JP2004282570A - Image processor - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor capable of judging the reliability of accompanying information accompanying a digital image. <P>SOLUTION: A printer 1 analyzes flesh color area, average brightness or color balance, etc. of image data, or judges the reliability of tag information for specifying a photographic scene based on an analysis result, camera information (such as a lens F value, subject distance, shutter speed) included in other pieces of tag information, determines correction quantity according to the judged reliability and the photographic scene and performs image correction according to the determined correction quantity. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an image processing apparatus, an image processing method, and a program for acquiring a digital image captured by a digital still camera or the like and additional information attached to the digital image, and using the additional information for image processing. About.
[0002]
[Prior art]
Some digital still cameras can attach camera information such as date and time of shooting, exposure, shutter speed, or shooting scene type to image data. Further, there has been proposed an image processing apparatus that performs image quality correction processing that reflects a photographer's intention at the time of photographing, using camera information (additional information) attached to image data as described above (for example, Patent Documents) 1).
However, when the photographer captures an image with an incorrect setting, the setting is output to the image processing apparatus as camera information, and the image processing apparatus performs image correction according to the incorrect setting. In general, landscape images tend to prefer high contrast and high sharpness, while portrait images tend not to favor high contrast or extremely high sharpness. Then, the image processing apparatus determines that the mode is the landscape shooting mode, and performs inappropriate image correction on the portrait image, such as increasing the contrast and sharpness of the image.
[0003]
[Patent Document 1]
Japanese Patent Application Laid-Open No. 2002-314809
[Problems to be solved by the invention]
The present invention has been made in view of the above background, and has as its object to provide an image processing apparatus that can determine the reliability of additional information attached to a digital image.
[0005]
[Means for Solving the Problems]
In order to achieve the above object, an image processing apparatus according to the present invention comprises: an attribute analysis unit for analyzing attributes of a digital image based on the digital image; and an additional information acquisition unit for acquiring additional information attached to the digital image. Means for determining reliability of the additional information acquired by the additional information acquiring means based on the image attributes analyzed by the attribute analyzing means.
[0006]
The image processing apparatus according to the present invention further comprises: additional information acquisition means for acquiring a plurality of pieces of additional information attached to the digital image; And determination means for determining the reliability of.
[0007]
Preferably, the image processing apparatus further includes image quality adjusting means for adjusting the image quality of the digital image according to the reliability determined by the determining means.
[0008]
Preferably, the determination unit determines the reliability of the additional information regarding the shooting scene.
Preferably, the determination unit determines the reliability of the additional information indicating a shooting mode when the digital image was shot.
[0009]
Preferably, the apparatus further comprises warning means for transmitting warning information when the reliability determined by the determination means is lower than a predetermined reference.
[0010]
[Image processing method]
Further, the image processing method according to the present invention analyzes the attribute of the digital image based on the digital image, acquires additional information attached to the digital image, and acquires the additional information based on the analyzed image attribute. The reliability of the additional information is determined.
[0011]
The image processing method according to the present invention acquires a plurality of pieces of additional information attached to a digital image, and determines the reliability of the additional information based on the acquired pieces of additional information.
[0012]
[program]
A program according to the present invention includes, in an image processing apparatus including a computer, analyzing an attribute of the digital image based on the digital image, and acquiring additional information attached to the digital image. Determining the reliability of the acquired additional information based on the obtained image attribute.
[0013]
Further, a program according to the present invention includes, in an image processing apparatus including a computer, a step of acquiring a plurality of pieces of additional information attached to a digital image; The step of determining is performed by the computer of the image processing apparatus.
[0014]
BEST MODE FOR CARRYING OUT THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram exemplifying a hardware configuration of a printer device 1 to which an image processing method according to the present invention is applied, focusing on a control device 2 thereof.
As shown in FIG. 1, the printer device 1 includes a control device 2 and a printer device main body 10.
The control device 2 includes a control device main body 20 including a CPU 202 and a memory 204, a communication device 22, a recording device 24 such as an HDD / CD device, and a user interface including an LCD display device or a CRT display device and a keyboard / touch panel. Device (UI device) 26.
The printer device 1 acquires image data photographed by a digital still camera or the like and additional information (hereinafter, tag information) indicating photographing conditions via the communication device 22 or the recording device 24, and analyzes the image data. Then, the reliability of the tag information is determined, and image quality correction processing is performed according to the reliability and the tag information.
The tag information is information attached to the image data, information indicating a shooting mode of the image data, information for specifying a digital still camera used for shooting, shutter speed at shooting, lens F value at shooting, The information includes a distance to a subject at the time of shooting (hereinafter referred to as a subject distance), the presence or absence of a flash, a shooting luminance value, a shooting contrast, and the like.
[0015]
FIG. 2 is a diagram showing a configuration of an image processing program 5 which is executed by the control device 2 (FIG. 1) and realizes the image processing method according to the present invention.
As shown in FIG. 2, the image processing program 5 includes a tag acquisition unit 510 (additional information acquisition unit), an image acquisition unit 520, an image analysis unit 530 (attribute analysis unit), a reliability determination unit 540 (determination unit), a warning It comprises a unit 545, a correction amount calculation unit 550, an image quality correction processing unit 560 (image quality adjustment means), and an image output unit 580.
The image quality correction processing unit 560 includes a noise removal unit 562, a white balance correction unit (WB correction unit) 564, an exposure correction unit 566, a contrast correction unit 568, a saturation correction unit 570, a storage color correction unit 572, and a sharpness correction unit. 574.
The image processing program 5 is supplied to the control device 2 via, for example, the recording medium 240 (FIG. 1) or a network, and is loaded into the memory 204 and executed.
[0016]
In the image processing program 5, the tag acquisition unit 510 acquires the tag information attached to the image data and outputs the tag information to the reliability determination unit 540. The tag obtaining unit 510 obtains, for example, chunk information and tag information that record a shooting situation attached to image data of a digital still camera shooting. The tag information is held in the same data file together with the image data in a predetermined image format (for example, EXIF 2.2), and includes additional information related to the number of image pixels, resolution, scene classification, and the like. The additional information in the EXIF image format is not limited to the digital still camera image format. Further, the tag acquisition unit 510 may similarly acquire tag information (additional information) based on an image format TIFF or the like that can hold high-precision imaging information by reversible compression.
When acquiring image data of a digital image via the communication device 22 or the recording device 24, the image acquisition unit 520 outputs the acquired image data to the image analysis unit 530 and the image quality correction processing unit 560.
[0017]
The image analysis unit 530 analyzes at least a part of the image data input from the image acquisition unit 520, calculates a feature amount indicating a feature such as color, brightness, or sharpness included in the image, and uses the reliability as an image attribute. Output to determination section 540.
For example, the image analysis unit 530 calculates a feature amount characterizing the lightness distribution, the saturation distribution, and the color balance in the image based on the RGB histogram or the HSL histogram of the image data, and calculates the image size and the edge of the image data. An edge degree of image sharpness is calculated as a feature amount based on the amount and the edge strength.
Further, the image analysis unit 530 calculates a feature amount (skin color area, sky area, green area, and the like) indicating the distribution of the skin color, sky color, green, and the like inside the image.
Further, the image analysis unit 530 determines a feature amount such as a shooting state of a scene (whether there is a flash, a backlight state of a main subject, a size of a person, and the like) based on a local brightness distribution state in the image. It may be calculated as an attribute.
[0018]
The reliability determination unit 540 determines the reliability of the tag information input from the tag acquisition unit 510 based on the image attribute (analysis result) input from the image analysis unit 530, and outputs a warning unit 545 and a correction amount calculation unit. Output to 550. In this example, a case where the reliability determination unit 540 determines the reliability of the tag information indicating the shooting mode by a determination method described later will be described as a specific example. Here, the photographing mode is a setting mode set by the photographer at the time of photographing an image, and includes, for example, a person photographing mode, a landscape photographing mode, and a night scene photographing mode. These shooting modes are associated with shooting conditions (image shooting attribute information) such as a shutter speed, a lens aperture value, and the presence or absence of a strobe, and include at least one shooting condition corresponding to the selected shooting mode. This is the setting information to be specified.
The reliability determination unit 540 may determine the reliability of the tag information based on other attribute information such as a shooting date and time, a shooting location, and a temperature at the time of shooting. Further, the reliability determination unit 540 may determine the reliability of the tag information based on the change history of the shooting mode.
[0019]
The warning unit 545 outputs a warning indicating that the reliability is low when the reliability input from the reliability determination unit 540 is equal to or less than the reference value. The warning unit 545 controls, for example, the UI device 26 to display a warning on a display device. The warning unit 545 may issue a warning by a warning sound, blinking light, printing on a print medium, or the like. Further, when the reliability is equal to or less than the reference value, the warning unit 545 may temporarily suspend the printing process and restart the printing process after waiting for a user's instruction.
[0020]
The correction amount calculation unit 550 calculates a correction amount based on the reliability and the tag information input from the reliability determination unit 540, and outputs the correction amount to the image quality correction processing unit 560. For example, the correction amount calculation unit 550 refers to a table that associates the shooting mode and the correction parameter with each other, adjusts the correction parameter corresponding to the shooting mode according to the reliability, and obtains the correction amount. This correction parameter adjustment is performed by applying a coefficient such that the higher the reliability, the greater the contribution of the correction parameter corresponding to the shooting mode.
[0021]
The image quality correction processing unit 560 includes a noise removal unit 562, a WB correction unit 564, an exposure correction unit 566, a contrast correction unit 568, a saturation correction unit 570, a memory color correction unit 572, and a sharpness correction unit 574, and an image acquisition unit 520. The image data is input to the image data, and the image data is subjected to image quality correction processing according to the correction amount input from the correction amount calculation unit 550, and is output to the image output unit 580.
The noise removing unit 562 removes noise by performing a smoothing process on the image data. The WB correction unit 564 performs white balance adjustment processing on the image data from which noise has been removed. The exposure correction unit 566 corrects the exposure amount of the image data on which the white balance has been adjusted. The contrast correction unit 568 adjusts the contrast of the image data whose exposure has been corrected. The saturation correction unit 570 adjusts the saturation of the image data on which the contrast has been adjusted. The storage color correction unit 572 performs storage color correction on the image data on which the saturation has been adjusted. The sharpness correction unit 574 performs a process of enhancing sharpness on the image data on which the memory color correction has been performed.
[0022]
The image output unit 580 converts the image data input from the image quality correction processing unit 560 into a CMYK color space, and controls a print engine (not shown) of the printer apparatus main body 10 to print on a sheet.
[0023]
FIG. 3 is a diagram illustrating a determination table when the reliability determination unit 540 determines the reliability of the tag information.
As illustrated in FIG. 3, the reliability determination unit 540 has a determination table indicating evaluation items and evaluation criteria regarding image analysis results and other tag information, and determines the reliability of tag information indicating a shooting mode. Refer to In the case of this example, when calculating the reliability of the shooting mode specified by the tag information, the reliability determination unit 540 determines a plurality of evaluation items (“image analysis result” and “tag information”) corresponding to the shooting mode. ), It is determined whether the analysis result (skin color area, presence / absence of a subject, etc.) and the content of the tag information satisfy evaluation criteria (skin area ratio, lens F value, subject distance, etc.), and are determined to satisfy the evaluation criteria. The reliability of the shooting mode is calculated based on the number of evaluation items thus obtained.
For example, when determining the reliability of tag information indicating a person photographing scene, the reliability determining unit 540 acquires an image analysis regarding the size of the skin color area and the presence or absence of a subject, and further obtains a lens at the time of photographing. Tag information indicating the F value and the subject distance is acquired, and the number of items that match the evaluation conditions for these evaluation items is defined as the reliability.
[0024]
[motion]
Hereinafter, the operation of the printer device 1 will be described.
FIG. 4 is a flowchart showing the operation (S10) of the printer device 1 (image processing program 5).
In step 100 (S100), the image acquisition unit 520 of the printer device 1 acquires image data via the communication device 22 or the recording device 24, and outputs the acquired image data to the image analysis unit 530 and the image quality correction processing unit 560. The tag acquisition unit 510 acquires the tag information attached to the image data acquired by the image acquisition unit 520, and acquires the tag information from the reliability determination unit 540.
[0025]
In step 102 (S102), based on the image data input from the image acquisition unit 520, the image analysis unit 530 determines the size of the area such as skin color, sky, or green, the presence or absence of a subject, the histogram distribution, and the brightness. The average value and the like are analyzed and output to the reliability determination unit 540.
[0026]
In step 104 (S104), the reliability determination unit 540 refers to the determination table illustrated in FIG. 3 and analyzes the analysis result input from the image analysis unit 530 and the tag input from the tag acquisition unit 510. The reliability corresponding to the information is determined and output to the warning unit 545 and the correction amount calculation unit 550.
[0027]
In step 106 (S106), the warning unit 545 compares the reliability input from the reliability determination unit 540 with the reference value of the warning. The image processing program 5 proceeds to the process of S106 when the reliability is equal to or less than the reference value, and otherwise proceeds to the process of S110.
In step 108 (S108), if the reliability is equal to or less than the reference value, the warning unit 545 controls the UI device 26 (FIG. 1) to display that the reliability of the tag information is low.
[0028]
In step 110 (S110), the correction amount calculation unit 550 calculates the correction amount according to the tag information input from the reliability determination unit 540 and the reliability of the tag information, and sends the correction amount to the image quality correction processing unit 560. Output to
In step 112 (S112), the image quality correction processing unit 560 performs image quality correction of the image data input from the image acquisition unit 520 according to the correction amount input from the correction amount calculation unit 550, and sends the image data to the image output unit 580. Output to
In step 114 (S114), the image output unit 580 controls the printer device main body 10 (FIG. 1) to print the corrected image data input from the image quality correction processing unit 560.
[0029]
As described above, the printer device 1 of the present embodiment determines the reliability of the input tag information based on the image analysis. It is possible to determine whether or not the setting matches the intention, prevent the image quality from being corrected out of the photographing intention, and obtain a high-quality output image.
[0030]
[Modification]
Next, a modified example of the present invention will be described. In the above embodiment, the reliability of the tag information is determined based on the result of the image analysis. In the present modification, however, the reliability of the tag information is determined based on a plurality of pieces of tag information. For example, the printer device 1 acquires tag information indicating the contents set by the photographer and tag information indicating the shooting parameters that are not affected by the settings of the operator, and converts the contents set by the photographer based on their correspondence. The reliability of the indicated tag information is determined.
[0031]
FIG. 5 is a diagram illustrating the configuration of the image processing program 52 according to the present modification.
As shown in FIG. 5, the image processing program 52 has a configuration in which the image analysis unit 530 is deleted from the image processing program 5 shown in FIG. 5 that are substantially the same as those shown in FIG. 2 are denoted by the same reference numerals.
[0032]
The tag acquisition section 520 in the image processing program 52 acquires a plurality of pieces of tag information and outputs the information to the reliability determination section 540.
The reliability determining unit 540 determines the reliability of the tag information regarding the shooting scene based on the plurality of pieces of tag information input from the tag acquiring unit 520, and outputs the determined reliability to the warning unit 545 and the correction amount calculating unit 550.
[0033]
FIG. 6 is a diagram exemplifying a judgment table referred to by the reliability judgment section 540 (FIG. 5) in the present modification.
As illustrated in FIG. 6, the reliability determination unit 540 determines the reliability of tag information (shooting scene information) based on a plurality of tag information. The reliability determination unit 540 of this example automatically includes a tag information A indicating photographer setting information (such as a lens F value or a shutter speed) set by the photographer and a digital still camera regardless of the photographer's setting. The reliability of the tag information indicating the shooting scene is determined based on the set or measured tag information B indicating the camera setting information (subject distance or luminance value, etc.).
For example, when the lens F value is smaller than the reference b and the subject distance is smaller than the reference c, it is considered that a close-up subject is photographed in a state close to the lens opening, and the reliability determination unit 540 determines that the person It is determined that the reliability of the tag information indicating the shooting scene (person shooting mode) is high. When the lens F value is larger than the reference d and the subject distance (automatic focal length) is larger than the reference e, it is considered that a distant view was taken with a large depth of field, and the reliability was high. The determination unit 540 determines that the reliability of the tag information indicating the scenery shooting scene (landscape shooting mode) is high.
[0034]
As described above, by determining the reliability of the tag information based on the plurality of pieces of tag information, it is possible to determine the reliability of the tag information without performing a heavy load process such as image analysis.
[0035]
As another modified example, the reliability determination unit 540 may assign an evaluation value to the image analysis result and the tag information, and determine the reliability of the tag information based on the evaluation value. .
FIG. 7 is a diagram illustrating a graph of an evaluation value used by the reliability determination unit 540. FIG. 7A shows the relationship between the skin area ratio for the entire image and the evaluation value for the tag information (person shooting scene), and FIG. 7B shows the relationship between the subject distance and the tag information (person shooting scene). FIG. 7C shows the relationship between the lens F value and the evaluation value for the tag information (person shooting scene).
As illustrated in FIG. 7A, the reliability determination unit 540 determines that the higher the skin area ratio with respect to the entire image, the higher the possibility of a person photographing scene. As shown in FIG. 7B, a higher evaluation value is assigned, and the closer the subject distance, the higher the possibility of a person shooting scene. Therefore, a higher evaluation value is assigned to the tag information indicating the person shooting scene. Give. Also, as illustrated in FIG. 7C, the reliability determination unit 540 increases the possibility that the smaller the lens F value is, the higher the possibility of a person photographing scene is, and therefore, the higher the tag information indicating the person photographing scene is. Give an evaluation value.
For example, the reliability determining unit 540 refers to the determination table illustrated in FIG. 3 and determines the reliability of the tag information indicating a person photographing scene, based on the image analysis result. (See FIG. 7A) and an evaluation value according to the presence or absence of the subject, and further, based on the tag information, the lens F value (see FIG. 7C) and the subject distance (see FIG. 7B) ) Is calculated, and each of the evaluation values is multiplied by a weighting coefficient and summed. The evaluation value for the presence or absence of the subject is, for example, a binary value set in advance according to the presence or absence of the subject.
Thus, by setting continuous evaluation values for the image analysis result and the content of the tag information, the accuracy of the reliability determination can be further improved.
[0036]
【The invention's effect】
As described above, according to the image processing apparatus of the present invention, it is possible to determine the reliability of additional information attached to a digital image.
[Brief description of the drawings]
FIG. 1 is a diagram exemplifying a hardware configuration of a printer device 1 to which an image processing method according to the present invention is applied, focusing on a control device 2 thereof.
FIG. 2 is a diagram showing a configuration of an image processing program 5 which is executed by a control device 2 (FIG. 1) and realizes an image processing method according to the present invention.
FIG. 3 is a diagram illustrating an example of a determination table when a reliability determination unit determines a reliability of tag information;
FIG. 4 is a flowchart showing an operation (S10) of the printer device 1 (image processing program 5).
FIG. 5 is a diagram illustrating a configuration of an image processing program 52 according to the present modification.
FIG. 6 is a diagram exemplifying a determination table referred to by a reliability determination unit 540 (FIG. 5) in the present modified example.
FIG. 7A illustrates a relationship between a skin area ratio for the entire image and an evaluation value for tag information (person shooting scene), and FIG. 7B illustrates a subject distance and tag information (person shooting scene). FIG. 9C is a graph illustrating the relationship between the lens F value and the evaluation value for the tag information (person photographing scene).
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 ... Printer apparatus 10 ... Printer apparatus main body 2 ... Control apparatus 20 ... Control apparatus main body 202 ... CPU
204 memory 22 communication device 24 recording device 240 recording medium 26 UI device 5, 52 image processing program 510 tag acquisition unit 520 image Acquisition unit 530 Image analysis unit 540 Reliability determination unit 545 Warning unit 550 Correction amount calculation unit 560 Image quality correction processing unit 562 Noise removal unit 564 White balance corrector 566 Exposure corrector 568 Contrast corrector 570 Saturation corrector 572 Memory color corrector 574 Sharpness corrector 580 Image output unit

Claims (10)

Attribute analyzing means for analyzing attributes of the digital image based on the digital image;
Additional information obtaining means for obtaining additional information attached to the digital image,
An image processing apparatus comprising: a determination unit configured to determine a reliability of the additional information acquired by the additional information acquisition unit based on the image attribute analyzed by the attribute analysis unit. Additional information acquisition means for acquiring a plurality of additional information attached to the digital image,
An image processing apparatus comprising: a determination unit that determines the reliability of the additional information based on the plurality of pieces of additional information acquired by the additional information acquisition unit. The image processing apparatus according to claim 1, further comprising an image quality adjustment unit that adjusts an image quality of the digital image according to the reliability determined by the determination unit. The additional information obtaining means obtains additional information regarding a shooting scene of the digital image,
The image processing apparatus according to claim 1, wherein the determination unit determines the reliability of the additional information regarding the shooting scene acquired by the additional information acquisition unit. The additional information obtaining means obtains additional information indicating a shooting mode set when the digital image was shot,
The image processing apparatus according to claim 4, wherein the determining unit determines the reliability of the additional information indicating the shooting mode acquired by the additional information acquiring unit. The image processing apparatus according to claim 1, further comprising a warning unit that sends warning information when the reliability determined by the determination unit is lower than a predetermined reference. Analyzing the attributes of the digital image based on the digital image,
Acquire additional information attached to the digital image,
An image processing method for determining the reliability of acquired additional information based on the analyzed image attributes. Acquire a plurality of additional information attached to the digital image,
An image processing method for determining reliability of acquired additional information based on a plurality of acquired additional information. In an image processing apparatus including a computer,
Analyzing the attributes of the digital image based on the digital image;
Obtaining additional information attached to the digital image;
Determining the reliability of the acquired additional information based on the analyzed image attributes. In an image processing apparatus including a computer,
Obtaining a plurality of additional information attached to the digital image;
Determining the reliability of the acquired additional information based on the acquired plural pieces of additional information by the computer of the image processing apparatus.

Images