JP2009239889A - Color processing system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a color processing system for easily specifying an image subjected to incorrect color processing due to erroneous analysis. <P>SOLUTION: A color processing system comprises: an image analyzing section for performing image analysis on each of a plurality of images; a color processing section for applying color processing to each of a plurality of images based on a result of image analysis for each image; a defect detecting section for detecting the degree of a color defect caused in color processing, for each image subjected to color processing by the color processing section; and a ranking section for ranking each of a plurality of images in accordance with the degree of defect detected by the defect detecting section. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a color processing system that performs color processing on an image.

  In recent years, along with the development of imaging devices centered on digital cameras and image readers centered on scanners, captured color images and scanned color images are imported into computers, and printed materials using the captured color images as materials. DTP (desktop publishing) for creating is widely used.

  In addition, a color processing system that performs color processing on an image so that the color image captured in the computer looks beautiful on a display medium has been proposed (for example, see Patent Document 1).

In such a color processing system, by simply registering image data to be processed in a predetermined holder on the client side, the server side analyzes characteristics such as color gradation for each image, and the image is It is detected in advance which image is a typical scene such as 'sunset', 'human face', 'blue sky', 'underwater', for example, if the scene is 'sunset' , There is a function that automatically corrects the color to be close to red, which humans think is appropriate for the color of the “evening scene”, and then returns it to the client side, which makes it easy to process a large number of images It is like that.
JP-A-8-307713

  However, in a color processing system having the above-described functions, if incorrect analysis is performed in advance in image analysis performed for color processing, color processing that is not intended by the user may be performed. is there. Therefore, even if color processing can be automatically performed on a large number of images by the above-described function, there is a problem that it is troublesome to check whether erroneous color processing due to erroneous analysis has been performed.

  Note that this problem is not limited to erroneous analysis in scene analysis, and may be caused by erroneous analysis in white balance processing, for example.

  In view of the above circumstances, an object of the present invention is to provide a color processing system that can easily identify an image subjected to erroneous color processing by erroneous analysis.

In order to achieve the above object, the color processing system of the present invention provides:
An image analysis unit that performs image analysis on each of a plurality of images;
For each of the plurality of images, a color processing unit that performs color processing based on the result of the image analysis for each image;
For each image that has undergone color processing in the color processing unit, a defect detection unit that detects the degree of a defect related to color that occurs with the color processing, and
A rank assigning unit that assigns a rank according to the degree of the defect detected by the defect detection unit to each of the plurality of images.

  It is considered that an image with a greater degree of color processing malfunction is more likely to have been subjected to erroneous color processing due to erroneous analysis. Therefore, in the color processing system of the present invention, each color processed image has a color. A rank according to the degree of processing failure is given. Therefore, according to the color processing system of the present invention, by following this order, it is possible to efficiently check an image on which erroneous color processing has been performed by erroneous analysis.

  Here, it is preferable that the color processing system of the present invention includes a search unit that searches for an image using the rank assigned by the rank assigning unit, and the color processing system of the present invention includes the rank assigning unit. It is also a preferable aspect that a display unit for displaying the ranks assigned by is provided.

  In such a manner, since the image corresponding to the rank can be quickly searched, it is possible to more efficiently check the image that has been subjected to erroneous color processing by erroneous analysis.

  Here, the color processing system according to the present invention displays the plurality of images, and among the plurality of images, the image having the highest ranking given by the ranking giving unit to the predetermined ranking is ranked high. It is preferable to include a display unit that displays the order by marking the mark as being. Alternatively, the color processing system of the present invention displays the plurality of images side by side in the order given by the order assigning unit. It is also a preferable aspect to include a display unit that displays this order.

  In this way, since the image subjected to the color processing can be visually observed, it is possible to confirm the result of erroneous color processing due to erroneous analysis.

  Further, the color processing system of the present invention displays the order by arranging the plurality of images in the order given by the order assigning unit. The images before and after the color processing are also arranged for each of the plurality of images. It is also a preferable aspect that a display unit for displaying is provided.

  In this way, since the images before and after the color processing can be visually confirmed, it is possible to confirm the content of the erroneous color processing due to the erroneous analysis.

Here, the color processing system of the present invention displays the order by displaying the plurality of images side by side in the order given by the order giving unit,
It is preferable to include a selection correction receiving unit that receives a selection correction operation for selecting an image from the images displayed on the display unit and correcting the color.

  In this way, it is possible to perform color correction to a color according to the operator's preference for an image that has been subjected to erroneous color processing by erroneous analysis.

  Here, the defect detection unit detects, as the degree of the defect, a predetermined change element indicating an excessive degree of the color processing among various change elements included in the image change before and after the color processing. It is preferable that

  Since the predetermined change element indicating the excessive degree of color processing is considered to accurately reflect the presence or absence of erroneous color processing due to erroneous analysis, in this way, an image subjected to erroneous color processing due to erroneous analysis is processed. Confirmation can be performed accurately.

  The defect detection unit may calculate a maximum color change amount among color change amounts before and after the color processing at various points in the image as the degree of the defect, or the image may be a predetermined color. The color is expressed within the reproduction range, and the defect detection unit calculates the amount of increase before and after the color processing at the position reaching the boundary of the color reproduction range in the image as the degree of the defect. It may be calculated.

  The maximum color change amount before and after color processing in each part of the image, and the increase amount before and after color processing in the part reaching the boundary of the color reproduction range in the image are the degree of excess processing. It is an example of the predetermined change element which shows.

Here, as the image analysis, the image analysis unit analyzes which scene the image corresponds to among a plurality of predetermined scenes.
It is preferable that the color processing unit performs color processing according to a scene obtained by the image analysis.

  The color processing system according to the present invention performs color processing based on scene analysis in which there is a high possibility of erroneous analysis because improvement in analysis accuracy cannot be expected so much due to difficulty in setting a judgment criterion. It is suitable for.

Further, the color processing system of the present invention, a scene designating unit for designating a scene selected from the plurality of scenes,
Of the plurality of images, a scene extraction unit that extracts an image analyzed by the analysis by the image analysis unit and corresponding to the scene specified by the scene specification unit;
The plurality of images are displayed, and an image extracted by the scene extraction unit among the plurality of images is displayed with a mark indicating that it is an extracted image and the rank given by the rank giving unit. It is also a preferable aspect to include a display unit.

  In this way, the causal relationship between the scene determined as the corresponding scene by analysis and the order, for example, the displayed image does not include a human face, but the scene analysis result of the image is a person. It can be confirmed that it was ranked high because of the face of

Here, the image analysis unit calculates the probability that the image corresponds to each scene, and analyzes that this image corresponds to the scene with the highest probability,
A scene designating unit for designating one or more scenes selected from the plurality of scenes;
A display unit that displays the plurality of images, displays the ranks assigned by the rank assigning unit, and also displays a probability corresponding to the scene designated by the scene designation unit along with each image; It is preferable to provide.

  In this way, it is possible to confirm the certainty made for a designated scene among a plurality of scenes for each image.

In addition, the image analysis unit calculates the probability that the image corresponds to each scene, and analyzes that this image corresponds to the scene with the highest probability,
A scene designating unit for designating one or more scenes selected from the plurality of scenes;
Among the plurality of images, an analysis by the image analysis unit, a probability extraction unit for extracting an image whose probability corresponding to the scene specified by the scene specification unit reaches a default value,
A display unit that displays the plurality of images, displays the ranks given by the rank assigning unit, and displays the probability of each image extracted by the probability extracting unit along with each image; Is also a preferred embodiment.

  In this way, it is possible to display only images with a high probability of the designated scene, and it is possible to efficiently narrow down the causes of defects due to color processing.

  Further, the color processing system of the present invention uses a condition that the probability reaches a default value when a plurality of scenes are designated by the scene designation unit, and uses a logical product for the designated plurality of scenes. It is preferable that a condition setting unit that receives setting of whether or not to be used is provided, and the probability extraction unit extracts an image using a logical operation that is set by the condition setting unit.

  In this way, it is easy to confirm when the cause of the problem due to color processing is complex.

  Preferably, a default value setting unit that receives the setting of the default value is provided, and the probability extraction unit extracts an image using the default value that is set by the default value setting unit.

  In this way, the amount of extraction can be adjusted, and for example, an extraction mode in which the cause of the defect can be easily pursued can be obtained.

  According to the color processing system of the present invention, it is possible to easily identify an image subjected to erroneous color processing by erroneous analysis.

  Hereinafter, embodiments of the present invention will be described.

  FIG. 1 is a schematic configuration diagram of a color processing system.

  A color processing system 1 shown in FIG. 1 includes a server computer (hereinafter abbreviated as a server device) 100, a client computer (hereinafter abbreviated as a client device) 200, a color scanner 400, and a color printing machine 500. They are connected via an area network (hereinafter abbreviated as “LAN”) 300. FIG. 1 shows one server apparatus 100 and one client apparatus 200. This is an example of a computer constituting the color processing system 1. The color processing system 1 also includes other server devices and client devices. However, for the sake of simplicity, the following description will be continued using the server device 100 and the client device 200 exemplified here. This color processing system 1 is a first embodiment of the color processing system of the present invention.

  Here, originally, in a computer, an image is handled as image data, and the image data is a target of storage or processing in the form of a file or the like. In this specification, these image data, file, and image Is simply referred to as an image without particular distinction, and the expression that the image is stored and processed is used.

  In the client device 200, a job ticket describing processing conditions such as parameters used for color processing is edited by an operator. The edited job ticket is provided to the server device 100. Further, in the client device 200, an image for printing read by the color scanner 400 by the operator is stored in the hard disk device, and the operator selects an image from the images stored in the client device 200 by a predetermined selection operation. The server device 100 receives the selected image from the client device 200 and stores it in the hard disk device. In the server apparatus 100, each of the received images is an image of any one of typical scenes of “person face”, “blue sky”, “underwater”, “evening view”, “night view”, and “nature”. For example, if the scene is “sunset”, color correction is performed so that a human thinks that the color of “sunset” is appropriate, and the image after color correction is stored in the hard disk device. Thereafter, the color-processed image is sent to the client device 200 and stored in the hard disk device of the client device 200. In addition, the server device 100 executes image display processing for previewing the image sent to the client device 200 so that the operator can preview the image on the monitor 220 of the client device 200, and the color on the preview screen by the operator. Accept correction requests. The image confirmed by the operator is sent to the color printer 500 for printing. The computer constituting the server device 100 and the computer constituting the client device 200 are different in their operation contents, but are substantially the same in hardware configuration. A computer constituting the apparatus 100 will be described.

  The computer constituting the server device 100 has a main body part 110, a monitor 120 that displays an image on the display screen 121 according to an instruction from the main body part 110, and various main body parts 110 according to key operations. And a mouse 140 for inputting an instruction corresponding to, for example, an icon or the like displayed at that position by designating an arbitrary position on the display screen 121. The main body 110 has an FD loading port 111 for loading a flexible disk (hereinafter abbreviated as FD) and a CD loading port 112 for loading a CD-type medium represented by a CD-ROM. Have. Inside, an FD drive and a CD-ROM drive (to be described later) for driving the loaded FD and CD-ROM are also incorporated.

  FIG. 2 is an internal block diagram of the main body.

  Inside the main body 110, a CPU 113 that executes various programs, a hard disk device 115 that stores various programs and images, and a program that is stored in the hard disk device 115 are read out and expanded for execution by the CPU 113. The main memory 114 and the FD 300 are loaded, the FD drive 116 that accesses the loaded FD 300 and the CD-ROM 310 are loaded, and the CD-ROM drive 117 that accesses the loaded CD-ROM 310 is built in. These various elements and the monitor 120, keyboard 130, and mouse 140 are connected to each other via a bus 150. The main body 110 also includes an input interface 118 for receiving an image from the color scanner 400 and the like, and an output interface 119 for transmitting the image to the color printing machine 500. In addition, the input interface 118 and the output interface 119 are also connected to each other through the bus 150 and the above-described various elements constituting the hardware inside the main body 110.

  Next, a color processing program installed in this computer will be described. When this color processing program is stored in the CD-ROM 310, for example, when the CD-ROM 310 is loaded into the main body 110 from the CD-ROM loading port 112, the color stored in the CD-ROM 310 is stored. A processing program is installed in the hard disk device 115 by the CD-ROM drive 117. When the color processing program installed in the hard disk device 115 is activated, the computer becomes the server device 100 and the other computer becomes the client device 200. The server device 100 and the client device 200 are It operates as the first embodiment of the color processing system of the invention.

  FIG. 3 is a configuration diagram of the color processing program.

  Here, the color processing program 700 is stored in the CD-ROM 310. The storage medium for storing the color processing program 700 is not only the CD-ROM 310 shown in FIG. 2, but also various kinds of storage such as the hard disk device 115 and FD 300 shown in FIG. A medium may be employed.

  The color processing program 700 is executed on a computer, and operates the server device 100 and the client device 200 as the first embodiment of the color processing system of the present invention as described above. The color processing program 700 includes an image analysis unit 701, a color processing unit 702, a resolution conversion unit 703, a sharpness control unit 704, a format conversion unit 705, a thumbnail creation unit 706, an output unit 708, and a display operation unit 709. is doing.

  The image analysis unit 701 includes an acquisition unit 7011, a color conversion parameter creation unit 7012, and a resolution parameter creation unit 7013.

  The color processing unit 702 includes a scene analysis unit 7021, a color correction unit 7022, a color change amount calculation unit 7023, and a rank assignment unit 7024.

  The display operation unit 709 includes a display unit 7091, an image search unit 7092, and a selection / correction reception unit 7093.

  Detailed contents of each element of the color processing program 700 will be described later.

  FIG. 4 is a diagram showing an outline of elements constructed on this computer for causing the server apparatus and the client apparatus to operate as the first embodiment of the color processing system, and actions by these elements.

  When the color processing program 700 shown in FIG. 3 is installed in the computer, the image analysis unit 601, color processing unit 602, resolution conversion unit 603, sharpness control unit 604, format conversion unit 605, thumbnail creation unit 606, shown in FIG. Each element of the output unit 608 and the display operation unit 609 is constructed on a computer. These elements cause the server apparatus 100 and the client apparatus 200 to operate as the first embodiment of the color processing system of the present invention. Therefore, each element in FIG. 3 corresponds to each element in FIG. 4, but each element in FIG. 4 is composed of a combination of computer hardware and an OS or application program executed on the computer. On the other hand, each element of the color processing program 700 shown in FIG. 3 is different in that it is constituted only by application programs.

  Below, the effect | action by each element shown in FIG. 4 is demonstrated.

  In the color processing system 1, as described above, the printing image read by the operator by the color scanner 400 is stored in the hard disk device 115 of the client device 200, and the operator operating the client device 200 stores the image. When an image for which color processing is desired is registered in a predetermined folder, the image registered in the folder is sent to the image analysis unit 601 of the server apparatus 100 and color processing is started. The elements constructed in the client device 200 are elements that are basically provided in the computer as they are, so that the illustration of the elements is omitted, and only the operation of each element is the same as that of the server apparatus 100. It will be described together with the operation of the element. Further, information such as resolution information, color space information used, device link profile, and data amount of the color scanner 400 that has read the image is added to the image stored in the hard disk device 115.

  The acquisition unit 6011 of the image analysis unit 601 acquires the above-described information added to the image from the input image.

  The color conversion parameter creation unit 6012 creates a color conversion parameter for converting the color space represented by the image into the S-RGB color space based on the device link profile.

  A resolution conversion parameter creation unit 6013 creates resolution conversion parameters that are thinning rates and interpolation rates to match the resolution of the color printing machine 500 based on the resolution information of the color scanner 400.

  Subsequently, the image is sent to the color processing unit 602 and subjected to color processing.

  The scene analysis unit 6021 analyzes the image with a predetermined algorithm, and the image is assigned to any scene of “person face”, “blue sky”, “underwater”, “evening view”, “night view”, and “nature”. It is determined whether the image is applicable.

  In the color correction unit 6022, the color space is converted into the S-RGB color space by using the color conversion parameter, and for the determined corresponding scene, for example, if the corresponding scene is “Evening”, the human A correction is made to bring it closer to red, which is considered appropriate for the color of the evening scene.

  Here, if an erroneous analysis is performed in the scene analysis in the scene analysis unit 6021, an incorrect color correction is performed, so that all or a part of the RGB values (range 0 to 255) of each pixel constituting the image are greatly increased. Is likely to change.

  Therefore, the color change amount calculation unit 6023 calculates the change amount of the RGB value (range from 0 to 255) before and after color correction of each pixel constituting the image for each color and sums it for each pixel. Is added to the image as a representative change amount of the image.

  The rank assigning unit 6024 ranks the images in descending order of the representative change amount added to the image. The order is added to the image as information.

  Next, the resolution conversion unit 603 converts the resolution of the image based on the above-described resolution conversion parameter, and the sharpness control unit 604 performs edge enhancement using an unsharp mask. Thereafter, the format conversion unit 605 performs JPEG data compression processing, and the thumbnail creation unit 606 creates a thumbnail. The thumbnail created by the thumbnail creating unit 606 is stored in the hard disk device 115. Further, the image subjected to the data compression processing by JPEG in the format conversion unit 605 is stored in the hard disk device 115 together with the order given to the image. The hard disk device 115 stores an image and a thumbnail corresponding to the image in association with each other.

  In this color processing system 1, the same image as the image sent to the image analysis unit 601 is directly sent to the resolution conversion unit 603 without passing through the image analysis unit 601 and the color processing unit 602. Therefore, an unprocessed color image that has not been subjected to color processing is sent to the format conversion unit 605 and the thumbnail creation unit 606 via the sharpness control unit 604. The color unprocessed image sent to the format conversion unit 605 is subjected to data compression processing and stored in the hard disk device 115. A thumbnail is also created for the unprocessed color image sent to the thumbnail creation unit 606, and the thumbnail is stored in the hard disk device 115. The hard disk device 115 stores the color unprocessed image and its thumbnail, the corresponding color processed image that has passed through the image analysis unit 601 and the color processing unit 602, and the thumbnail thereof in association with each other.

  In the display unit 6091 of the display operation unit 609, an icon is displayed on the monitor 220 of the client device 200 so that the operator can preview the color processing image in the client device 200. When the operator receives an operation on the icon, the color processing image is displayed. The thumbnails of the color unprocessed images are read from the hard disk device 115, and the two thumbnails are displayed next to each other in the descending order of the order given to the images on the monitor 220 of the client device 200.

  FIG. 5 is a diagram showing thumbnails displayed on the display screen in the order corresponding to the order given to the images.

  In FIG. 5, thumbnails corresponding to each of the color processed image and the color unprocessed image created by the thumbnail creating unit 606 for the same image are paired, and the higher order is given to the image. Are displayed in order from the top left to the bottom right of the display screen 121.

  The selection correction accepting unit 6093 accepts selection by the mouse 140 for the thumbnail displayed on the display screen 121 of the monitor 220 of the client device 200 by the display unit 6091. The image search unit 6092 searches the hard disk device 115 for both the image with the color correction and the image with the color correction omitted corresponding to the thumbnail selected by the mouse 140. The image extracted from the hard disk device 115 is sent to the output unit 608, and the output unit 608 converts the color space based on the device link profile of the monitor 220 of the client device 200 and sends it to the display unit 6091.

  FIG. 6 is a diagram illustrating an enlarged thumbnail image.

  FIG. 6 shows a screen display 1211 when the selection operation with the mouse 140 is performed on the fourth thumbnail from the top of the rightmost column of the thumbnails shown in FIG. 5. Both the color-processed image and the color-unprocessed image corresponding to the thumbnails that have been made are displayed on the display screen 121 after the color space conversion in the output unit 608.

  Here, the color processing system 1 can perform both redo color correction using a scene designated by the operator and manual color correction on the screen display 1211.

  In the upper part of the screen display 1211, in order from the left, a scene designation area 1211a in which an icon to be operated for performing redo color correction by a scene designated by the operator is displayed, and the operator operates for manual color correction. A manual correction area 1211b in which an icon is displayed, and a selection area 1211c in which an icon to be operated to select whether to re-register or cancel the result image of redo color correction or manual correction as a color processed image are displayed. Is provided. In FIG. 6, the “face” in the scene designation area 1211 a is indicated by hatching because the image currently displayed on the screen display 1211 is color-corrected assuming that it is the scene “human face”. If the operator wants to display a color-processed image when the corresponding scene of the image is analyzed as “empty”, for example, the “empty” portion of the scene designation area 1211a is displayed with the mouse. Click at 140. When the manual correction area 1211b is operated with the mouse 140, another window (not shown) is opened, and manual correction such as tone curve and level correction can be performed on the window.

  As described above, when redo color correction and color correction are completed and the operator operates the icon “registration” in the selection area 1211c, the redo color correction and color correction performed on the redo color correction and color correction are performed. Is stored in the hard disk device 115 in place of the original image that is the target of the above.

  As described above, in this color processing system 1, an image with a larger amount of color change is considered to be more likely to have been subjected to erroneous color processing due to erroneous analysis as an image with a larger amount of representative change accompanying color correction. Since it is possible to visually check the color-processed images arranged in order from the highest ranking, the images that have been subjected to incorrect color processing by misanalysis can be confirmed efficiently, and incorrect colors due to misanalysis The result of processing can be confirmed.

  Further, in this color processing system 1, since both the image subjected to color correction and the image not subjected to color correction can be displayed side by side with respect to the same image, the contents of erroneous color processing due to erroneous analysis are confirmed. be able to. Furthermore, in this color processing system 1, both manual color correction and redo correction using a scene designated by the operator can be performed, and an image subjected to erroneous color processing due to erroneous analysis is applied. The color correction to the color according to the operator's preference or the redo color correction by the scene according to the operator's preference can be performed. As described above, when the confirmation or color correction by the operator is completed and a print instruction is issued for the image designated by the operator, the server apparatus 100 displays a color processed image corresponding to the designated image. The data is read from the hard disk device 115 and sent to the color printer 500 via the output unit 608. The output unit 608 performs color space conversion on the image based on the device link profile of the color printer 500 when transmitting to the color printer 500.

  In the embodiment described above, an example has been described in which thumbnails of color processed images and color unprocessed images are displayed side by side as a pair. However, even if only thumbnails of color processed images are displayed. The basic effect of the color processing system 1 is not reduced.

  Next, a second embodiment of the color processing system of the present invention will be described.

  The difference between the color processing system of the present embodiment and the color processing system 1 of the first embodiment is that the configuration of the color processing unit and the display on the display screen 121 of the images that have been subjected to color correction and ranked. Therefore, the following description will focus on these points.

  FIG. 7 is a diagram illustrating a part of internal blocks of the color processing system. 7 that are the same as those in FIG. 4 are assigned the same reference numerals as those in FIG.

  FIG. 7 shows a color processing unit 802 of the color processing system of the second embodiment corresponding to the color processing unit 602 of the color processing system 1 shown in FIG.

  The color processing unit 802 includes a scene analysis unit 6021, a color correction unit 6022, a color boundary arrival degree calculation unit 8023, and a rank assignment unit 6024.

  Description of the functions of the scene analysis unit 6021 and the color correction unit 6022 has been described above, and will be omitted.

  Here, if the scene analysis unit 6021 performs erroneous color correction by erroneous analysis, all or part of the RGB values (range 0 to 255) of each pixel constituting the image change significantly. Even if none of the RGB values reach 255 before color correction, there is a high possibility that some or all of RGB will reach 255 after color correction. In view of this, the color boundary reach calculation unit 8023 counts pixels in which at least one of the RGB values has reached 255 by color correction, and indicates the ratio (%) of the number to the total number of pixels constituting the image. The degree of color boundary arrival of the image is calculated for each image. The rank assigning unit 6024 ranks the images in descending order of the color boundary arrival degree, and the rank is added to the corresponding image.

  FIG. 8 is a diagram showing thumbnails of images subjected to color processing in the color processing system of the present embodiment.

  In FIG. 8, from the upper left to the lower right of the display screen 121, the thumbnails of the color-corrected images are simply subjected to color correction, not in the order according to the order given to each color-corrected image. They are shown in order.

  In the color processing system of the present embodiment, thumbnails of images given a rank higher than the rank specified by the operator are indicated by being outlined with a black frame 1212. FIG. 8 shows a screen display when the operator inputs “3” in the input area 1211d provided on the upper left side on the screen display 1211 for inputting the order. The thumbnails of the top three images are outlined with a black frame 1212. Further, FIG. 8 shows a scene selection area 1211e indicating the type of scene analysis provided on the upper right side of the screen display 1211. Here, the icon “face” of the scene selection area 1211e is shown. Is shown with diagonal lines. This is because, in order for the operator to know which of the thumbnails shown in the screen display 1211 is a thumbnail of an image that has been analyzed as a “human face” and subjected to color correction, the operator can select a scene selection area 1211e. FIG. 8 shows a state where an ellipse mark 1213 is added to the thumbnail of the corresponding image. In the example of FIG. 8, the thumbnail in the second row from the top of the screen display 1211 in FIG. 8 and the second column from the left is that the scene is “person face” even though the scene is not “person face”. It has been misanalyzed. For this reason, this image is also shown to be bordered by a black frame 1212 indicating that it is that of the image ranked in the top three. In the color processing system of the present embodiment, a color processed image corresponding to the thumbnail selected with the mouse 140 is displayed on the display screen 121, and redo color correction is performed on the color processed image according to a scene designated by the operator. And manual color correction on the screen display 1211 can be performed.

  As described above, in the color processing system according to the second embodiment, an image having a higher degree of color limit achievement due to color correction is given a higher ranking as being more likely to have been subjected to erroneous color processing due to erroneous analysis. Black thumbnails 1212 are attached to the thumbnails of the images from the first place to the designated order, and the scene analysis results performed on the images are known, so that erroneous color processing due to erroneous analysis is performed. The checked image can be checked efficiently.

  Finally, a third embodiment of the color processing system of the present invention will be described.

  Since the difference between the color processing system of the third embodiment and the color processing system of the second embodiment resides in the scene analysis unit and display operation unit of the color processing unit, these will be described below.

  In the scene analysis unit of the color processing system according to the third embodiment, for each image that is sent, first, “person face”, “blue sky”, “underwater”, “evening view”, “night view”, and “nature” are displayed. The probability for each scene is determined based on an algorithm prepared for each scene, and then a scene with a high probability is determined as a corresponding scene as an analysis result. Information representing the probability determined for each scene is added to the image together with information representing the determined corresponding scene. The “probability” is obtained by a known method such as the method disclosed in Japanese Patent Application Laid-Open No. 2006-303899, and thus a detailed description thereof is omitted. However, only the accuracy of the “person face” is described. Whether or not an image portion representing a human face is included in the image is detected and extracted by pattern matching, and the certainty is determined by the circularity of the extracted image portion.

  FIG. 9 is an internal block diagram of the display operation unit of the color processing system according to the third embodiment.

  FIG. 9 shows a display operation unit 809 of the color processing system according to the third embodiment corresponding to the display operation unit 609 of the color processing system 1 shown in FIG.

  The display operation unit 809 includes a display unit 8091, an image reading unit 8092, a scene designation receiving unit 8093, a scene extracting unit 8094, a probability designation receiving unit 8095, a display threshold setting receiving unit 8096, a display condition selection receiving unit 8097, and a probability extraction. Part 8098 and a selection correction accepting part 6093. Note that the selection / correction receiving unit 6093 has been described in the color processing system 1 of the first embodiment, and a description thereof will be omitted here.

  In the display unit 8091 of the display operation unit 809, icons are displayed on the monitor 220 of the client device 200 so that the operator can preview the color processed image in the client device 200. When an operation on the icon is recognized on the display unit 8091, the image reading unit 8092 reads out the thumbnail corresponding to each color-processed image from the hard disk device 115, and the display screen 121 is color-corrected. As in the color processing system according to the second embodiment, the thumbnails of the images given the ranks up to the designated number are shown with a black frame.

  Here, FIG. 10 is a diagram illustrating thumbnails of images subjected to color processing in the color processing system of the third embodiment.

  In FIG. 10, from the upper left to the lower right of the display screen 121, the thumbnails of the images subjected to color correction are not subjected to the order according to the order given to the respective images subjected to color correction, but are simply subjected to color correction. An image display 1211 arranged in the order shown is shown. In addition, since “3” is input in the input area 1211d for inputting the number indicating the order, which is provided on the upper left side on the screen display 1211, the top three ranks with the highest degree of color processing. The thumbnails of the images are outlined with a black frame 1212.

  FIG. 10 shows the result of scene analysis for each image, which will be described in detail later, below the scene selection area 1211e described in the color processing system of the second embodiment, on the upper right side of the screen display 1211. A certainty selection area 1211f for displaying the certainty of each scene from which the corresponding scene is determined is shown. Returning to FIG.

  A scene designation accepting unit 8093 of the display operation unit 809 accepts a scene designation for the scene selection area 1211e.

  A scene extraction unit 8094 of the display operation unit 809 extracts an image that has been analyzed that the scene designated by the scene designation reception unit 8093 is an appropriate scene from among the images whose thumbnails are arranged on the screen display 1211. .

  In FIG. 10, the icon “face” in the scene selection area 1211e is operated by the operator, and a diagonal line indicating that this operation is received by the scene designation receiving unit 8093 is attached to the icon “face” in the scene selection area 1211e. Has been shown. This operation is performed in order for the operator to know which of the thumbnails arranged on the screen display 1211 is the thumbnail of the image whose color is corrected by analyzing the corresponding scene as a human 'face'. It is a thing. Here, simultaneous selection of a plurality of scenes is prohibited.

  As a result of the above operation, in FIG. 10, a portion detected as an image portion representing a human face by pattern matching as described above in the thumbnail of the image analyzed that the corresponding scene is a human “face” Is shown with an ellipse mark 1213. With this function, for example, the operator mistakes that the thumbnail in the second row from the left and the second row from the top is a person's 'face' even though there is no person's 'face' on the image. As a result of the analysis, it can be understood that the ranking of this image is in the top three. If the scene is a scene other than 'face', the illustration is omitted, but if the scene is 'blue sky', the letter 'blue' is displayed in the center of the image and the scene is 'natural'. If it is' The character 'self' is displayed over the center of the image. Returning again to FIG. 9, the description will be continued.

  A probability designation accepting unit 8095 of the display operation unit 809 accepts an instruction to display the certainty of each scene, which is the basis for determining the corresponding scene of each image. This instruction is given to the certainty designation area 1211f shown on the upper right side of the image display 1211 in FIG. 10, and each icon of the scene selection area 1211e shown above is displayed in the certainty designation area 1211f. A check box corresponding to is displayed. FIG. 10 shows that the check boxes corresponding to the icon “face” and the icon “empty” among the six check boxes shown in the probability specification area 1211f are checked. Yes. Returning to FIG. 9, the description will be continued.

  Here, in the display threshold value setting reception unit 8096 of the display operation unit 809, among the images having the certainty about the scene specified by the certainty designation receiving unit 8095, the display of the certainty is performed on the thumbnail. The setting of the threshold value used as the extraction reference is accepted for each scene. That is, even for an image having a certainty about the scene designated by the certainty designation receiving unit 8095, a thumbnail of the certainty within the certainty less than the threshold set by the display threshold setting receiving unit 8096. The above display will be prohibited.

  Further, in the display condition selection receiving unit 8097 of the display operation unit 809, an image in which the probability display is performed on the thumbnail among the images having the certainty for each of the plurality of scenes designated by the certainty designation receiving unit 8095. Accepts selection of a logical operation as a reference for extraction of That is, in the display condition selection accepting unit 8097, if there is even one scene whose probability does not exceed the threshold accepted by the display threshold setting accepting unit 8096 for the plurality of scenes designated by the certainty designation accepting unit 8095, The display on the thumbnail for the certainty of a plurality of specified scenes is prohibited, and “AND” which means a so-called logical product, and the certainty of the scenes specified by the certainty designation receiving unit 8095 is a display threshold. For a scene that exceeds the threshold accepted by the setting accepting unit 8096, one of the settings of 'OR' meaning so-called logical sum that permits display on the thumbnail of the probability of the scene is set. Accept.

  FIG. 11 is a diagram showing a screen display for setting a threshold and selecting a display condition.

  FIG. 11 shows a state where a screen display 1212 for setting conditions is displayed on the display screen 121 by operating an icon (not shown). In this screen display 1212, in the upper part, a threshold value setting area 1212a for setting a threshold value for each of a plurality of scenes also shown in the scene selection area 1211e, and in the lower part, AND and logical sum indicating logical product are displayed. A logical operation selection area 1212b for selecting one of the meanings 'OR' is provided.

  Further, in FIG. 11, in the threshold setting area 1212a, the threshold value for the scene “face” is “60%”, the threshold value for the scene “sky” is “30%”, and the threshold value for the scene “sea” is “30%”. “,“ 20% ”is set as the threshold value for the scene“ evening ”,“ 30% ”is set as the threshold value for the scene“ night ”, and“ 30% ”is set as the threshold value for the scene“ nature ”. The state where “OR” is selected is shown. Returning to FIG. 9 again, the description will be continued.

  The probability extraction unit 8098 of the display operation unit 809 extracts an image corresponding to the threshold set in the screen display 1212 of FIG. 11 and the selected logical operation from among the images displaying thumbnails. In FIG. 10, the likelihood is displayed by being superimposed on the thumbnail of the image extracted by the probability extraction unit 8098. For example, in the uppermost image in the third column from the left, the probability “70%” for the scene “face” and the probability “65%” for the scene “sky” are displayed in an overlapping manner. This is because the scene “face” in which the check box shown in the certainty designation area 1211f is checked out of the certainty of each scene from which the corresponding scene “face” is determined for this image. This is because both of the certainty of the scene and the certainty of the scene “sky” are equal to or greater than the threshold set for each scene.

  In addition, if only one of the certainty of the scene 'face' and the certainty of the scene 'sky' is superimposed on the image, the probability of the scene 'face' and the certainty of the scene 'sky' This is because the probability of either one of the randomness is below the threshold value.

  FIG. 10 shows a case where “OR” is selected in the logical operation selection area 1212b shown in FIG. 11, and when “AND” is selected in the logical operation selection area 1212b, a scene is displayed. Either the likelihood of 'face' and the probability of 'sky' of the scene are both overlaid on the image because they are greater than or equal to the threshold set for each, and one of the certainty Or both are less than a threshold value, and it becomes either of the aspects in which a probability is not displayed. Accordingly, there is no aspect in which only one of the probability of the scene 'face' and the probability of the scene 'sky' is displayed superimposed on the image. When only one of the check boxes shown in the certainty designation area 1211f is checked, selection of “AND” or “OR” in the logical operation selection area 1212b has no meaning.

  As described above, in the color processing system according to the third embodiment, thumbnails of a plurality of images subjected to color processing are displayed in the order of processing, and within the order of values specified from the one with the higher degree of color processing. A black frame is attached to the thumbnail of the image, and a mark corresponding to the corresponding scene is attached to the thumbnail of the image specified by the scene selection area 1211e and the same scene as the scene analysis result. As a result, the operator, for example, has a higher level of color processing because the result of scene analysis of the thumbnail image is a human face even though the human face does not exist in the thumbnail. It is possible to confirm the causal relationship between the corresponding scene and the order as a result of the scene analysis.

  In the color processing system according to the third embodiment, the operator can confirm the certainty of a designated scene among a plurality of scenes for each image.

Furthermore, in the color processing system according to the third embodiment, the image display of the certainty for the scene designated in the certainty designation area 1211f can be displayed only for the threshold setting area 1212a or more. As a result, according to the color processing system of the third embodiment, it is possible to display only images with a high probability of the designated scene, and it is possible to efficiently narrow down the causes of defects due to color processing. For example, even if it is an image of 'Underwater', the probability of 'Underwater' is not displayed, or it is clearly an image of 'Underwater' and there is an indication of 'Underwater'. From the situation where the ranking is high, the cause of the failure can be narrowed down efficiently. Moreover, since the amount of extraction information can be adjusted, for example, an extraction mode in which the cause of a defect can be easily pursued can be obtained.
Furthermore, by setting the threshold value for a specific scene low, it is possible to find an image in which any element of the specific scene exists.

  Further, in the color processing system according to the third embodiment, the image display of the certainty about the scene designated in the certainty designation area 1211f may be in accordance with the selection of the logical computation in the logical computation selection area 1212b. In particular, by selecting a logical product as a logical operation in the logical operation selection area 1212b, it becomes easy to confirm when the cause of the failure due to color processing is complex.

  In the embodiment described above, the scene analysis is described as an example of the image analysis according to the present invention. However, the image analysis according to the present invention is not limited to this, and the white balance processing analysis is used. There may be. Further, in the embodiment described above, as an example of the degree of the failure described in the present invention, the amount of change of each RGB color value accompanying color correction and the color boundary reachability of RGB values accompanying color correction are described as examples. However, the degree of the problem referred to in the present invention is not limited to these as long as it is a predetermined change element indicating an excessive degree of color correction.

It is a schematic block diagram of a color processing system. It is an internal block diagram of a main-body part. It is a block diagram of a color processing program. It is a figure showing the outline of the effect | action by these elements constructed | assembled on this computer in order to operate a server apparatus and a client apparatus as 1st Embodiment of a color processing system. It is a figure which shows the thumbnail displayed on the display screen in the order according to the order | rank given to the image. It is a figure which shows the enlarged image of a thumbnail. It is a figure which shows a part of internal block of a color processing system. It is a figure which shows the thumbnail of the image which performed the color process in the color processing system of this embodiment. It is an internal block diagram of the display operation part of the color processing system of 3rd Embodiment. It is a figure which shows the thumbnail of the image in which the color processing was performed in the color processing system of 3rd Embodiment. It is a figure which shows the screen display for the setting of a threshold value and the setting of a display condition.

Explanation of symbols

1 color processing system 100 server apparatus 601, 701 image analysis unit 6011, 7011 acquisition unit 6012, 7012 color conversion parameter creation unit 6013, 7013 resolution conversion parameter creation unit 602, 702 color processing unit 6021, 7021 scene analysis unit 6022, 7022 color Correction unit 6023, 7023 Color change amount calculation unit 6024, 7024 Ordering unit 603, 703 Resolution conversion unit 604, 704 Sharpness control unit 605, 705 Format conversion unit 606, 706 Thumbnail creation unit 608, 708 Output unit 609, 709 Display operation Unit 6091, 8091 display unit 6092 image search unit 6093 selection correction receiving unit 700 color processing program 8092 image reading unit 8093 scene designation receiving unit 8094 scene extraction unit 8095 sure Likeness designation acceptance unit 8096 Display threshold setting acceptance unit 8097 Display condition selection acceptance unit 8098 Probability extraction unit

Claims (16)

An image analysis unit that performs image analysis on each of a plurality of images;
For each of the plurality of images, a color processing unit that performs color processing based on the result of the image analysis for each image;
For each image that has undergone color processing in the color processing unit, a defect detection unit that detects the degree of a defect related to color that occurs with the color processing;
A color processing system comprising: a rank assigning unit that assigns a rank according to the degree of defect detected by the defect detection unit to each of the plurality of images.   The color processing system according to claim 1, further comprising a search unit that searches for an image using the rank assigned by the rank assigning unit.   The color processing system according to claim 1, further comprising a display unit that displays the ranks assigned by the rank assigning unit.   The plurality of images are displayed, and among the plurality of images, a ranking indicating that the ranking is high is given to images from a higher ranking given by the ranking granting unit to a predetermined ranking. The color processing system according to claim 1, further comprising: a display unit that displays   5. The color processing according to claim 1, further comprising: a display unit configured to display the plurality of images side by side in the order assigned by the order assigning unit to display the order. system.   A display unit is provided that displays the order by displaying the plurality of images side by side in the order given by the order giving unit, and also displays the images before and after the color processing for each of the plurality of images. The color processing system according to any one of claims 1 to 5. A display unit for displaying the plurality of images in order by displaying the images arranged in the order given by the rank assigning unit;
The selection correction receiving part which receives the selection correction operation which selects an image from the images displayed on the said display part, and corrects a color is provided, The any one of Claim 1 to 6 characterized by the above-mentioned. Color processing system.   The defect detection unit detects, as the degree of the defect, a predetermined change element indicating an excess degree of the color processing among various change elements included in the image change before and after the color processing. The color processing system according to claim 1, wherein there is a color processing system.   9. The defect detection unit, as the degree of the defect, calculates a maximum color change amount among color change amounts before and after the color processing in various places in an image. The color processing system according to claim 1. The image is a color represented within a predetermined color reproduction range,
2. The defect detection unit, as the degree of the defect, calculates an increase amount before and after the color processing at a position reaching the boundary of the color reproduction range in an image. The color processing system according to any one of 1 to 9. The image analysis unit analyzes the scene corresponding to an image among a plurality of predetermined scenes as the image analysis,
The color processing system according to claim 1, wherein the color processing unit performs color processing according to a scene obtained by the image analysis. A scene designating unit for designating a scene selected from the plurality of scenes;
Among the plurality of images, a scene extraction unit that extracts an image analyzed by the analysis by the image analysis unit and corresponding to the scene specified by the scene specification unit;
The plurality of images are displayed, and an image extracted by the scene extraction unit among the plurality of images is displayed with a mark indicating that it is an extracted image and a rank assigned by the rank assigning unit. The color processing system according to claim 11, further comprising a display unit. The image analysis unit calculates a probability that the image corresponds to each scene, and analyzes that the image corresponds to a scene having the highest probability,
A scene designating unit for designating one or more scenes selected from the plurality of scenes;
A display unit that displays the plurality of images, displays the ranks assigned by the rank assigning unit, and further displays a probability corresponding to the scene designated by the scene designation unit along with each image; The color processing system according to claim 11 or 12, further comprising: The image analysis unit calculates a probability that the image corresponds to each scene, and analyzes that the image corresponds to a scene having the highest probability,
A scene designating unit for designating one or more scenes selected from the plurality of scenes;
Among the plurality of images, in the analysis by the image analysis unit, a probability extraction unit that extracts an image in which the probability corresponding to the scene specified by the scene specification unit reaches a default value;
A display unit that displays the plurality of images, displays the ranks assigned by the rank assigning unit, and displays the probability of the images extracted by the probability extracting unit along with each image; The color processing system according to claim 11, wherein the color processing system is a color processing system. When a plurality of scenes are designated by the scene designation unit, a condition setting unit that receives a setting for whether the certainty reaches a default value is used as a logical product or a logical sum for the designated plurality of scenes. With
The color processing system according to claim 14, wherein the probability extraction unit extracts an image using a logical operation set by the condition setting unit. A default value setting unit for receiving the setting of the default value;
The color processing system according to claim 14, wherein the probability extraction unit extracts an image using a default value set by the default value setting unit.

Images