JP2013131077A - Image processor, image processing method and program and image processing system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain an image processor and an image processing method that can appropriately perform image conversion processing for converting a photographic image in which a face of a person or the like is imaged into a painterly image.SOLUTION: An image processor comprises: a communication section 40 for receiving image data uploaded from an external terminal via a network; a face detection processing section 314 for detecting a face from an image represented by the image data received; and a picture conversion processing section 302 that sets a predetermined region corresponding to the face to the image and applies painterly conversion processing for performing first painterly conversion of the image data of the predetermined region and second painterly conversion different from the first painterly conversion of the image data of regions other than the predetermined region. The image processor transmits the image data after conversion to the terminal by the communication section 40. On account of this, by performing painterly conversion of a face portion in the image suitable for the face and performing painterly conversion of portions other than the face portion suitable for a background, the image processor realizes natural painterly conversion as a whole.

Description

  The present invention relates to an image processing apparatus, an image processing method, and a program which are processed by changing the degree of conversion of a person's face part when, for example, converting a photographic image including a person into a painting.

  In recent years, with the widespread use of digital cameras, the way to enjoy photos has become diversified. In particular, since it is digital image data, various image processing is possible.

  For example, a technique has been proposed that can generate and display an image with a different tone (such as a painting tone) based on an original photograph by adding image processing (for example, a patent) Reference 1).

  The technology of Patent Document 1 is developed, and features such as color information and brushing information are extracted from the image of the painting actually drawn by the painter, and the extracted feature is added to the photographed image, so that the entire original image can be obtained. Considering this, a technique for converting to a painting-like image with high artisticness has also been proposed (see, for example, Patent Document 2).

  In addition, a technique for changing a picture quality such as a painting style has been proposed (see, for example, Patent Document 3).

  In addition, a technique has been proposed in which image tone conversion such as a painting tone is performed at a network service site to which an arbitrary terminal can be connected via the Internet (for example, see Patent Document 4).

JP-A-8-44867 JP 2004-213598 A JP-B-1-46905 JP 2011-243187 A

  However, when converting a photo into a painting-like work, it is possible to obtain artistic effects even when bold, such as landscapes, flowers, and buildings, but in the case of a human face, There was a problem that it might become a work that looks strange when it is subjected to various transformations.

  Further, when printing image data that has undergone image tone conversion, there has been a problem that the above-described unnaturalness of the face is more conspicuous.

  The present invention naturally detects a human face by performing a different tone conversion between a face area and another area by detecting a face area when performing a tone conversion such as a painting style. An object is to provide an image processing apparatus, an image processing method and program, and an image processing system that can be expressed.

  In order to solve the above problem, in the first invention, in an image processing apparatus connected to an external terminal via a network, a receiving means for receiving original image data uploaded from the terminal; Image-tone conversion means for converting into converted image-tone image data of a predetermined image tone, transmission means for transmitting the converted image-tone image data converted into a predetermined image tone by the image-tone conversion means to the terminal, and the original A face detection means for detecting a face from image data; and an area setting means for setting a predetermined area corresponding to the face detected by the face detection means for the original image data, and the image tone conversion means When the original image data is converted into the predetermined image tone, the image data of the predetermined area set by the area setting means includes a first Subjected to conversion processing, wherein the image data of a predetermined region other than the region, there is provided an image processing apparatus characterized by comprising a conversion adjusting means the second conversion process is performed.

  In the second invention, in an image processing apparatus connected to an external terminal via a network, receiving means for receiving original image data uploaded from the terminal; and the original image data having a predetermined image tone Image-tone conversion means for converting into converted image-tone image data, selection means for selecting the predetermined image-tone type, and a converted image converted by the image-tone conversion means into the image tone of the type selected by the selection means Transmitting means for transmitting toned image data to the terminal, face detecting means for detecting a face from the original image data, and a predetermined area corresponding to the face detected by the face detecting means is set for the original image data. An area setting unit, and the image tone conversion unit converts the original image data into a type of image tone selected by the selection unit. The image data of the predetermined area set by the area setting means is subjected to a first conversion process, and the image data of an area other than the predetermined area is provided with a conversion adjustment means for performing a second conversion process. An image processing apparatus is provided.

  According to the present invention, when converting a photographic image in which a person is photographed into an image having a predetermined image tone such as a painting tone, it is possible to eliminate the unnaturalness of the entire image and realize a tone conversion in which a person's face looks natural. can do.

1 is a block diagram showing a configuration of a network system of an image processing system according to an embodiment of the present invention. The figure which shows an example of the terminal by the embodiment. The functional block diagram which shows schematic structure of the terminal by the embodiment. The figure which shows the image selection screen of the terminal by the embodiment. The block diagram which shows schematic structure of the server by the embodiment. The figure which shows the attribute information of the user ID by the embodiment. The figure which shows the attribute information of image ID by the embodiment. FIG. 5 is a process diagram for illustrating data exchange between the terminal and the server according to the embodiment. The flowchart for demonstrating the picture conversion process by the embodiment. The figure for demonstrating the fineness in an image tone conversion process. The figure for demonstrating the shape of the touch (brush) in an image tone conversion process. 6 is a flowchart for explaining face detection processing according to the embodiment; The figure for demonstrating creation of the area | region of the face by the embodiment. The figure for demonstrating a face area | region map. The figure for demonstrating the picture conversion using a face area | region map. The figure for demonstrating the boundary of a face area | region. The flowchart for demonstrating download of the work in the embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 1 is a block diagram showing a configuration of a network system of an image processing system according to an embodiment of the present invention.

  Reference numeral 10 in the figure denotes an image service site having an SNS (social network service) function, and is connected to a plurality of terminals 1-1, 1-2, 1-3,.

  The image service site 10 includes a server 11 and image data uploaded from a user by a plurality of terminals 1-1, 1-2, 1-3... (Mainly image data of a photograph taken by a digital camera). This site provides services such as storage of images, conversion of uploaded image data into painting-like images, browsing of uploaded images and converted painting-like images, downloading, and printing.

  Further, the image service site 10 includes a printing device 12 and prints a picture-like image, which has undergone an order from the user and converted into a painting, on a print medium. Note that the printing device 12 is not limited to that provided in the image service site 10, but also includes those obtained from other sites that provide image data print services.

  The terminals 1-1, 1-2, 1-3... Are arbitrary devices having a communication function and a function for displaying an image represented by image data, for example, a normal personal computer or a mobile phone terminal. It is.

  FIG. 2 is a diagram illustrating an example of a terminal 1-1 that can access the image service site 10, and more specifically, a smartphone that is a so-called multifunctional mobile phone terminal. As shown in FIG. 2, the terminal 1-1 has a relatively large display screen 84a on which an arbitrary image 91 can be displayed.

  FIG. 3 is a functional block diagram showing a schematic configuration of the terminal 1-1. Reference numeral 81 denotes a camera installed on the back surface of the terminal 1-1 not shown in FIG. 2, and functions to shoot an arbitrary subject and acquire it as image data.

  A transmission unit 82 functions to access the server 11 and upload image data of a photograph taken by the camera 81 to the server 11 as necessary.

  A receiving unit 83 functions to receive control data transmitted from the server 11 and painting-like image data after painting conversion by the server 11.

  84 denotes a display unit that functions to display an image captured by the camera 81 on the display screen 84a shown in FIG. 2 and a painting-like image based on the painting-like image data downloaded from the server 11 by the receiving unit 83. The display screen 84a also functions as a touch pal, and various operation screens are displayed on the display screen 84a.

  For example, as shown in FIG. 4, the operation screen includes an image selection screen 801 in which a plurality of image selection buttons 801a, 801b, 801c,... Are arranged to allow the user to select a desired image adjustment. It is.

  A storage unit 85 mainly functions to store image data of images taken by the camera, picture-like image data downloaded from the server 11, and the like.

  A display control unit 86 functions to cause the display unit 84 to display an image, an operation screen, or the like on the display unit 84 in accordance with a predetermined display control program.

  A communication control unit 87 functions to cause the transmission unit 82 and the reception unit 83 to perform data communication such as uploading and downloading of image data in accordance with a predetermined communication program.

  Reference numeral 88 denotes an operation control unit for detecting the touch position of the display screen 84a (touch panel) by the user, specifying the instruction content of the user, and supplying the specified instruction content to the display control unit 86 and the communication control unit 87. To work.

  FIG. 5 is a block diagram illustrating a main part of the configuration of the server 11 that implements the image service site 10. The server 11 is provided with a member area 100, a common area 200, and a control area 300.

  The member area 100 is an area provided for each registered member, and has a user ID 102 for identifying the member and various attribute information 104 for each user correspondingly.

  As shown in FIG. 6, the attribute information 104 is user-specific information such as name, handle name, gender, age, region, membership type, and the like. The membership type includes a free member who has just registered for free, a paid member who has registered for a fee, and a premium member who satisfies a predetermined condition such as paying a special membership fee (for example, an annual membership fee).

  Reference numeral 106 denotes an uploaded image area in which image data of a photograph uploaded by the user is stored, reference numeral 108 denotes a work buffer area in which a painting-like image (work) converted into a painting on the image service site 10 is stored, and reference numeral 110 denotes another user. This is the download work buffer area where you download and store your work.

  The common area 200 is an area provided in common to all users, and includes a work area 202 in which a number of works obtained by converting an image uploaded by the user into a painting style are stored.

  Each work stored in the work area 202 stores an image ID 204 for identifying the work and attribute information 206 of the work together with image data 208.

  As shown in FIG. 7, the attribute information 206 includes a user ID indicating the contributor of the work, date information such as a creation date or a posting date, image type information such as the size of the image data and the type of the image, Access number information indicating the number of times of browsing, download number information indicating the number of times the work has been downloaded, point information indicating evaluation of the work, and other information unique to the work. The user ID can identify the creator of the work and can identify whether the creator is a paid member or a premium member.

  The control area 300 includes a painting conversion processing unit 302, a parameter table 304, a face area map 306, a display control unit 308, an evaluation control unit 310, a member management unit 312, a face detection processing unit 314, and a print processing unit 316. Yes.

  The painting conversion processing unit 302 performs a painting conversion process for converting the image data stored in the work buffer area 108 into painting-like image data. The face detection processing unit 314 detects the face of an arbitrary person from the image data stored in the work buffer area 108. The parameter table 304 stores parameters for picture conversion that the picture conversion processing unit 302 refers to in the picture conversion process. The face area map 306 stores data indicating the face area in the image that is referred to by the picture conversion processing unit 302 during the picture conversion process. The display control unit 308 stores a control program for displaying works on the screens of the terminals 1-1, 1-2, 1-3,.

  The evaluation control unit 310 evaluates the work stored in the work buffer area 108 of the member area 100 according to the number of accesses and gives points for each work. The member management unit 312 manages members based on the user ID and controls services for free members, paid members, and premium members. The member management unit 312 also manages the SNS function of the image service site 10. The print processing unit 316 performs print processing of a work by the printing apparatus 12.

  The server 11 is provided with a CPU 20, a display buffer 30, and a communication unit 40. The CPU 20 controls the entire server 11 (each unit described above) and performs various processes necessary for displaying a list of many works on the Internet. The processing performed by the CPU 20 includes processing accompanying the painting conversion processing in the painting conversion processing unit 302. The display buffer 30 is a working memory for developing a display image when the CPU 20 displays a large number of works as a list. The communication unit 40 performs communication processing necessary for data transmission / reception between the terminals 1-1, 1-2, 1-3,.

  Hereinafter, specific operations of the image processing system of the present embodiment will be described with reference to flowcharts.

  First, referring to FIG. 8, image upload, display, browsing, download, and the like are performed between the terminals 1-1, 1-2, 1-3,... And the server 11 of the image service site 10. The process will be described.

  If the user is a member (free member, paid member, or premium member), the user accesses the image service site 10 from his / her terminal 1 (step SB1). The server 11 authenticates the user ID by logging in the user (step SC1), and when it is confirmed that the user is a member, the server 11 transmits the member's page so that the member can see it (step SC2).

  When the member's own page is opened, the member uploads an image from the terminal 1 (step SB2). The uploaded image, that is, the original image data is received by the communication unit 40 and then stored in the upload image area 106 of the member area 100 of the server. When the member selects the type of painting style desired and requests the picture conversion of the uploaded image (step SB3), the server 11 performs a picture conversion process (step SC3), and the converted image, that is, the work is a work. It is stored in the buffer area 108.

  Here, when the member requests picture conversion from the server in step SB3, for example, when the terminal used by the member is the terminal 1-1 shown in FIG. 2, the member performs the predetermined operation as shown in FIG. A desired image tone type is selected by displaying an appropriate image tone selection screen 801 on the terminal 1-1. The type of image tone selected by the member is transmitted from the terminal 1-1 to the server 11 as the type of image tone to be converted.

  Also, the converted image-tone image data, which is a work converted by the server 11, is transmitted from the server 11 to the member's terminal 1 and displayed on the terminal 1.

  When the member requests printing of the converted work (step SB4), the painting-like image data, which is image data after the painting conversion process stored in the work buffer area 108, is transmitted from the server 11 to the printing device 12 by the communication unit 40. And the print processing is performed (step SC4). In the print process, the work is printed on a predetermined print medium based on the painting-like image data. The print medium is sent to the member offline.

  In addition, the member may enjoy the converted work as it is, but if he wants to make it available to other users, he / she posts it (step SB5). The submitted work is transferred from the work buffer area 108 in the member area 100 to the work area 202 in the common area 200 and stored. Note that the attribute information 206 as described in FIG. 7 is also added to the works in the work area 202.

  The works in the work area 202 are displayed as a list by the server 11 as necessary (step SC5). Note that the server 11 appropriately resizes the works in the work area 202 when displaying the list. That is, since the size of the work in the work area 202 is usually larger than the image size for list display, the work is reduced, and when the size of the work in the work area 202 is smaller than the image size for list display. Enlarge the work.

  In addition, the member can browse any work displayed in a list at an actual size by requesting browsing (step SB6). When there is a viewing request, the server 11 displays the requested work in actual size (step SC6) and adds points to the work requested to be browsed (step SC7).

  In addition, the member can press a GOOD button indicating that he likes the viewed work or write a comment such as an impression (step SB7). When the GOOD button is pressed or a comment such as an impression is written, the server adds points of attribute information of the viewed work (step SC7). This increases the evaluation of the work. It is assumed that the number of points for writing comments is higher than that for the GOOD button.

  Further, the member can request download of the viewed work (step SB8). When the server 11 receives a download request from the member, the server 11 permits download as necessary (step SC8), and the member can download the viewed work only when the download is permitted (step SB9). The downloaded work is stored in the download work buffer 110 in the member area 100.

  The server 11 also adds points to the work even when there is a download request (step SC9).

  On the other hand, a user other than the member, that is, an arbitrary user, accesses the image service site 10 as appropriate (step SA1), and browses in a state in which the works stored in the work area 202 of the common area 200 are displayed as a list. can do. Furthermore, an arbitrary user can also browse an arbitrary work displayed in a list at an actual size by requesting browsing (step SA2).

  When the user browses the work viewed by an arbitrary user and presses the GOOD button (step SA3), the server 11 also adds points to the viewed work (step SC7).

  Next, a picture conversion processing technique when the server 11 converts uploaded image data into a picture-like image will be described.

  Picture conversion means that each pixel constituting an image such as a photo is converted according to predetermined parameters (painting conversion parameters), oil painting, watercolor, pastel, colored pencil painting, crayon painting, illustration painting, dot drawing. This is an image processing technique for converting into a so-called painting tone, such as a tone, an airbrush, a silk screen tone, an embroidery tone, and a collage tone. These multiple image tones are referred to as types of image tones.

  In picture conversion, parameters of various effect processes known basically by photo retouching software or the like are automatically adjusted and combined so that the original image to be processed is converted to look like a picture.

  As effect processing, for example, texture processing is performed by mapping a texture to an image to give a special texture, and the image is classified into a texture portion and a flat portion such as a contour portion, a fine pattern, etc. Resolution processing that enhances resolution, HSV processing that adjusts the color by classifying it into three elements of Hue, Saturation, and Lightness (Value), R (Red) G (Green) B (Blue) ) RGB processing for adjusting the degree of each color, RGB exchange processing for exchanging in the direction of R → G → B, edge extraction processing for applying a filter called a Laplacian filter, intermediate density extraction processing for applying a filter called a median filter, adjacent pixels The RGB histogram is extracted, and the density extraction process is performed when the minimum / intermediate / maximum density is extracted, respectively, the darkest part of the image is black, The white part is white and the histogram between them is distributed as appropriate, the contrast is corrected and the histogram of the image is expanded, the gamma correction process that adjusts the intermediate brightness while maintaining the bright and dark parts, the image Shadow processing that brightens dark areas or darkens bright areas, Solarization processing that inverts RGB values when the RGB value of each pixel is equal to or higher than the threshold value, draws dots randomly, There is noise addition processing that generates noise and adjusts the amount and color of noise.

  In addition, a photo with a wide dynamic range that cannot be represented by a normal photo called HDR (High Dynamic Range) is included in a narrow dynamic range width by tone mapping to correct overexposure and overexposure blackout. There is also an effect process that increases expressiveness. The HDR is one of effect processes, but is also one of the types of image tone.

  In other words, the picture conversion process is a kind of effect process in principle, and the picture conversion algorithm creates various painting styles by combining the effect process and parameters, and the conversion algorithm is programmed.

  In the conversion algorithm, a parameter group P which is a set of the parameters for converting the pixels of the original image is prepared in advance. If there are 12 types of image tone types, the parameter groups are represented as P (1) to P (12). The tone of the converted image also changes depending on how the parameters are determined. Assuming that a parameter group for converting to an oil painting tone is P (1), and there are m parameters necessary for effect processing for converting an image so that it looks like an oil painting tone in P (1), the parameter is The parameters can be expressed as parameters P1 to Pm, and the parameter group P (n) includes a plurality of parameters P1 to Pm.

  A pixel is generally expressed by gradations of a plurality of bits for each of RGB, but a parameter is an element for performing an operation on the bit data. For example, when the red component is emphasized and the green component and the blue component are slightly suppressed, the coefficients “2” and “0.9” are used in the calculation such as R × 2, G × 0.9, and B × 0.5. "," 0.5 "is a parameter.

  Alternatively, the calculation elements are programmed in advance, and R × 1.1 when the red emphasis level is 1, R × 1.2 when the emphasis level is 2, and R × 1.3 when the emphasis level is 3. The degree of emphasis when performing simple calculations is also a parameter.

  In addition, a predetermined calculation may be performed between the target pixel and adjacent pixels. For example, as shown in FIG. 10A, the pixel A1 (RGB), A2 (RGB), A3 (RGB), A4 (RGB), A5 (RGB), A6 (RGB) centering on the target pixel A5 (RGB). , A7 (RGB), A8 (RGB), and A9 (RGB) are aligned vertically and horizontally, A5 (R) = A1 (R) × q1 + A2 (R) × q2 + A3 (R) with respect to A5 (R). The calculation of * q3 + A4 (R) * q4 + A5 (R) * q5 + A6 (R) * q6 + A7 (R) * q7 + A8 (R) * q8 + A9 (R) * q9 is performed, and the same calculation is performed for G and B. Here, q is a parameter, and different effect processing can be performed by changing this numerical value (coefficient).

  There is also an effect process that processes the touch (hereinafter referred to as “brush touch”) differently.

  Specifically, pixels having high correlation are collected from pixels constituting image data on the basis of color or the like to form a group. Subsequently, for each group of pixels, for the same group of pixels, the color is replaced with the representative color of the group. A group of pixels in which the colors are replaced with the representative colors in this way form each brush stroke. According to such image processing, by changing the correlation of the pixels collected as a group and the shape (length (distance), flatness) of the group composed of pixels of the same color (representative color) The formed brush can be changed, and as a result, the tone of the image represented by the image data can be changed to various painting tone. For each image tone, an optimum combination of parameters such as the degree of correlation used in each process, the length representing the shape of the group, and the flatness is set.

  For example, when the shape of the group of pixels having high correlation with the target pixel A5 is the shape shown in FIGS. 11A and 11B, the shape shown in FIG. The flatness is larger and the length (distance) is shorter than the shape shown in FIG.

  Changing each of the plurality of pieces of image data to a different stroke can be realized by adjusting the shape of the group in which the pixels constituting the stroke are collected, for example, the flatness of the group when changing the image tone. When the flatness of the group composed of pixels of the same color representing the brush stroke is increased, the brush stroke becomes thick, and as a result, the touch of the image is displayed roughly. When the flatness of the group composed of pixels of the same color is reduced, a small brush can be created, and as a result, the touch of the image is displayed finely.

  The picture conversion algorithm described in detail above is stored in the picture conversion processing unit 302 of the control area 300 of the server 11, and the parameter group is also stored in the parameter table 304 of the control area 300.

  FIG. 9 is a flowchart showing a picture conversion process performed by the picture conversion processing unit 302. In the server 11, as shown in FIG. 6, the picture conversion processing unit 302 first performs preprocessing (step SC101). This process is executed in common regardless of the type of image tone.

  Since the effect processing as described above is performed on each pixel, the image data needs to be in a bitmap format. Therefore, the picture conversion processing unit 302 converts image data normally expressed in the JPEG format into a bitmap format.

  The picture conversion processing unit 302 has various sizes of image data uploaded from the terminals 1-1, 1-2, 1-3..., And this is reduced to the number of pixels in the display area, for example, 800 × 600 pixels. Resize. Larger images are reduced and smaller images are enlarged. This is because the parameters are fixed when the size is determined, and the processing is efficient. Of course, at the time of picture conversion of the main image, which will be described later, the picture conversion is performed for the size of the uploaded image data as it is.

  Next, the picture conversion processing unit 302 confirms whether or not the image to be converted includes a face by face detection processing (step SC102). This is because the face portion becomes unnatural when an extreme conversion is applied to the face portion in the image, so that the face portion is subjected to painting conversion processing different from other portions. More specifically, this is because a picture conversion process in which the conversion intensity is set weaker than the other parts or a picture conversion process that is finer than the other parts is performed on the face part. Basically, this is because a picture conversion process is performed on the image to be converted so that the image after the conversion process has a face portion closer to the conversion target image than the other portions.

  “Detailed” means that a group of target pixels is reduced when effect processing is performed. For example, in the case of blurring processing, a group is formed between adjacent pixels for the pixel of interest A (x, y), and blurring is performed by taking the average value of each pixel and replacing the pixels in the group with the average value. Expresses feeling (smoothing or airbrushing). At this time, for example, when the pixels A1, A2, A3, A4, (A5), A6, A7, A8, and A9 are adjacent to each other with the pixel of interest A5 as the center, A2, A4, A6, and A8 on the top, bottom, left, and right of the pixel A5. When the four pixels are grouped with respect to the target (see FIG. 10B), the eight pixels of the surroundings A1 to A9 are grouped (see FIG. 10C), and the surroundings are also included. In addition, it is assumed that the pixel is finer than the case of grouping for 24 pixels (see FIG. 10D) (the opposite word is coarse).

  Further, depending on the type of image tone, the grouping may be performed in an indefinite form as shown in FIG. Also in this case, it is assumed that it is finer to perform the tone conversion process for a small group for each smaller number of pixels than to perform a tone conversion process for a large number of pixels as one group.

  Similarly, touch processing is performed more frequently in a group formed with a smaller number of pixels as shown in FIG. 11A, and a smaller number of processes are performed in a group formed with a larger number of pixels as shown in FIG. 11B. It is more detailed than processing it once.

  The face detection process will be described later with reference to the flowchart of FIG. 12, but since the importance varies between the face area and the background area in one image, the picture conversion processing unit 302 performs the face detection process. Then, data of a face area map indicating the face area in the processing target image is created and stored in the face area map 306 of the control area 300.

  Subsequently, the painting conversion processing unit 302 causes the user to select a desired tone from among oil painting, watercolor, pastel, colored pencil, etc. (step SC103).

  When the image tone is selected, the picture conversion processing unit 302 proceeds to the flow of each picture conversion algorithm. For example, if it is oil painting tone conversion, the process proceeds to step SC104, and if it is watercolor painting tone conversion, the process proceeds to step SC105. Otherwise, the flow proceeds to a flow of another picture conversion algorithm (step SC106). The painting conversion processing unit 302 refers to the parameter table 304 and the face area map 306 in the control area 300 when executing each algorithm (steps SC107, SC108, SC109, and SC110).

  At the time of picture conversion in steps SC104, SC105, and SC106, the picture conversion processing unit 302 performs picture conversion on image data having a display screen size displayed as a list. The converted image is sent to the user's terminal 1 and displayed on the screen at the terminal 1. After that, if a decision is instructed from the user's terminal 1 (step SC112: YES), the picture conversion processing unit 302 proceeds to the picture conversion of the main image (step SC113), and is instructed to redo with another image tone. If it is (step SC112: NO), the process returns to step SC103.

  In the picture conversion of the main image in step SC113, the picture conversion processing unit 302 performs the picture conversion by referring to the parameter table 304 and the face area map 306 using the picture conversion algorithm determined in step SC112 (steps SC114 and SC115). Even if the image tone is the same, the appropriate parameter differs when the image size is different. Therefore, the parameter table referred to in step SC115 is different from the parameter acquired in step SC107 or SC108.

  Thereafter, the picture conversion processing unit 302 performs post-processing to convert the main image after the picture conversion back into the JPEG format (step SC116).

  Next, the face detection process of step SC102 described above will be described with reference to FIGS.

  As shown in FIG. 12, in the face detection process, the picture conversion processing unit 302 first detects a face with the face detection processing unit 314 using target image data as a target (step SC151). Here, since the face detection technique is known, it will not be described in detail.

  Next, the picture conversion processing unit 302 sets a face area for the target image data (step SC152). At this time, even if the face can be detected in step SC151, since it is difficult to accurately extract the contour, the painting conversion processing unit 302 has an ellipse or a square including the face part. Set the area as the face area.

  FIG. 13 is a diagram for explaining an example of an emphasis area including a face area. In FIG. 13, sq is a square area including a face F1, and el includes a face F1. This is an ellipse region. That is, sq and el are areas corresponding to the detected face. That is, a rectangular area including the detected face area is sq, and an elliptical area inscribed by the sq is defined as el.

  Thereafter, the picture conversion processing unit 302 creates a face area map (step SC153). FIG. 14 is a conceptual diagram for explaining a face area map. In step SC153, when the picture conversion processing unit 302 detects the faces F1, F2, and F3 from the image data as shown in FIG. 10A, the face regions sq1, sq2, and so on shown in FIG. sq3 is set in the image data. That is, the picture conversion processing unit 302 stores data indicating the face areas sq1, sq2, and sq3 in the image in the face area map 306 of the control area 300.

  Then, when the picture conversion processing unit 302 performs picture conversion processing on each pixel of the image data by the picture conversion in steps SC104, SC105, SC106, and SC113 described above, the picture conversion processing unit 302 is based on the face area map as shown in FIG. Then, set the conversion strength to a low value for the face area, set the conversion strength to a high level for the background area excluding the face area, and perform painting conversion more finely than the background area for the face area. .

  In the painting conversion process, as will be described later, a number of different effect processes are executed depending on the type of painting tone (see FIG. 15). Therefore, the conversion strength is appropriately set to be weak or finely set for each effect process. It is something to do. As a result of comprehensively executing them, the transformation strength is set to be weak for the face area, the transformation strength is set to be strong for the background area excluding the face area, and the face area is compared to the background area. It will be a fine picture conversion. Therefore, the process for setting the conversion strength and the process for setting the fineness coexist.

  As a result, in the painting-like image after painting conversion, the difference between the face region and the original image is small, and the difference between the background region and the original image is large.

  Therefore, when a person's face is present in the original image, natural painting conversion can be performed without the face atmosphere being disturbed in the painting-like image after the painting conversion. Of course, this is merely an example, and the face regions sq1, sq2, and sq3 may not be subjected to a painting conversion process so as not to disturb the facial atmosphere.

  Here, the conversion intensity in the picture conversion process will be described in detail. The strength of the conversion intensity is basically the magnitude of the parameter described above. In other words, the strength of the conversion strength is the parameters P1 to Pm necessary for the effect processing exemplified above, elements (coefficients) for calculating the bit data for each RGB of each pixel, the color enhancement degree, the target pixel and the adjacent pixel The numerical value (coefficient) q when a predetermined calculation is performed between the pixel groups, and the shape (length, flatness, etc.) of the pixel group when expressing the brush stroke. That is, the larger the parameter, the greater the difference from the original image in the picture-like image.

  In general, image conversion is the mapping of an original image to another image. When mapping, a predetermined conversion is applied. At that time, if the conversion coefficient (parameter) is small, the difference between the original image and the converted image is small, and if the conversion coefficient is minimum, the original image and the converted image are not changed, and the same image is obtained. . If the conversion coefficient is large, the difference between the original image and the converted image becomes conspicuous.

For image conversion, the pixel value of the original image is A, the pixel value of the converted image is B, and the conversion algorithm is f.
B = f (A)
It can be expressed as.

  Here, f is a plurality of types of effect processing such as texture processing, HSV processing, Laplacian filter, and median filter. Further, f is a process of converting to an oil painting tone, for example, and is a processing of converting to a watercolor painting tone.

  FIG. 15A is a diagram conceptually showing the processing content of the picture conversion as a general theory. As shown in the figure, the conversion algorithm actually includes individual algorithms of a plurality of types of effect processes 1 to N.

  FIG. 11B is a conceptual diagram corresponding to FIG. 11A when the target image tone is an image tone. As shown in the figure, the conversion algorithm includes algorithms of specific types of effect processing 1, 7, 9,... M according to the target image tone.

On the other hand, conversion of an image that incorporates elements of conversion strength
B = f (A, I)
It can be expressed as. I is intensity.

  For example, photo retouching software or the like generally used in a personal computer can perform various image processing with adjustable intensity, and the intensity adjusted by such image processing corresponds to the value I.

  In addition, the conversion algorithm f is not limited to the process of maintaining the position of one pixel (x, y), but includes a process of moving the position of the pixel or moving in units of groups of a plurality of pixels. For example, a distorted image can be obtained by moving the pixel (x1, y1) to (x3, y4) or moving the surrounding pixels together. In this case, the greater the moving distance, the stronger the conversion intensity. Further, the conversion algorithm f includes various blurring processes. For example, in the blurring process in which the average value of the peripheral pixels is set for the pixel of interest, the conversion intensity increases as the number of peripheral pixels increases.

  Here, in the picture conversion in steps SC104, SC105, SC106, and SC113 described above, different conversion intensities are set for the face area shown in the face area map and the background area excluding the face area. In other words, in the picture conversion, by performing the process of applying the conversion intensity I set in the area including the target pixel to the target pixel to be processed, the difference between the face image and the original image is small. The background area is converted into a painting-like image having a large difference from the original image.

  FIG. 15 (c) is a diagram corresponding to FIG. 15 (b), conceptually showing the processing content of the picture conversion in which the conversion intensity I set in the region including the target pixel is applied to the target pixel. As shown in the figure, at the time of painting conversion, the conversion intensity I corresponding to the area shown in the face area map is reflected in each of a plurality of types of effect processing 1, 7, 9,. Processing is performed on the pixel of interest. As a result, the original image is subjected to painting conversion having different conversion strengths in the face area and the background area excluding the face area.

  In short, in the above-described picture conversion in steps SC104, SC105, SC106, and SC113, the process of B = f (A, I) is performed on all the pixels of the image data. The value of I is changed depending on which of the background areas it belongs to. Note that there is an effect process that does not reflect the conversion intensity I depending on the type of image tone to be converted.

  In the above picture conversion, for example, the conversion intensity for each region indicated by the importance map 306 is an α that constitutes an α map known in the image processing field (see Japanese Patent No. 4151234, Japanese Patent No. 4797039, etc.). The converted image (painting-like image) and the original image once converted into a picture by the conversion algorithm according to the painting tone, reflecting the value (transmission information of each pixel different from the data R, G, B of the color expression) It is also possible to perform a process of α mixing (alpha blending).

  FIG. 15 (d) is a diagram corresponding to FIG. 15 (c), conceptually showing the processing content of the picture conversion by α mixing.

In the picture conversion by α mixture, if the original pixel value is A, the converted pixel value B, and each pixel value of the α map is α (0.0 to 1.0),
B = α × A + (1.0−α) × f (A)
It can be expressed as.

  Therefore, for example, when the converted image is overlaid and mixed on the original image, if the α value of the pixel in the face area with low conversion intensity is increased and the α value of the pixel in the background area with high conversion intensity is decreased, In the face area (sq1, sq2, sq3 in FIG. 14B), the degree to which the original image appears through the converted image can be increased. That is, in the finally obtained picture conversion image, the difference between the face region and the original image can be reduced, and the difference between the background region and the original image can be increased.

  FIG. 16 is a further subdivision of the contour region (boundary region) of the face region sq. For example, if the conversion strength is changed between the inside and outside of the outline of the face region sq, there is a possibility that a step in which a difference in atmosphere is manifested in a picture-converted image may be formed. Therefore, an elliptical area el similar to that illustrated in FIG. 16 is set outside the face area sq, and a slightly larger elliptical area el5 surrounding the area el is set outside the area el. Then, the relationship of the conversion intensity corresponding to each region sq, el, el5 may be set as sq> el> el5. The same applies to the case where the face area sq is subjected to finer picture conversion than the background area. By doing so, it is possible to transform the picture of the contour portion of the face step by step with a natural feeling.

  In the image service site 10 of the present embodiment, downloading is performed as shown in FIG. Here, membership registration is required for downloading.

  FIG. 17 is a flowchart showing processing related to downloading of works in the server 11. 17 is performed by the CPU 20 of the server 11, the evaluation control unit 310, and the member management unit 312.

  In the server 11, when a work to be downloaded is designated by the member (step SC 201), the user is a paying member (here, a normal paying member and a premium member) by the member management unit 312, or It is determined whether the member is a free member (step SC202). If the member is a paying member, the process immediately proceeds to step SC207 described later.

  On the other hand, in the case of a free member, the point corresponding to the evaluation of the work is read from the attribute information 206 of the corresponding work (step SC203), and the held point is read from the attribute information of the member who is going to download (step SC203). SC204).

  Next, the payment point is calculated from the difference between the point (equivalent to the price) of the work and the point held by the member (step SC205), and if it is satisfied, the process proceeds to step SC207, but is insufficient. Since the work cannot be downloaded, the process returns to step SC201 to allow the user to select another work.

  In the server 11, the CPU 20 reads the work designated by the user from the work buffer area 108 of another user who is the creator of the work (step SC 207), and the evaluation control unit 310 reads the work author and the work. Each point is added to (step SC208). In other words, as members (free members, regular paid members, premium members) download more of their work, the evaluation of the work increases, and points are also added to the point area of the attribute information of the user ID of the member who is the author As a result, the number of points owned by members is increased.

  Thereafter, in the server 11, the CPU 20 performs a town load process for storing the work read in step SC207 in the download work buffer 110 of the user who requested the download (step SC209).

  Furthermore, since the image service site 10 has an SNS function, a comment on another member's work can be written, a reply to it can be written, a group of members with similar preferences can be created, and a fan of a specific author You can create a group. Since such a mechanism is already implemented in an existing SNS, it will not be described in detail, but the member management unit 312 realizes the SNS mechanism together with the member management mechanism.

  According to the present embodiment described above, it is possible to suitably perform image conversion processing for converting a photographic image in which a person is photographed into a painting-like image. In particular, by changing the conversion intensity between the face part of the person and the part other than the face, or changing the fineness, the overall unnaturalness in the painting-like image is eliminated, and the face of the person looks natural. Can transform paintings.

  In addition, the structure of each part demonstrated by this embodiment can be suitably changed and changed.

  For example, an area corresponding to a person's face may be cut out from the image data 208, and the area corresponding to the face and other areas may be separately transformed and then combined.

As mentioned above, although embodiment of this invention and its modification were demonstrated, as long as these are in the range with which the effect of this invention is obtained, it can change suitably, and embodiment after change is also in a claim. It is included in the scope of the invention described and equivalent invention. The invention described in the claims of the present application will be added below.
(Appendix)
[Claim 1]
In an image processing apparatus connected to an external terminal via a network, receiving means for receiving original image data uploaded from the terminal, and converting the original image data into converted image image data of a predetermined image tone A tone conversion means, a transmission means for transmitting converted tone image data converted to a predetermined tone by the tone conversion means to the terminal, a face detection means for detecting a face from the original image data, and Area setting means for setting a predetermined area corresponding to the face detected by the face detection means for the original image data, and the image tone conversion means converts the original image data into the predetermined image tone. In doing so, a first conversion process is performed on the image data of the predetermined area set by the area setting means, The image data, the image processing apparatus characterized by comprising a conversion adjusting means the second conversion process is performed.
[Claim 2]
In an image processing apparatus connected to an external terminal via a network, receiving means for receiving original image data uploaded from the terminal, and converting the original image data into converted image image data of a predetermined image tone Image conversion means, selection means for selecting the predetermined image adjustment type, and converted image adjustment image data converted into the image type of the type selected by the selection means by the image adjustment conversion means is transmitted to the terminal. A transmission means for detecting a face from the original image data, and an area setting means for setting a predetermined area corresponding to the face detected by the face detection means for the original image data. The image tone conversion unit converts the original image data into the type of image tone selected by the selection unit by the area setting unit. Image processing comprising a conversion adjustment unit that performs a first conversion process on image data in a predetermined area that has been set, and performs a second conversion process on image data in an area other than the predetermined area apparatus.
[Claim 3]
3. The image processing apparatus according to claim 1, wherein the first conversion process and the second conversion process performed by the conversion adjustment unit are different from each other in conversion intensity of image tone conversion for the original image data.
[Claim 4]
3. The image processing apparatus according to claim 1, wherein the first conversion process and the second conversion process are different from each other in fineness of image tone conversion.
[Claim 5]
3. The conversion process according to claim 1, wherein the first conversion process is a conversion process in which a difference between the original image data and the converted image-tone image data is smaller than that of the second conversion process. 4. Image processing device.
[Claim 6]
The image processing apparatus according to claim 1, wherein the predetermined area set by the area setting unit is a rectangular or elliptical area including the face.
[Claim 7]
The image processing apparatus according to claim 6, wherein the predetermined area set by the area setting unit includes a face area including the face and a boundary area surrounding the first face area.
[Claim 8]
8. The conversion adjustment unit performs a third conversion process different from the first conversion process and the second conversion process on the image data of the boundary region during the conversion process. Image processing apparatus.
[Claim 9]
The image processing apparatus according to claim 8, wherein the first conversion process, the second conversion process, and the third conversion process performed by the conversion adjusting unit are different in conversion strength of image tone conversion.
[Claim 10]
3. The image processing apparatus according to claim 1, wherein the tone conversion processing by the tone conversion unit converts the original image data into painting-like image data representing a painting-like painting tone.
[Claim 11]
The second conversion processing by the conversion adjusting unit converts the original image data into painting-like image data representing a painting-like image with a stronger conversion intensity than the first conversion processing. Item 15. The image processing apparatus according to Item 10.
[Claim 12]
The image processing apparatus according to claim 1, wherein the face detection unit detects a human face from the original image data.
[Claim 13]
3. The image processing apparatus according to claim 1, wherein the transmitting unit further transmits the converted image tone image data converted into a predetermined image tone by the image tone converting unit to the printing unit.
[Claim 14]
A step of receiving original image data uploaded from an external terminal via a network; a step of detecting a face from the received original image data; and converting the original image data into a converted image image data of a predetermined image tone. At the time of conversion, a predetermined area corresponding to the detected face is set, a first conversion process is performed on the image data of the predetermined area, and a first image is applied to image data of an area other than the predetermined area. A step of performing a conversion adjustment process for performing a second conversion process different from the tone conversion to convert the converted image tone image data of a predetermined tone, and a step of transmitting the converted tone image data to the terminal An image processing method.
[Claim 15]
15. The image processing apparatus method according to claim 14, wherein the first conversion process and the second conversion process have different conversion intensities of tone conversion for the original image data.
[Claim 16]
The step of converting the original image data into converted image-tone image data having a predetermined image tone is a step of converting the original image data into image-like image data representing an image-like image tone. Item 15. The image processing method according to Item 15.
[Claim 17]
A process of receiving original image data uploaded from the terminal, a process of detecting a face from the received original image data, and a process of detecting a face from the received original image data to a computer included in a server connected to an external terminal via a network. On the other hand, processing for setting a predetermined area corresponding to the detected face, predetermined image tone conversion on the image data in the predetermined area, and image data in an area other than the predetermined area are included in the predetermined image tone. A process of performing conversion with a conversion intensity stronger than the conversion intensity for the image data of the predetermined area, and image tone conversion with different conversion intensity for the original image data in the predetermined area and an area other than the predetermined area. A program for executing the process of transmitting the converted image-tone image data to the terminal.
[Claim 18]
A process of receiving original image data uploaded from the terminal, a process of detecting a face from the received original image data, and a process of detecting a face from the received original image data to a computer included in a server connected to an external terminal via a network. In a process of setting a corresponding predetermined area, a process of converting the original image data into painting-like image data representing a painting-like image tone, and a process of converting the original image data into the painting-like image data, A first conversion is performed on the image data in the predetermined area, and a second conversion process is performed on the image data in an area other than the predetermined area, and the first conversion and the second conversion are performed. And a program for transmitting the picture-like image data to the terminal.
[Claim 19]
A face is detected from the original image data, a predetermined area corresponding to the detected face is set for the original image data, and a first conversion process is performed on the image data of the predetermined area for the original image data; The original image data is converted into a converted image with a predetermined image tone by performing a conversion adjustment process for performing a second conversion process different from the first image conversion on the image data in an area other than the predetermined area. Processing for transmitting the original image data to the server to a computer included in a terminal connected via a network to a server that converts the data; and processing for designating a type of image tone to be converted to the server Receiving from the server the converted image tone image data obtained by converting the original image data into the specified type of image tone; A program characterized by executing the processing of displaying the converted image tone image data received.
[Claim 20]
In an image processing system including a terminal and a server connected via a network, the server includes receiving means for receiving original image data uploaded from the terminal, and an image tone specified by the terminal. A tone conversion means for converting the converted image tone image data to the terminal, a transmission means for transmitting the converted tone image data converted to a predetermined tone by the image tone conversion means, and a face from the original image data. And a face setting means for setting a predetermined area corresponding to the face detected by the face detection means for the original image data, and the image tone conversion means includes the original image data. When converting the data into the predetermined image tone, the image data of the predetermined area set by the area setting means A conversion adjustment unit that performs a second conversion process on image data in a region other than the predetermined region, and the terminal includes a unit that acquires original image data, and the original image data. A transmission means for transmitting to the server, an image tone designating means for designating the type of image tone to be converted to the server, and the original image data of the type designated by the image tone designating means from the server. An image processing system comprising: receiving means for receiving converted image-tone image data converted into image tone; and display means for displaying converted image-tone image data received by the receiving means.

1 Terminal 10 Image Service Site 20 CPU
30 display buffer 100 member area 102 user ID
104 Attribute information 200 Common area 202 Work area 204 Image ID
206 Attribute Information 208 Image Data 300 Control Area 302 Painting Conversion Processing Unit 304 Parameter Table 306 Face Area Map 308 Display Control Unit 314 Face Detection Processing Unit 310 Evaluation Control Unit 500 Internet

Claims (20)

In an image processing apparatus connected to an external terminal via a network,
Receiving means for receiving original image data uploaded from the terminal;
Image tone conversion means for converting the original image data into converted image image data of a predetermined image tone;
Transmitting means for transmitting the converted image-tone image data converted into a predetermined image tone by the image-tone conversion means to the terminal;
Face detection means for detecting a face from the original image data;
An area setting unit that sets a predetermined area corresponding to the face detected by the face detection unit with respect to the original image data;
When converting the original image data into the predetermined image tone, the image tone conversion unit performs a first conversion process on the image data of the predetermined region set by the region setting unit, and converts the original image data to a region other than the predetermined region. An image processing apparatus comprising conversion adjustment means for performing a second conversion process on image data of a region. In an image processing apparatus connected to an external terminal via a network,
Receiving means for receiving original image data uploaded from the terminal;
Image tone conversion means for converting the original image data into converted image image data of a predetermined image tone;
Selecting means for selecting the predetermined image type;
Transmitting means for transmitting the converted image-tone image data converted into the type of image tone selected by the selection means by the image-tone converting means to the terminal;
Face detection means for detecting a face from the original image data;
An area setting unit that sets a predetermined area corresponding to the face detected by the face detection unit with respect to the original image data;
The image tone conversion unit performs a first conversion process on the image data of the predetermined area set by the area setting unit when converting the original image data into the type of image tone selected by the selection unit; An image processing apparatus comprising: a conversion adjustment unit that performs a second conversion process on image data in an area other than the predetermined area.   3. The image processing apparatus according to claim 1, wherein the first conversion process and the second conversion process performed by the conversion adjustment unit are different from each other in conversion intensity of image tone conversion for the original image data.   3. The image processing apparatus according to claim 1, wherein the first conversion process and the second conversion process are different from each other in fineness of image tone conversion.   3. The conversion process according to claim 1, wherein the first conversion process is a conversion process in which a difference between the original image data and the converted image-tone image data is smaller than that of the second conversion process. 4. Image processing device.   The image processing apparatus according to claim 1, wherein the predetermined area set by the area setting unit is a rectangular or elliptical area including the face.   The image processing apparatus according to claim 6, wherein the predetermined area set by the area setting unit includes a face area including the face and a boundary area surrounding the first face area.   8. The conversion adjustment unit performs a third conversion process different from the first conversion process and the second conversion process on the image data of the boundary region during the conversion process. Image processing apparatus.   The image processing apparatus according to claim 8, wherein the first conversion process, the second conversion process, and the third conversion process performed by the conversion adjusting unit are different in conversion strength of image tone conversion.   3. The image processing apparatus according to claim 1, wherein the tone conversion processing by the tone conversion unit converts the original image data into painting-like image data representing a painting-like painting tone.   The second conversion processing by the conversion adjusting unit converts the original image data into painting-like image data representing a painting-like image with a stronger conversion intensity than the first conversion processing. Item 15. The image processing apparatus according to Item 10.   The image processing apparatus according to claim 1, wherein the face detection unit detects a human face from the original image data.   3. The image processing apparatus according to claim 1, wherein the transmitting unit further transmits the converted image tone image data converted into a predetermined image tone by the image tone converting unit to the printing unit. Receiving original image data uploaded from an external terminal via a network;
Detecting a face from the received original image data;
When the original image data is converted into converted image data of a predetermined image tone, a predetermined area corresponding to the detected face is set,
The image data of the predetermined area is subjected to a first conversion process, and the image data of the area other than the predetermined area is subjected to a conversion adjustment process for performing a second conversion process different from the first image tone conversion. A step of converting the image into a converted image data of a predetermined image tone;
Transmitting the converted image-tone image data to the terminal.   15. The image processing apparatus method according to claim 14, wherein the first conversion process and the second conversion process have different conversion intensities of tone conversion for the original image data.   The step of converting the original image data into converted image-tone image data having a predetermined image tone is a step of converting the original image data into image-like image data representing an image-like image tone. Item 15. The image processing method according to Item 15. To a computer that has a server connected to an external terminal via a network,
Processing to receive original image data uploaded from the terminal;
Processing to detect the face from the received original image data;
A process of setting a predetermined area corresponding to the detected face for the original image data;
A predetermined tone conversion is performed on the image data of the predetermined region, and the image data of the region other than the predetermined region is subjected to a conversion strength stronger than the conversion strength for the image data of the predetermined region. With the process
A process of transmitting, to the terminal, converted image-tone image data obtained by performing image-tone conversion at different conversion intensities for the original image data in the predetermined region and a region other than the predetermined region. Program. To a computer that has a server connected to an external terminal via a network,
Processing to receive original image data uploaded from the terminal;
Processing to detect the face from the received original image data;
A process of setting a predetermined area corresponding to the detected face;
A process of converting the original image data into painting-like image data representing a painting-like painting tone;
In the process of converting the original image data into the painting-like image data, a first conversion is performed on the image data in the predetermined area, and a second conversion is performed on the image data in an area other than the predetermined area. Processing,
A program for executing the first conversion and the process of transmitting the painting-like image data subjected to the second conversion to the terminal. A face is detected from the original image data, a predetermined area corresponding to the detected face is set for the original image data, and a first conversion process is performed on the image data of the predetermined area for the original image data; The original image data is converted into a converted image with a predetermined image tone by performing a conversion adjustment process for performing a second conversion process different from the first image conversion on the image data in an area other than the predetermined area. To the computer that the terminal connected via the network to the server that converts to data,
Processing to send the original image data to the server;
Processing for designating the type of image tone to be converted to the server;
A process of receiving, from the server, converted original image data obtained by converting the original image data into the specified type of original image;
And a program for displaying the received converted image data. In an image processing system including a terminal and a server connected via a network,
The server
Receiving means for receiving original image data uploaded from the terminal;
Tone conversion means for converting the original image data into converted tone image data of the tone specified by the terminal;
Transmitting means for transmitting the converted image-tone image data converted into a predetermined image tone by the image-tone conversion means to the terminal;
Face detection means for detecting a face from the original image data;
An area setting unit that sets a predetermined area corresponding to the face detected by the face detection unit with respect to the original image data;
When converting the original image data into the predetermined image tone, the image tone conversion unit performs a first conversion process on the image data of the predetermined region set by the region setting unit, and converts the original image data to a region other than the predetermined region. The image data of the area includes a conversion adjustment unit that performs a second conversion process,
The terminal
Means for obtaining original image data;
Transmitting means for transmitting the original image data to the server;
Tone design means for designating the type of tones to be converted for the server;
Receiving means for receiving, from the server, converted image-tone image data obtained by converting the original image data into a type of image tone designated by the image-tone designating means;
Display means for displaying the converted image-tone image data received by the receiving means;
An image processing system comprising:

Images