JP2007200069A - Photographic image processing method and device thereof - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a photographic image processing method and its device, capable of acquiring a photographic print reflecting the photographic intention, while detecting a facial image of a person contained in an original image. <P>SOLUTION: This photographic image processing device is equipped with a facial image detection means 51 for detecting the facial image of the person from original image data, a photographic scene determination means 53 for determining that the image is photographic scene of at least a portrait picture, a commemorative picture or a landscape picture, based on a detection result by the face image detection means 51, and a correction processing means 54 for performing correction processing of the original image data, based on a determination result by the photographic scene determination means 53. The device is also equipped with an attitude determination means 52 for determining, to which direction of vertical and horizontal directions of the original image the attitude of the detected face image, is faced. The photographic scene determination means 53 sets a facial image detection region, based on the attitude of the face image determined by the attitude determination means 52, and determines the photographic scene, based on the area ratio of the face image existing in the facial image detection region. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  According to the present invention, a face image detection process for detecting a human face image from input original image data, and at least a portrait photograph and a photograph other than a portrait photograph are distinguished based on the detection result of the face image detection process. The present invention relates to a photographic image processing method and apparatus including a photographic scene determination step for determining a scene, and a correction processing step for correcting the original image data based on a determination result in the photographic scene determination step.

  When a digital image taken with a film scanner or a digital image taken with a digital still camera is output to the photographic printer as original image data, the input system for the film scanner or digital still camera, or the original image data There is a problem that the image quality of the output photograph deteriorates due to the inherent cause of each of the image processing system such as enlargement / reduction processing and the output system such as a photographic printer, which is damaged by a poorly focused image or enlargement / reduction processing etc. Various sharpening treatment methods have been proposed to restore the sharpness.

  In general, there is a tendency to prefer a print image in which sharpening strength is set to be higher in the case of landscape photography, and in which sharpening strength is set to be lower in the case of portrait photography. As an image processing method capable of estimating shooting scenes such as photographs, ID photos, portraits, snapshots, group photos, etc., and performing image processing suitable for each shooting scene, a face area is detected by face detection means, An image processing method is proposed in which an image processing condition parameter is generated based on the number of detected face areas and the size information of the largest face area, and image processing is performed based on the image processing condition parameter. Has been.

  Further, in Patent Document 2, a person's face is detected from an input image to determine the presence or absence of a person. When there is no person, it is determined to be a landscape photograph image. When the face area is greater than or equal to a predetermined percentage of the screen and this number is not less than the predetermined number, it is determined as a person / commemorative photo image. In some cases, an image discrimination method for determining a portrait image has been proposed.

JP 2005-141523 A JP 2005-173932 A

  However, according to the above-described prior art, since the shooting scene is determined based on the number and size of face images detected from the entire area of the original image, a plurality of other face images other than the subject of interest are included. If it is included, or if another face image larger than the subject of interest is included, image processing such as sharpening processing that reflects those effects will be performed, so photo prints contrary to the shooting intention There is a disadvantage that is generated.

  In view of the above-described conventional drawbacks, the present invention provides a photographic image processing method and apparatus capable of obtaining a photographic print reflecting a shooting intention while detecting a face image of a person included in an original image. Objective.

  In order to achieve the above-mentioned object, the first characteristic configuration of the photographic image processing method according to the present invention is that, as described in claim 1 of the document of the claims, a human face image is input from the input original image data. A face image detection step to detect, a shooting scene determination step of determining a shooting scene by distinguishing at least a portrait photo and a photo other than the portrait photo based on the detection result of the face image detection step, and the shooting scene determination step A photographic image processing method comprising a correction processing step for correcting the original image data based on a determination result, wherein the posture of the face image of the person detected in the face image detection step is either vertical or horizontal. A posture determination step for determining whether the image is along a direction, and the photographing scene determination step includes a face image detection region based on the posture of the face image determined in the posture determination step Set lies in that the photographic scene is determined based on the area ratio of the face image existing in the face image detection area.

  In general, when taking a portrait photograph, the subject is located in the center of the image and the portrait is vertically oriented with respect to the frame image divided by rectangles having different aspect ratios. When taking a commemorative photo, the subject is positioned in the center of the image so that the background appears to the left and right, and the horizontal orientation of the frame image is divided into rectangles with different aspect ratios. There are many cases where shooting is performed. This tendency becomes more prominent when a plurality of people are photographed. In addition, when taking a landscape photograph, it is often the case that a landscape is taken up and down with respect to a frame image divided by rectangles having different aspect ratios.

  According to the above-described configuration, in view of such a tendency, it is determined whether the posture of the person's face image is along the vertical or horizontal direction of the original image by the posture determination step, and the posture determination step is performed by the shooting scene determination step. A face image detection area based on the posture of the face image determined in step 1, that is, an image detection area that differs depending on whether the frame image is an image having a vertical orientation or an image having a horizontal orientation. By doing so, it is possible to reliably eliminate the influence of other face images that do not conform to the shooting intention, and to appropriately select the shooting scene based on the area ratio of the face image of the subject of interest existing in the face image detection region. It will be possible to make a decision. Accordingly, it is possible to perform an optimal correction process in accordance with the photographing intention.

  In the second feature configuration, in addition to the first feature configuration described above, in the shooting scene determination step, the area ratio of the face image existing in the face image detection region is preset. Among the face images that are larger than the reference area ratio, the shooting scene is determined using the face image having the maximum size as the determination reference face image.

  According to the above-described configuration, when there is a face image in which the area ratio of the face image of the subject of interest is larger than a preset reference area ratio, it can be determined that the shooting is based on the specific gravity of the person. By using the maximum-sized face image as the determination reference face image, it is possible to appropriately determine the shooting scene.

  According to the first characteristic configuration of the photographic image processing apparatus of the present invention, as described in the third aspect of the present invention, a face image detecting unit that detects a face image of a person from input original image data and the face image detecting unit A shooting scene determination unit that determines a shooting scene by distinguishing at least a portrait photo and a photo other than the portrait photo based on the detection result, and a correction that corrects the original image data based on the determination result by the shooting scene determination unit A photographic image processing apparatus comprising processing means, comprising posture determination means for determining whether the posture of the face image of the person detected by the face image detection means is along the vertical or horizontal direction of the original image; The shooting scene determination unit sets a face image detection region based on the posture of the face image determined by the posture determination unit, and detects a face image existing in the face image detection region. It lies in that the photographic scene is determined based on the product ratio.

  In the second feature configuration, as described in claim 4, in addition to the first feature configuration described above, the shooting scene determination unit sets the area ratio of the face image existing in the face image detection region in advance. The photographic scene is determined using a face image having a maximum size among the face images larger than the determined reference area ratio as a determination reference face image, and the correction processing unit determines the photographic scene determined by the photographic scene determination unit and the determination. The original image data is corrected based on the area ratio of the reference face image.

  As described above, according to the present invention, it is possible to provide a photographic image processing method and apparatus capable of obtaining a photographic print reflecting a shooting intention while detecting a face image of a person included in an original image. I can do it now.

  The photographic image processing method and apparatus according to the present invention will be described below. As shown in FIGS. 1 and 2, the digital photographic image processing apparatus includes a film scanner 1a that reads a photographic image from a filmed negative film (hereinafter simply referred to as “film”) F, and a digital still camera. The image data input unit 1 includes a media driver 1b corresponding to various card-type memories M such as an SD card or a memory stick in which captured image data is stored, and a hard disk or the like that stores the input image data. An image data storage unit 2, a monitor 3 for displaying an image based on the image data, an operation input unit 4 having a keyboard and a mouse, and the operation input unit 4 for the image displayed on the monitor 3 The image processing unit 5 that edits the image data based on various operations, and the photographic paper P is exposed based on the data after the image processing. A photographic printer 6 for generating a photographic print Te, the system controller 7 controls the individual blocks of the above as a system (hereinafter referred to as "the controller 7".) Configured with a.

  The film scanner 1 a is recorded on the illumination optical system 10 that irradiates the illumination light for reading onto the film F, the film transport unit 11 that transports the film F, and the film F transported by the film transport unit 11. An image reading unit 12 for reading the frame image, and a scanner control unit 13 for controlling an image reading process by the illumination optical system 10, the film transport unit 11, and the image reading unit 12.

  The illumination optical system 10 includes a rod-shaped halogen lamp 10a arranged along a main scanning direction orthogonal to a sub-scanning direction (indicated by an arrow in FIG. 2) that is a conveyance direction of the film F, and A light control filter 10b that adjusts the color distribution of the light beam, a cylindrical lens 10c that collects the light beam in a slit shape, a diffusion plate 10d that makes the intensity distribution uniform, and a narrow slit 10e are configured. The

  The film transport unit 11 is driven by a transport motor (not shown), and includes a plurality of transport roller pairs 11a that transport the long film F toward the film projection unit directly below the slit 10e at a predetermined speed. The

  The image reading unit 12 includes a condenser lens, a CCD line sensor, a sample hold circuit, an A / D converter, and the like, and slit light from the illumination optical system 10 that has passed through the film F is collected. An analog signal formed on the CCD line sensor by the optical lens and read by the CCD line sensor is converted to digital data by the A / D converter. The CCD line sensor is composed of three lines of line sensors each provided with a color filter that selectively transmits light of each of the R component, G component, and B component of the transmitted light of the film. As the film F is conveyed, each frame image is separated into R component, G component, and B component color components and read.

  The photographic printer 6 includes a paper magazine 60 in which roll-shaped photographic paper P is accommodated, a plurality of photographic paper transport rollers 61 that pull out and transport the photographic paper P from the paper magazine 60, and a motor that drives the transport roller 61. 62, a fluorescent beam type print head 63 that exposes the photosensitive surface of the conveyed photographic paper P, a development processing unit 64 that performs development, bleaching, and fixing processes on the exposed photographic paper P, and development processing. The photographic paper P drawn out from the paper magazine 60 includes a drying unit 65 that transports the photographic paper P while drying, and a discharge unit 66 that discharges the dried photographic paper P as a final print. The paper is cut into a predetermined print size by a cutter (not shown) disposed either before or after the development processing and output to the discharge unit 66.

  The print head 63 includes R, G, and B laser light sources and a deflection optical system that scans and exposes the photographic paper P by deflecting light beams output from the laser light sources, and the film scanner 1a. The photographic image is exposed on the photographic paper P by adjusting and controlling the amount of light output from each laser based on the R component, G component, and B component pixel data of the image data read and edited via Is done.

  The controller 7 includes a CPU, a ROM, a RAM used as a data processing area, a RAM used for image data editing, hardware including peripheral circuits, and a CPU stored in the ROM. If it is divided into functional blocks related to the present invention and is composed of software consisting of programs to be executed, as shown in FIG. 3, a graphic including soft switches and the like on a window displayed on the monitor 3 A graphic user interface unit (hereinafter referred to as “GUI unit”) 7 a that generates a control command corresponding to a user operation by the operation input unit 4 via the operation screen display or the graphic operation screen, and the monitor 3 Are read from the video memory 7b and the image data storage unit 2. An image processing memory 7d to which the outputted image is loaded and subjected to various correction processes; an image file editing section 7c for editing the processed image data into an image file for writing to a medium such as a CD-R; A print data conversion unit 7e for converting the corrected data into output data corresponding to the photographic printer 6 is provided.

  The image processing unit 5 is composed of software for editing a target image with a predetermined algorithm and hardware having an image processing processor, and detects a human face image from image data loaded in the image processing memory 7d. A face image detecting means 51 for performing the determination, a posture determining means 52 for determining whether the posture of the face image of the person detected by the face image detecting means 51 is in the vertical or horizontal direction of the original image, and the face image detecting means. Based on the detection result by 51, a shooting scene determination means 53 for determining at least a portrait photograph, a commemorative photograph, or a landscape photograph, and the image data based on the determination result by the shooting scene determination means 53 And a correction processing means 54 for correcting the above. The correction processing means 54 includes a sharpening processing means 54a for sharpening the image data, a color correction means 54b for adjusting a color balance for the sharpened image data, and a gradation. It is configured to include gradation correction means 54c for adjusting.

  When a film reading command is sent from the controller 7, the scanner control unit 13 turns on the halogen lamp 10a and then drives the film transport unit 11 to transport the film F at a predetermined speed in the sub-scanning direction. Then, the frame images recorded on the film are sequentially read by the image reading unit 12, the read image data is transmitted to the controller 7, and the image data transmitted from the scanner control unit is stored in the image data storage unit 2. Is done.

  When a medium is inserted into the media driver 1 b under the control of the controller 7, image data stored in the medium is read and stored in the image data storage unit 2.

  The image data stored in the image data storage unit 2 is subjected to a predetermined correction process by the image processing unit 5, and the print data converted by the print data conversion unit 7 e is output to the photo printer 6. In the photo printer 6, the print head 63 is driven based on the input print data, and the photographic paper P exposed by the print head 63 is developed and output as a photo print.

  More specifically, in the photographic image processing apparatus, when a photographic print is generated based on an image input from the film scanner 1a, a film image is first read at a low resolution by a pre-scan operation and displayed on the monitor 3. The image quality such as the color balance of each frame image is verified with the setting processing of the print size and the number of prints by the operator via the operation input unit 4 for the displayed frame image.

  This verification operation is a series of operations in which the controller 7 and the operator proceed in an interactive manner, and the correction processing conditions by the image processing unit 5 are determined in addition to the setting of the number of prints described above. In other words, a series of correction processing such as sharpening processing, color correction processing, gradation correction processing, and the like is preliminarily determined for each shooting scene determined by the shooting scene determination processing described later on image data read at a low resolution. It is automatically executed with the specified correction conditions. Then, a low-resolution image based on the corrected image data is displayed on the monitor 3, and whether or not the correction result is appropriate is evaluated by an operator, and various inconveniences such as occurrence of a color failure occur. If it occurs, the color correction process is performed again manually, and the recorrection conditions at that time are stored in the internal memory.

  When the above-described verification operation is completed and a photographic print is output, a main scan, that is, a film image reading process at a high resolution via the film scanner 1a is performed. The various correction processes described above are executed. If necessary, the correction process is executed under the re-correction conditions set in the verification operation, and then the print data converted by the print data conversion unit 7e is transferred to the photo printer. 6 is output. The pre-scan operation is provided for the purpose of reducing the number of processing target pixels of the correction processing performed during the above-described verification operation to increase the speed, and the image file to be read for the image captured by the digital still camera The verification operation is performed on the thumbnail image attached to, and when there is no thumbnail image, the verification operation is performed on the thumbnail image generated by thinning the input image.

  Hereinafter, the shooting scene determination process will be described based on the flowchart shown in FIG.

  The image data input from the image data input unit 1 and stored in the image data storage unit 2 is developed in the image processing memory 7d in the RGB dot sequential RAW format or the RGB plane sequential RAW format in the order of the frame image unit. (SA1), all face images are detected for each frame image by the face image detecting means 51 (SA2).

  As the face image detection algorithm by the face image detecting means 51, various known algorithms can be used, for example, those disclosed in Japanese Patent Application Laid-Open No. 08-63597. That is, color feature values such as brightness, hue, saturation, chromaticity, (BR), and (GR) are obtained from the BGR value of each pixel, and the feature values of these colors are within a predetermined range. If the target pixel is included, it is determined that the target pixel is a skin color, and edge extraction is performed on an image of an area including pixels determined to be a skin color, and a predetermined size, a long axis / short axis (la / lb) ) Of a plurality of ellipse or circular face templates (the face template is binarized depending on whether it is an ellipse or a contour of a circle) and the degree of matching between the extracted edge images. When the matching degree is equal to or greater than a predetermined threshold value, the image in that region is determined to be a face image.

  It is also possible to use a pattern recognition technique that uses a neural network or the like that detects a human face image based on the face contour, eyes, nose, mouth, ears, and other patterns.

  When a face image is detected by the face image detecting means 51 (SA3), the photographing scene determining means 53 is configured so that the posture of the face image of the person detected by the face image detecting means 51 is the vertical and horizontal (normal photograph) of the original image. When the print size is taken as an example, the longitudinal direction is considered as the vertical direction.) It is determined which direction is along (SA4).

  As for the posture of the face image, for example, position information such as eyes, nose and mouth is extracted from the face image detected by the face image detecting means 51, and the relationship between the mutual positional relationship and the orientation of the original image. Can be determined based on

  Specifically, for example, the position information of both eyes is extracted, the direction perpendicular to the line connecting the eyes is set as the normal posture direction of the face image, and the longitudinal direction of the original image and the normal posture direction of the face image are parallel. Is determined that the orientation of the face image is along the vertical direction of the original image. On the other hand, when the longitudinal direction of the original image and the normal posture direction of the face image are perpendicular to each other, it is determined that the posture of the face image is along the horizontal direction of the original image.

  Further, for example, the nose and mouth position information is extracted, the direction parallel to the line connecting the nose and mouth is set as the normal posture direction of the face image, and the longitudinal direction of the original image and the normal posture direction of the face image are vertical. Is determined that the orientation of the face image is along the horizontal direction of the original image. On the other hand, when the longitudinal direction of the original image and the normal posture direction of the face image are parallel, it is determined that the posture of the face image is along the vertical direction of the original image.

  The posture of the face image is determined based on the face image having the largest area among the detected face images when a plurality of face images are detected by the face image detecting means 51. Is preferred. It is possible to appropriately determine the shooting scene.

  When the posture determination unit 52 determines that the posture of the face image of the person detected by the face image detection unit 51 is along the vertical direction of the original image (SA5). For example, as shown in FIG. 5A, a predetermined vertical width region Rt in the original image Ra is set as the face image detection region Rk (SA6). Specifically, a face width detection area is defined as a vertical width area Rt in which the short side width (width in the direction perpendicular to the longitudinal direction) of the original image is reduced to, for example, 65% around the central axis Ot. Set as Rk.

  On the other hand, if the posture determination unit 52 determines that the posture of the face image of the person detected by the face image detection unit 51 is along the horizontal direction of the original image (SA7), for example, FIG. As shown in FIG. 5, a predetermined vertical width region Ry in the original image Ra is set as the face image detection region Rk (SA8). Specifically, the lateral width region Rt in which the long side width (the width in the longitudinal direction) of the original image is reduced to, for example, 80% around the central axis Oy is set as the face image detection region Rk.

  That is, the shooting scene determination unit 53 sets the face image detection region Rk based on the posture of the face image determined by the posture determination unit 52.

  Next, as shown in FIGS. 6A and 6B, the shooting scene determination unit 53 derives the area Sf of the face image Fp existing in the set face image detection region Rk (SA9). ) And [Expression 1], the ratio Rfa of the area Sf of the face image to the area Sa of the original image Ra is calculated (SA10). As shown in FIG. 6C, the face image Fp does not exist in the set face image detection area Rk, and instead, the face image Fp exists only in an area other than the set face image detection area Rk. In this case, the ratio Rfa of the area Sf of the face image to the area Sa of the original image Ra is set to 0%.

  When the ratio Rfa is a preset reference area ratio Rth, for example, 30% or more (SA11), it is determined that the image data is a portrait photograph (SA12). When the ratio Rfa is less than the reference area ratio Rth, for example, 30% (SA11), it is determined that the image data is a commemorative photo (SA13).

  Note that the determination of the shooting scene is preferably based on the face image having the largest area when there are a plurality of face images Sf in the face image detection region Rk. That is, a scene to be photographed is determined using a face image having a maximum size as a determination reference face image among face images in which the area ratio Rfa of the face image Sf existing in the face image detection region Rk is larger than a preset reference area ratio Rth. It is preferable to do. It is possible to appropriately determine the shooting scene.

  Further, when no face image is detected by the face image detection means 51 (SA3), the shooting scene determination means 53 determines that the image data is a landscape photograph (SA14).

  In the photographic image processing apparatus, as described above, when the image data is determined by the shooting scene determination process, the correction processing unit 54 performs the image processing under a correction condition predetermined for each determined shooting scene. Correction processing is performed on the data.

  More specifically, the correction processing unit 54 performs sharpening processing of the image data by the sharpening processing unit 54a, for example, as shown on the horizontal axis of FIG. And the degree of adjustment of the color balance of the image data by the color correcting unit 54b as shown on the vertical axis of FIG. 7A, and further, the gradation as shown in FIG. 7B. A correction amount such as the degree of correction of gradation by the correction unit 54c is stored, and the correction processing unit 54 corrects the image data based on the correction amount corresponding to the shooting scene determined by the shooting scene determination process. Process.

  Here, the sharpening processing is specifically processing for sharpening an image as a method for removing “blur” which is one cause of image quality deterioration and making the image clear. The image blur is caused by the high spatial frequency component being weakened compared to the low spatial frequency component. The effect appears at the boundary portion (edge) of the uniform density region. Therefore, in order to remove the blur, processing for enhancing high spatial frequency components is performed, and a high frequency enhancement filter in the image space is used.

  As this sharpening process, for example, as shown in FIG. 8, a convolution operation using a 3 × 3 or 5 × 5 size spatial filter can be performed. FIG. 8A shows an example of a mask for emphasizing particularly high frequency components of 3 × 3 size, and the degree of emphasis can be adjusted by the value of k. FIG. 8B is an example of a mask that particularly emphasizes low frequency components, and the degree of enhancement can be adjusted by the value of k.

  In other words, the correction processing means 54, when it is determined that the image data is a portrait photograph, the image data is a landscape photograph so that the image is soft and moist and the saturation is suppressed. When it is determined that the image data is a sharp and vivid image with sharpness, and when it is determined that the image data is a commemorative photo, each of the image data Is corrected.

  As described above, the photographic image processing apparatus determines whether the orientation of the face image of a person is along the vertical or horizontal direction of the original image, and the face image detection area based on the determined orientation of the face image. In other words, by setting different image detection areas depending on whether the vertical image of the frame image is in an up / down orientation or an image in which the landscape image is in an up / down orientation, the influence of other facial images that do not meet the shooting intention Is corrected, and an appropriate correction process in accordance with the shooting intention is performed by appropriately determining the shooting scene based on the area ratio of the face image of the subject of interest existing in the face image detection region.

  Hereinafter, another embodiment will be described. In addition to the above-described embodiment, the image processing apparatus includes a second face image detection unit that detects a face image based on whether eyes are detected in at least a skin color region included in the original image data. The configuration may be such that when a face image is not detected, the face image is detected again by the second face image detection means.

  More specifically, the second face image detecting means extracts a skin color closed area of a predetermined size or more which is a skin color hue, and a white area and a black color of a predetermined shape in the extracted skin color closed area. The presence or absence of the region is determined, and when there is, the skin color closed region is detected as a face image.

  That is, by providing the second face image detecting means, even if the face image is a sideways face that does not face the camera and only one eye is photographed, it is reliably detected as a face image. Will be able to.

  In addition to the above-described embodiment, the correction processing unit 54 corrects the original image data based on the area ratio of the determination reference face image in addition to the shooting scene determined by the shooting scene determination unit 53. It is good also as a structure. Even if the shooting scenes determined by the shooting scene determination unit 53 are the same, the original image data is corrected more appropriately based on the area ratio of the determination reference face image included in the image.

  In addition to the above-described embodiment, the correction processing unit 54 adjusts the sharpening intensity based on the area ratio of the determination reference face image in addition to the shooting scene determined by the shooting scene determination unit 52. Also good. For example, when the shooting scene is a landscape, the sharpening strength is increased, and when the portrait is a portrait, the sharpening strength is reduced based on the area ratio of the judgment reference face image to correct the image to be more attractive. Can do.

  In addition to the above-described embodiment, the correction processing unit 54 is configured such that when the shooting scene determined by the shooting scene determination unit 52 is a scene including a human face image, for example, the portrait photograph or the commemorative photograph. The exposure condition that is the acquisition condition of the image data may be determined, and the correction process according to the exposure condition may be executed.

  Specifically, the determination of the exposure condition is, for example, an average value distribution of R component, G component, and B component of each pixel data in the face image extracted from the image data, as shown in FIG. A density histogram is generated and determined by the degree of bias of the density histogram. That is, when the density histogram is biased toward the low density value (dark) side, it is determined that the underexposure is performed. On the other hand, when the density histogram is biased toward the high density value (bright) side, it is determined that the exposure is overexposed. When the density histogram is not biased toward the low density value (dark) side or the high density value (bright) side, it is determined that the exposure is appropriate.

  When the under-exposure is determined, the correction processing unit 54 performs correction processing with the sharpening processing unit 54a, for example, by increasing the sharpening intensity more than the correction condition according to the determined shooting scene. . When it is determined that the exposure is overexposed, the correction processing is performed with the sharpening intensity weakened, for example, in comparison with the correction condition corresponding to the determined shooting scene.

  Further, when it is determined that the exposure is appropriate, as shown in FIG. 9B, a density histogram is generated for each of the R component, G component, and B component of each pixel data in the face image extracted from the image data. The degree of occurrence of color feria is determined based on the degree of mismatch (dispersion) of the histogram, and correction processing according to the degree of occurrence of color feria is executed. For example, when the degree of occurrence of the color feria is equal to or greater than a predetermined occurrence degree threshold, the sharpening processing unit 54a performs a correction process with a sharpening strength weaker than the correction condition according to the determined shooting scene. .

  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.

External view of photographic image processing device Functional block diagram of the image data processing unit Functional block diagram of system controller and image processing unit Flowchart for explaining the operation of the shooting scene determination process It is explanatory drawing of a face image detection area, (a) is a case where a vertical width area is a face image detection area, (b) is a case where a horizontal width area is a face image detection area (A) Example of face image existing in face image detection area, (b) Example of face image existing in face image detection area, (c) Example of face image not existing in face image detection area Illustration of the image of correction amount according to each shooting scene It is an example of the filter used for a sharpening process, (a) is a filter which emphasizes especially a high frequency component, (b) is a filter which emphasizes especially a low frequency component. It is explanatory drawing of a density histogram, (a) is an example in which image data is overexposed or underexposed, (b) An example of the relationship between each color component

Explanation of symbols

1: Image data input unit 1a: Film scanner 1b: Media driver 2: Image data storage unit 3: Monitor 4: Operation input unit 5: Image processing unit 6: Photo printer 7: System controller 51: Face image detection means 52: Posture Determination means 53: Shooting scene determination means 54: Correction processing means 54a: Sharpening processing means 54b: Color correction means 54c: Tone correction means

Claims (4)

A face image detection step for detecting a human face image from input original image data, and at least a portrait photo and a photo other than the portrait photo are determined based on the detection result of the face image detection step to determine a shooting scene. A photographic image processing method comprising: a photographic scene determination step; and a correction processing step for correcting the original image data based on a determination result obtained by the photographic scene determination step, wherein the person detected in the face image detection step A posture determination step of determining whether the posture of the face image is along the vertical or horizontal direction of the original image, wherein the shooting scene determination step is a face image based on the posture of the face image determined in the posture determination step A photographic image processing method for setting a detection area and determining a photographic scene based on an area ratio of face images existing in the face image detection area. In the shooting scene determination step, a shooting scene is determined using a face image having a maximum size as a determination reference face image among face images in which the area ratio of the face image existing in the face image detection region is larger than a preset reference area ratio. The photographic image processing method according to claim 1 for determination. A face image detection unit that detects a human face image from input original image data, and at least a portrait photo and a photo other than the portrait photo are determined based on a detection result by the face image detection unit, and a shooting scene is determined. A photographic image processing apparatus comprising: a photographic scene determination unit; and a correction processing unit that corrects the original image data based on a determination result by the photographic scene determination unit, wherein the person detected by the face image detection unit Posture determining means for determining whether the posture of the face image is along the vertical or horizontal direction of the original image, and the photographing scene determining means is a face image based on the posture of the face image determined by the posture determining means. A photographic image processing apparatus that sets a detection area and determines a photographic scene based on an area ratio of face images existing in the face image detection area. The shooting scene determination unit is configured to determine a shooting scene using a face image having a maximum size as a determination reference face image among face images in which an area ratio of a face image existing in the face image detection region is larger than a preset reference area ratio. 4. The photographic image processing apparatus according to claim 3, wherein the correction processing unit corrects the original image data based on an area ratio of the shooting scene determined by the shooting scene determination unit and the determination reference face image.