as the appropriate weight coefficient r. Here, the coefficient average value is obtained as an arithmetic average value of the density coefficient and the size coefficient, but may be a geometric average value.

  The weighting calculation unit 134 performs weighting calculation as shown in [Equation 3] based on the reference density correction value Gamma, the face-dependent density correction value Gamma (F), and the obtained appropriate weight coefficient r. The reference density correction value Gamma is corrected to an appropriate density correction value Gamma (R).

  As apparent from [Equation 3], when the coefficient average value becomes 0, the value of the appropriate weight coefficient r becomes 0, and the correction of the reference density correction value by the average density of the face region is substantially performed. Without being performed, a density correction curve is generated based on the reference density correction value Gamma.

Based on the appropriate density correction value Gamma (R) obtained by the density correction value setting unit 13 in this way, the contrast correction processing unit 14 is applied to the density correction curve generated by the density correction curve generating unit 11. Thus, contrast correction is performed.
For example, the contrast correction processing unit 14 converts the input density value Nin (i) of the original image data into output densities corresponding to the contrast correction values Cr1 and Cr2 according to [Equation 4] and [Equation 5] stored in advance. A contrast correction curve is generated as a lookup table for converting the density value to the value Cout (i).

  Specifically, in accordance with [Equation 4], with respect to the highlight area of the original image data in which the input density value Nin (i) is equal to or greater than a predetermined density threshold value Nth, as shown in FIG. A contrast correction curve to be subjected to contrast correction is generated, and the input image density value Nin (i) of the original image data having a predetermined density threshold value Nth or less as shown in FIG. A contrast correction curve for performing a contrast correction process on the shadow area is generated.

  The contrast correction values Cr1 and Cr2 are calculated based on the reference density correction value Gamma or the appropriate density correction value Gamma (R) set by the density correction value setting unit 14, and when the contrast correction value Cr1 is large. The look-up table corrects the contrast of the highlight area higher, and the look-up table corrects the contrast of the shadow area higher as the contrast correction value Cr2 becomes negative.

  The contrast correction processing unit 14 performs a fusion process on the generated contrast correction curve and the density correction curve, and generates a fusion curve as a lookup table capable of executing the density correction process and the contrast correction process simultaneously. That is, as shown in FIG. 12, when the original image data is input as an input density value Nin (i), the fusion curve has an output density value Cout (Nout (i) via the original curve and the contrast correction curve. ) Is generated as a lookup table for density value conversion.

  Hereinafter, the density correction processing by the density correction processing unit 10 will be described based on the flowchart of FIG. When thumbnail image data read in the prescan mode by the film scanner 31 or read from the media driver 32 is input to the memory 41 (S1), the reference density correction value setting unit 130 reads the original image. A density histogram is generated in the data, and the maximum density value of the original image data, that is, the density value Maxg of the brightest pixel, and the minimum density value of the original image data, that is, the density of the darkest pixel. A value Ming and a density value Mass which is an average density of the original image data are calculated, and a reference density correction value Gamma is calculated based on the [Equation 1] (S2).

  Subsequently, the face area extraction unit 120 executes a face area extraction process in the original image data (S3). At this time, if a face area is not extracted from the original image data by the face area extracting unit 120, that is, a landscape image or the like in which no person is present in the original image (S4), the density correction curve generation is performed. The unit 11 generates a reference density correction curve based on the reference density correction value Gamma (S16). Subsequently, the contrast correction processing unit 14 generates a density correction curve in which a contrast correction curve is merged with the reference density correction curve (S17), and density correction processing of original image data based on the density correction curve. The result is displayed on the monitor 34 (S18).

  On the other hand, if a face area is detected in the original image data by the face area extraction unit 120 in step S4 (S4), the average density calculation unit 121 determines the face area based on the detected face area data. The average density is calculated (S5), and the face area size calculation unit 122 calculates the face area size (S6).

  Subsequently, the face-dependent density correction value setting unit 131 calculates a face-dependent density correction value Gamma (F) based on the average density of the face area (S7), and the density coefficient setting unit 132 calculates the density coefficient. Then, the size coefficient is calculated based on the face area size by the size coefficient setting unit 133 (S9).

  If the calculated values of the density coefficient and the size coefficient are both 0 (S10), the results set and calculated in the face determination process from step S3 to step S9 are not used for density correction. (S14), a reference density correction curve based on the reference density correction value Gamma is generated (S16). Subsequently, in the contrast correction processing unit 14, the contrast correction curve is merged with the reference density correction curve. A density correction curve is generated (S17), density correction processing of the original image data is performed based on the density correction curve, and the result is displayed on the monitor 34 (S18).

  On the other hand, when the value of the density coefficient or the size coefficient is not 0 (S10), the weight coefficient calculation unit 135 calculates an average value (coefficient average value) of the density coefficient and the size coefficient (S11), The product of the coefficient average value and the reference weight coefficient stored in advance in the reference weight coefficient storage unit 134, that is, an appropriate weight coefficient r is calculated (S12).

  The weighting calculation unit 134 calculates the reference density correction value Gamma and the face-dependent density correction value Gamma (F) by the weighting calculation using the appropriate weighting factor r, that is, according to the above [Equation 3] (S13). The calculation result is calculated as an appropriate density correction value Gamma (R) (S15).

  The density correction curve generation unit 11 generates an appropriate density correction curve based on the appropriate density correction value Gamma (R) (S16). Subsequently, the contrast correction processing unit 14 applies the reference density correction curve to the reference density correction curve. A density correction curve in which the contrast correction curves are merged is generated (S17), density correction processing of the original image data is performed based on the density correction curve, and the result is displayed on the monitor 34 (S18).

Thus, the density correction curve obtained in step S17 is stored in the memory 41 as a density correction parameter, and then read in the main scan mode by the film scanner 31 or read from the media driver 32. Density correction is performed on the resolution image data by the stored density correction parameter.
Note that the above-described embodiment is merely an example of the present invention, and it is needless to say that the specific configuration and the like of each block can be changed and designed as appropriate within the scope of the effects of the present invention.

Explanatory drawing of functional block configuration in image processing unit Explanatory drawing of the external configuration of the photographic image processing apparatus Illustration of photo printer Explanatory drawing of functional block configuration of photographic image processing apparatus Explanatory diagram of density histogram related to density correction value calculation Explanatory drawing of density value transition in density correction processing Illustration of a photo with multiple people Explanatory drawing of the graph which is an example of the model formula for deriving the face dependent density correction value Explanatory drawing of a graph that is an example of a model formula for deriving a concentration coefficient Illustration of a graph that is an example of a model formula for deriving a size factor (A) Contrast correction curve in highlight area, (b) Contrast correction curve in shadow area Illustration of fusion curve Flow chart for explaining the operation of the image processing unit Illustration of a photo when a person is not a subject

Explanation of symbols

1: Photo image processing device 10: Density correction processing unit 13: Density correction value setting unit 12: Face area detection unit 11: Density correction curve generation unit 14: Contrast correction processing unit 47: Image processing unit 130: Reference density correction value setting Unit 131: Face-dependent density correction value setting unit 132: Density coefficient setting unit 133: Size coefficient setting unit 135: Weight coefficient calculation unit 134: Weighting calculation unit

Claims (4)

A density correction curve generation unit that generates a density correction curve based on a reference density correction value that is set based on all image characteristics corresponding to the original image data, and detects a face area of the subject included in the original image data An appropriate density set by the density correction value setting unit, comprising: a face area detection unit; and a density correction value setting unit that corrects the reference density correction value based on the face area information detected by the face region detection unit. An image processing apparatus for generating a density correction curve for correcting the density of the original image data based on a correction value,
The density correction value setting unit corrects the reference density correction value to the appropriate density correction value based on the average density and face area size of the face area detected by the face area detection unit.   The density correction value setting unit derives a face-dependent density correction value based on a face-dependent density correction value model expression using an average density of the face region as a variable, and the reference density correction value, the face-dependent density correction value, The image processing apparatus according to claim 1, wherein a weighting calculation is performed using a weighting coefficient based on the average density and the face area size to correct the density to the appropriate density correction value.   The weighting factor is obtained by a product of a density coefficient set based on the average density and an average value of a size coefficient set based on the face area size and a preset reference weighting coefficient. Image processing device. A density correction curve generating step for generating a density correction curve based on a reference density correction value set based on all image characteristics corresponding to the original image data, and detecting a face area of the subject included in the original image data An appropriate density set by the density correction value setting step, comprising: a face area detection step; and a density correction value setting step for correcting the reference density correction value based on the face area information detected in the face area detection step. An image processing method for generating a density correction curve for correcting the density of the original image data based on a correction value,
In the image processing method, the density correction value setting step corrects the reference density correction value to the appropriate density correction value based on an average density and a face area size of the face area detected in the face area detection step.

Images