JP3972914B2 - Image impression evaluation apparatus, image impression evaluation method, and image impression evaluation program - Google Patents

Description

  The present invention relates to an image impression evaluation apparatus, an image impression evaluation method, and an image impression evaluation program that present information related to an impression given to a human by the image based on visual information acquired from the image.

  With the recent increase in information processing speed and capacity, a large number of colored images are used in presentation materials and various websites. In these images, the visual impression given to humans varies greatly depending on the selection, arrangement, area, and area ratio of colors used in the images.

  However, much of the actual image creation is left to a general user. A general user who is unfamiliar with image creation often does not know how to color and color an image to obtain his intended atmosphere, aesthetics and visibility. In addition, a means for objectively evaluating the impression that the created image gives to the user is also required for an image creation expert.

  In order to solve this problem, research on image processing and image evaluation based on human sensitivity has been actively conducted, and in particular, sensitivity evaluation means for evaluating human sensitivity, and the results and image characteristics. Many sensuous image creation support means have been proposed which are linked to image analysis means for analysis.

  Japanese Patent Application Laid-Open Nos. 7-306935 and 8-249441 disclose an interactive color arrangement support method and a color arrangement support apparatus using the same. In this color arrangement support method, when the user edits image data, the appropriateness of the color arrangement such as the background of the image, characters or graphs is presented as a specific numerical value, or a color suitable for the color arrangement is presented as a candidate.

JP-A-7-306935 JP-A-8-249441

  However, in the above-described prior art, the feature extraction when obtaining the appropriate color arrangement of the image is not appropriate or the correspondence between the human sensibility and the image feature is often shifted. There was a problem that the atmosphere, aesthetics and visibility along the line could not be evaluated accurately.

  In addition, since the operation of the apparatus is interactive, an appropriate evaluation result cannot be presented when an instruction from the user is not appropriate. In particular, a user who has little experience in image creation often needs assistance, but often cannot give appropriate instructions, and has a problem in use.

  The present invention has been made in view of the above-described problems of the prior art, and an object thereof is to provide an image impression evaluation apparatus, an image impression evaluation method, and an image impression evaluation program capable of accurately evaluating an image impression based on human sensitivity.

  The present invention for solving the above-described problems is an image impression evaluation apparatus that presents information related to an impression given to a human by the image based on visual information acquired from the image, and at least from the image to be evaluated A feature amount acquisition means for acquiring one feature amount; and means for displaying the acquired feature amount on an output screen as information about an impression given to a human by the image to be evaluated, the area of the output screen Output means for displaying the information about the acquired feature amount in the divided screen region corresponding to the condition satisfied by the acquired feature amount, and assigning a condition to each of the divided screen regions It is characterized by providing.

  Further, the present invention for solving the above-described problem is an image impression evaluation apparatus that presents information related to an impression given to a human by the image based on visual information acquired from the image, and is an image to be evaluated Region dividing means for dividing the image area into a plurality of image areas, feature quantity obtaining means for obtaining at least one feature quantity from images included in each of the image areas, and the obtained feature quantity to be the evaluation target Means for displaying on the output screen as information relating to the impression that the image gives to a person, dividing the area of the output screen into a plurality of divided screen areas, assigning conditions to each of the divided screen areas, and obtaining the obtained feature amount Output means for displaying information related to the acquired feature amount in the divided screen area corresponding to the condition satisfied by.

  Further, the present invention for solving the above-described problem is an image impression evaluation apparatus that presents information related to an impression given to a human by the image based on visual information acquired from the image, and includes at least one image related Storage means for storing a database that associates a condition for a visual feature amount with expression information representing an impression felt by a person who sees the image, and a feature amount for acquiring at least one feature amount from the image to be evaluated An acquisition means, expression information extraction means for extracting the expression information associated with the condition that the acquired feature quantity satisfies, and the impression that the image to be evaluated gives to the human the extracted expression information A means for displaying information on an output screen, wherein the output screen area is divided into a plurality of divided screen areas, and the condition is set for each of the divided screen areas; Ri hit, and an outputting means for displaying the extracted expression information in the divisional area corresponding to the condition that the obtained characteristic amount satisfies.

  Another aspect of the present invention for solving the above-described problem is an image impression evaluation apparatus that presents information related to an impression given to a human by the image based on visual information acquired from the image. A storage unit that holds a database that associates at least one condition for at least one visual feature with respect to expression information representing an impression felt by a person who sees the image, and divides the image to be evaluated into a plurality of image regions Region dividing means for performing, at least one feature quantity obtaining means for obtaining at least one feature quantity from an image included in each of the image areas, and the expression associated with the condition that the obtained feature quantity satisfies from the database An expression information extracting means for extracting information, and the extracted expression information is output as information relating to an impression given to a human by the image to be evaluated. The display area is divided into a plurality of divided screen areas, the condition is assigned to each of the divided screen areas, and the divided area corresponding to the condition satisfied by the acquired feature amount And an output means for displaying the extracted expression information.

  In the image impression evaluation apparatus, it is preferable that the feature amount is at least one of feature amounts relating to lightness, saturation, hue, average color, area, or position.

  In the image impression evaluation apparatus, it is preferable that the feature amount includes a feature amount relating to a visual feature difference between the image regions.

  That is, in the image impression evaluation apparatus, the feature amount is a feature amount related to a color difference between the entire image and the image region, a color difference between the background and the image region, or a color difference between the image region and an image region adjacent to the image region. It is suitable that it is at least one of these.

  In the image impression evaluation apparatus, the output unit is a unit that displays the acquired feature amount on an output screen as information on an impression given to a human by the image to be evaluated, and an area of the output screen Is divided into a plurality of divided screen areas, a condition for the feature quantity is assigned to the divided screen area, and information on the acquired feature quantity is assigned to the divided screen area corresponding to the condition that the acquired feature quantity satisfies. It is preferable to include means for displaying.

  Here, in the image impression evaluation device, the feature amount includes an average color and an area, and the information on the acquired feature amount is proportional to the area of the image region from which the acquired feature amount is acquired. It is preferable that the image information display the average color of the image area in the area of the output screen.

  In the image impression evaluation apparatus, the feature amount includes an average color and an area, and the output unit divides the output screen area into a plurality of divided screen areas, and assigns different colors to the divided screen areas. Preferably, each image area includes means for displaying the average color of the image area in an area proportional to the area of the image area in the divided screen area corresponding to the average color of the image area. .

  The present invention for solving the above problems is an image impression evaluation method for presenting information related to an impression given to a human by the image based on visual information acquired from the image, and at least from the image to be evaluated A feature amount acquisition step of acquiring one feature amount, and a step of displaying the acquired feature amount on the output screen as information related to an impression given to a human by the image to be evaluated, the region of the output screen An output step of displaying the acquired feature amount in the divided region corresponding to the condition satisfied by the acquired feature amount. It is characterized by performing processing.

  Further, the present invention for solving the above-described problem is an image impression evaluation method for presenting information related to an impression given to a human by the image based on visual information acquired from the image, and the image to be evaluated A plurality of image regions, a feature amount acquisition step of acquiring at least one feature amount from images included in each of the image regions, and the acquired feature amount as the evaluation target The image is displayed on the output screen as information relating to an impression given to a human, the output screen area is divided into a plurality of divided screen areas, a condition is assigned to each of the divided screen areas, and the acquired feature amount And a process including an output step of displaying the acquired feature amount in the divided region corresponding to the condition that is satisfied.

  The present invention for solving the above-described problem is an image impression evaluation method for presenting information related to an impression given to a human by the image based on visual information acquired from the image, wherein at least one visual related to the image A feature amount for acquiring at least one feature amount from an image to be evaluated using a storage unit that holds a database that associates a condition for a particular feature amount with expression information representing an impression felt by a human who has viewed the image An acquisition step, an expression information extraction step for extracting the expression information associated with the condition that the acquired feature quantity satisfies, and an impression that the image to be evaluated gives to the human the extracted expression information A step of displaying information on an output screen, dividing the area of the output screen into a plurality of divided screen areas, and setting the condition for each of the divided screen areas. Ri hit, and performs the processing and an output step of displaying the extracted expression information in the divided area corresponding to the acquired feature value satisfies the condition.

  Another aspect of the present invention for solving the above problem is an image impression evaluation method for presenting information on an impression given to a human by the image based on visual information acquired from the image. An image to be evaluated is stored in a plurality of image regions by using a storage unit that holds a database that associates at least one condition for at least one visual feature amount and expression information representing an impression felt by a person who viewed the image. A region dividing step for dividing the image region, a feature amount acquiring step for acquiring at least one feature amount from an image included in each of the image regions, and the condition that the acquired feature amount satisfies from the database. The expression information extraction step for extracting the expression information, and the extracted expression information as information related to the impression given to the human by the image to be evaluated The output screen area is divided into a plurality of divided screen areas, the condition is assigned to each of the divided screen areas, and the condition corresponding to the condition that the acquired feature amount satisfies A process including an output step of displaying the extracted expression information in the divided area is performed.

  In the image impression evaluation method, it is preferable that the feature amount is at least one of feature amounts relating to lightness, saturation, hue, average color, area, or position.

  In the image impression evaluation method, it is preferable that the feature amount includes a feature amount relating to a visual feature difference between the image regions.

  That is, in the image impression evaluation method, the feature amount is a feature amount related to a color difference between the entire image and the image region, a color difference between the background and the image region, or a color difference between the image region and the image region adjacent to the image region. It is suitable that it is at least one of these.

  In the image impression evaluation method, the output step is a step of displaying the acquired feature amount on an output screen as information on an impression given to a human by the image to be evaluated, and an area of the output screen Is divided into a plurality of divided screen areas, a condition for the feature quantity is assigned to the divided screen area, and information on the acquired feature quantity is assigned to the divided screen area corresponding to the condition that the acquired feature quantity satisfies. It is preferable to include the step of displaying.

  Here, in the image impression evaluation method, the feature amount includes an average color and an area, and the information on the acquired feature amount is proportional to the area of the image region from which the acquired feature amount is acquired. It is preferable that the image information display the average color of the image area in the area of the output screen.

  In the image impression evaluation method, the feature amount includes an average color and an area, and the output step divides the output screen area into a plurality of divided screen areas, and assigns different colors to the divided screen areas. Preferably, the method includes a step of displaying the average color of the image area in an area proportional to the area of the image area in the divided screen area corresponding to the average color of the image area for each image area. .

  The present invention for solving the above-described problems is an image impression evaluation program for presenting information related to an impression given to a human by the image based on visual information acquired from the image, and is an evaluation target for the computer. A feature amount acquisition step of acquiring at least one feature amount from an image, and a step of displaying the acquired feature amount on an output screen as information on an impression given to a human by the image to be evaluated, the output An output step of dividing a screen area as a plurality of divided screen areas, assigning a condition to each of the divided screen areas, and displaying the acquired feature amount in the divided region corresponding to a condition satisfied by the acquired feature amount It is characterized by executing a process including:

  In addition, the present invention for solving the above-described problem is an image impression evaluation program that presents information related to an impression given to a human by the image based on visual information acquired from the image, and includes at least one image related image. At least one feature amount from an image to be evaluated is stored in a computer having a storage unit that holds a database that associates a condition for a visual feature amount with expression information representing an impression felt by a person who views the image. A feature amount acquisition step to acquire, a condition that the acquired feature amount satisfies, the expression information extraction step to extract the expression information associated with the condition, and the image to be evaluated is a human Displaying on the output screen as information on the impression given to the output screen, dividing the output screen area into a plurality of divided screen areas, The condition is assigned to each split screen area, and an output step of displaying the extracted expression information in the divided area corresponding to the condition satisfied by the acquired feature value is executed. .

  According to the present invention, a plurality of visual feature amounts are acquired from an image to be evaluated, and information on the impression that the image gives to a person is presented in a form that is easy to grasp based on the combination of the feature amounts. Can do. Further, the user can obtain the above information only by inputting image data of an image to be evaluated. Therefore, even a user with little experience in image creation or the like can accurately grasp information related to the impression of the image.

  Embodiments of the present invention will be described below in detail with reference to the drawings. As shown in FIG. 1, an impression evaluation apparatus according to an embodiment of the present invention basically includes a control unit 10, an internal storage unit 12, a large-capacity storage unit 14, an output unit 16, a standard input unit 18, and an image input unit 20. Composed. The control unit 10, the internal storage unit 12, the large-capacity storage unit 14, the output unit 16, the standard input unit 18, and the image input unit 20 are connected via a bus 24 so that information (data) can be transmitted.

  It is preferable that the impression evaluation apparatus further includes an interface unit 22. The interface unit 22 is connected to other components via a bus 24 so that information (data) can be transmitted. The interface unit 22 can be used for reading image data such as a web page from a server external to the impression evaluation apparatus via the network 26.

  The control unit 10 executes an image impression evaluation program held in the internal storage unit 12 and appropriately reads image data stored in the large-capacity storage unit 14 or image data via the network 26, and the image data The impression of the image expressed by is evaluated. The result of impression evaluation is output to the output unit 16 or the internal storage unit 12. As the control unit 10, a CPU of a general computer can be used.

  The internal storage unit 12 stores and holds an impression evaluation program executed by the control unit 10, each parameter used for evaluation processing, an impression evaluation value that is a processing result, and the like. The data held in the internal storage unit 12 can be referred to as appropriate from the control unit 10 via the bus 24. As the internal storage unit 12, a general semiconductor memory, a hard disk device, a magneto-optical disk device, or the like can be appropriately selected and used.

  The large-capacity storage unit 14 stores and holds image data of an image (hereinafter referred to as an evaluated image) that is an object of impression evaluation in the control unit 10. Image data is held in various data formats such as a bitmap format, a jpeg format, a tiff format, and an HTML format. The image data held in the large-capacity storage unit 14 can be appropriately referred to from the control unit 10 via the bus 24. The large-capacity storage unit 14 can select and use a large-capacity storage device such as a general hard disk device or a magneto-optical disk device.

  The output unit 16 outputs the processing result output from the control unit 10 as information that can be confirmed by the user. It is also used as a user interface when the user inputs control commands and parameters necessary for impression evaluation processing. As the output unit 16, a display device, a printer, a touch panel, or the like can be appropriately selected and used.

  The standard input unit 18 is used by the user to input control commands and parameters for image evaluation. For example, it is used when a control command for instructing the control unit 10 to start executing an impression evaluation program held in the internal storage unit 12 is used. The standard input unit 18 can be used by appropriately selecting a keyboard, a mouse, a touch panel, or the like.

  The image input unit 20 inputs image data to be subjected to impression evaluation. The image data input from the image input unit 20 is stored and held in the mass storage unit 14 or the internal storage unit 12. As the image input unit 20, a general image input device such as a scanner, a digital camera, or a digital video can be appropriately selected and used.

  The impression evaluation apparatus according to the present embodiment can be basically configured by a general computer. Moreover, it is not limited to the said structure, It is suitable to add, delete, or change a component suitably.

<First Image Impression Evaluation Method>
Hereinafter, a method for processing impression evaluation of an image using the impression evaluation apparatus will be described with reference to the drawings. FIG. 2 shows a flowchart in the first image impression evaluation method.

  As shown in FIG. 2, the present impression evaluation method includes inputting an image to be evaluated (step S1), dividing an image area (step S2), a subroutine for obtaining physical features (step S3), and extracting an impression evaluation (step S4) and an evaluation result output (step S5), which are executed by sequentially performing each step. Specifically, each step is stored and held in the internal storage unit 12 as an impression evaluation program that can be executed by a computer, and the impression evaluation program is executed by the control unit 10.

  When the user inputs a control command for starting execution of the impression evaluation program from the standard input unit 18, the control unit 10 executes the impression evaluation program held in the internal storage unit 12. As a result, the process immediately proceeds to step S1.

  In step S <b> 1, image data of an image to be evaluated for impression is acquired using the image input unit 20. Alternatively, image data such as a web page may be acquired via the network 26. The image data is stored and held in the large-capacity storage unit 14 or the internal storage unit 12 and is appropriately read out by the control unit 10 for processing.

  In step S2, the image to be evaluated is divided into a plurality of image areas. The division into image regions can be performed using a general image retoucher method. At this time, the image to be evaluated is displayed using the output unit 16, and the user selects and divides an arbitrary area in the image using the standard input unit 18 while confirming the image.

  In addition, when the image to be evaluated is image data in the bitmap format, the image is automatically processed using an image processing method that applies an image region segmentation algorithm typified by clustering using a well-known K-average algorithm. It is also preferable to divide the area into two.

  The divided image areas are stored and held in the large-capacity storage unit 14 or the internal storage unit 12, respectively.

  For example, as shown in FIG. 3, when the image to be evaluated is an image captured from a web page, the image data includes a header part 30, a title part 31, a heading part 32, a link button part 33, and an image image part 34. The area is divided into a text part 35 and the like.

In step S3, a physical feature amount is calculated for each image region. Here, the physical feature amounts are the area of the image area, the width w and height h of the image area, the upper left positions x and y, the color average of the entire image area, the average value of the L ^* component, and the a ^* component. mean values of, b ^* average component, color difference of the entire image color means and the image area the overall color average ΔL ^* a ^* b ^*, color differences average color of the image area to be close to the image area Δ _n L ^* a ^* b ^* , a color average color difference Δ _b L ^* a ^* b ^* between the background and the image area, and image characteristics such as color dispersion in the image area and the number of the same color.

  Step S3 is processed as a subroutine as shown in FIG.

In step S31, the color space of the image data of each divided image region is converted from the RGB space to the L ^* a ^* b ^* space. In general, image data used in a computer is often expressed in an RGB color space, which is an uneven color space, and cannot be analyzed close to human senses. Therefore, by converting the RGB color space, which is a non-uniform color space, to the L ^* a ^* b ^* color space, which is a uniform color space, an image can be analyzed and evaluated as an impression closer to human sensitivity. Of course, if the image data is already expressed in the L ^* a ^* b ^* color space, no conversion is necessary.

  FIG. 5 shows an example in which the uniform color space is expressed as a general Munsell hue ring (different colors are expressed by different hatching in the drawing). Usually, the Munsell hue ring performs multi-color classification, but a part of them is shown in FIG. In the following, description will be made using a Munsell hue ring in which the color space is divided into 10 for both hue and brightness. Of course, it is preferable to use a color palette in which the color space is further subdivided.

  In step S32, the image data of each image area subjected to color space conversion is stored and held in the large capacity storage unit 14 or the internal storage unit 12.

  In step S33, the feature quantity of position, area, color average, color dispersion, and number of colors is extracted for each image region. Image data of each image area held in the large-capacity storage unit 14 or the internal storage unit 12 is sequentially selected, and each feature amount for each image area is obtained. At this time, an image area having the maximum area among all image areas is defined as a background area.

For example, the position is determined by obtaining the position x, y of the upper left pixel for each image region. The area is determined by extracting the width w and height h of each image region. The color average and color variance are determined by calculating the arithmetic mean and variance value for the L ^* component, a ^* component, and b ^* component of all pixels in each image area, respectively. The number of colors is determined by accumulating the number of colors in which all of the L ^* component, the a ^* component, and the b ^* component are different for all pixels in each image region.

  Similarly, the color average, color dispersion, and number of colors of the entire image and the background area can be obtained.

In step S34, the color difference between each image area, the entire image, and the background area is obtained. First, the difference ΔL _i ^* , Δa _i ^* and Δb _i ^* of each color component with respect to the entire image is obtained for each image region. Differences ΔL _i ^* , Δa _i ^*, and Δb _i ^* between the color components are expressed by Equation (1).

(Equation 1)
[Delta] L _i ^* = color average of the L ^* component of the image area i - color average of the entire image in the L ^* component .DELTA.a _i ^* = color average of a ^* component of the image area i - the entire image a ^* component of the color average [Delta] b _i ^* = color average of b ^* component of the image area i - where color average of the entire image b ^* components, i is the identification of the image area code ............. (1)

Similarly, differences ΔL _j ^* , Δa _j ^*, and Δb _j ^* of the respective color components with respect to the background area are obtained for each image area. Differences ΔL _j ^* , Δa _j ^*, and Δb _j ^* between the color components are expressed by Expression (2).

(Equation 2)
[Delta] L _j ^* = color average of the L ^* component of the image region j - color average of the L ^* component of the background area .DELTA.a _j ^* = color average of a ^* component of the image region j - color average of a ^* component of the background area [Delta] b _j ^* = B in the image area j ^* color average of the component-b in the background area ^* color average of the component where j is an identification code of the image area (2)

Color difference Δ _bj L ^* a ^* b of the color difference delta _i L ^* a ^* b ^* and the image area and the background area of each image area and the whole image ^* can be calculated using Equation (3).

(Equation 3)
Δ _i L ^* a ^* b ^* = {ΔL _i ^{* 2} + Δa _i ^{* 2} + Δb _i ^{* 2} } ^1/2
Δ _bi L ^* a ^* b ^* = {ΔL _j ^{* 2} + Δa _j ^{* 2} + Δb _j ^{* 2} } ^1/2
Here, i and j are image area identifiers (3).

In step S35, a color difference between each image area and an image area adjacent to the image area is obtained. When the image area i is adjacent to the image area j, the differences ΔL _ij ^* , Δa _ij ^*, and Δb _ij ^* of the respective color components are obtained using Equation (4).

(Equation 4)
[Delta] L _ij ^* = color average of the L ^* component of the image area i - color average of the L ^* component of the image region j .DELTA.a _ij ^* = color average of a ^* component of the image area i - of the a ^* component of the image region j color average [Delta] b _ij ^* = average color of the b ^* component of the image area i - image region j b ^* component of the color average ........................... (4)

The color difference Δ _ni L ^* a ^* b ^* between the image area i and the image area j can be obtained using Equation (5).

(Equation 5)
_{^{Δ ni L * a * b *}} = {ΔL ij * 2 + Δa ij * 2 + Δb ij * 2} 1/2 ··· (5)

If the image area is adjacent to a plurality of image areas, the difference ΔL _ij ^* , Δa _ij ^* and Δb _ij ^* of each color component with respect to all the adjacent image areas is obtained, and the color difference is obtained by performing an arithmetic average thereof. Is preferably obtained.

  FIG. 6 illustrates the result of obtaining each feature amount for each image region. These feature amounts are stored and held in the large-capacity storage unit 14 or the internal storage unit 12 in association with each image area. When the extraction of each feature amount is completed, the process proceeds to step S4 of the main routine.

  In step S4, an evaluation for the impression of the image is obtained based on each feature amount extracted in step S3. Specifically, an expression that compares the value of each feature quantity between image areas, selects the feature quantity of an image area that satisfies a predetermined condition, and expresses an impression of an image that has been stored in a database based on the value. Extract information. The expression information is preferably not only text information but also image information and audio information.

  The database is stored and held in the internal storage unit 12 or the mass storage unit 14. In the database, a condition relating to at least one feature quantity and an expression information relating to an impression given to a person by an image, that is, an impression felt by a person who sees the image are stored in association with each other.

In the present embodiment, description will be made using the database shown in FIG. 7 as an example. In this database, the color average (L ^* component, a ^* component, and b ^* component) of the background region, the feature amount relating to the color component of the image region (main region) having the largest color difference from the background region and a predetermined area, A condition relating to a feature amount relating to a color component of an image area (accent area) having an area that is equal to or smaller than a predetermined value and having the largest color difference from the background area is associated with text information relating to an image impression.

  However, the feature quantities that can be used to extract information related to the impression of the image are not limited to these, and the image area having the second largest area that has a color difference from the background area that is equal to or greater than a predetermined value. It is more preferable to associate expression information by combining more feature amounts, such as using feature amounts relating to color components.

For example, the L ^* component of the background region (image region having the largest area) is 3, the a ^* component is 0.3 and the b ^* component is 0.1, the L ^* component of the main region is 3, and the a ^* component is If the 0.3 and b ^* components are 0.1, the L ^* component of the accent region is 3, the a ^* component is 0.3 and the b ^* component is 0.1, the condition 1 is satisfied. , Text information “having a personality” is extracted. When the acquired feature amount matches other conditions, text information associated with the conditions can be extracted.

  Further, a multidimensional database in which more feature value values are combined may be used. In this way, by combining as many feature quantities as possible, the impression that the image gives to humans can be made more detailed. In particular, by using conditions that include differences in feature quantities between different image areas, such as color differences between image areas, expression information representing impressions received from places with strong contrast in the evaluated image is extracted. Is also possible.

  Further, as in the database shown in FIG. 8, a plurality of associations between conditions for feature quantities and expression information may be used. In this case, there are a plurality of conditions that the acquired feature value satisfies, and a plurality of text information associated with each of the conditions is extracted.

For example, in the database of FIG. 8, if the L ^* component of the background region (image region having the largest area) is 3, the a ^* component is 0.3, and the b ^* component is 0.1, the condition 1 is satisfied. Therefore, text information “has a personality” is extracted. At the same time, when the L ^* component is 55, the a ^* component is 0.3, and the b ^* component is 0.1 in the image region (main region) having a color difference from the background region that is equal to or larger than a predetermined value and the largest area, Since the condition 102 is met, text information “natural” is extracted. Further, when the L ^* component is 65, the a ^* component is 0.3, and the b ^* component is 0.15 in the image area (accent area) having the largest area and a color difference from the background area, Since the condition 202 is met, the text information “peaceful” is extracted.

  In step S <b> 5, the output unit 16 displays information about the acquired feature amount and the extracted expression information. The output is preferably performed in such a manner that information relating to the image is easily grasped by the user.

  For example, as shown in FIG. 9, an image to be evaluated 90, an image color information display unit 91 indicating the distribution of the area and average color of each image region included in the image to be evaluated, and expression information extracted based on the feature amount It is preferable to include a color image 92 to be shown and a display portion 93 to show an average color of main image areas.

  As shown in FIG. 10A, the image color information display unit 91 obtains, for each image area, a color on the color palette that most closely approximates the average color of each image area, and for each color in the color palette, the color The total area of the image areas having an average color approximate to is obtained, and an area proportional to the area is filled with the color of the color palette and displayed.

Specifically, as shown in FIG. 10B, a database in which the screen position of the image color information display unit 91 is associated with the condition of the color component range included in the color palette is stored in the internal storage unit 12 or the large capacity storage unit. 14, refer to the color components (L ^* component, a ^* component and b ^* component) and the area of the average color of each image area stored in the internal storage unit 12 or the large capacity storage unit 14. Thus, the total area of the image areas having an average color that matches the conditions of each color component range is obtained, and an area proportional to the total area is displayed in the color palette color at the screen position associated with the condition of the color component range. Display filled image information.

  The image color information display unit 91 allows the user to confirm at a glance the distribution of colors (average colors) included in the image to be evaluated.

  As shown in FIG. 11A, the color image 92 divides the area of the output screen into a plurality of divided screen areas 95, and assigns a condition for the feature amount included in the database in step 4 for each divided screen area 95 in advance. The expression information extracted from the condition is displayed in the divided screen area 95 to which the condition used when extracting the information related to the impression of the image in step 4 is assigned.

  Specifically, as shown in FIG. 11B, a database in which the position information of each divided screen area 95 and the condition for the feature amount included in the database shown in FIG. The information is stored in the storage unit 12 or the large-capacity storage unit 14, and the expression information is displayed at the screen position of the matching condition with reference to this database.

  At this time, when assigning a condition to the divided screen area 95, it is preferable to assign a condition closer to the impression that humans feel from the image to the divided screen areas 95 that are close to each other.

  In the example of the color image 92 in FIG. 11, a condition that gives a “warm” impression is assigned to the left side of the color image 92, and conversely, a condition that gives a “cold” impression is assigned to the right side of the color image 92. In addition, a condition that gives a “soft” impression is assigned to the upper side of the color image 92, and conversely, a condition that gives a “hard” impression is assigned to the lower side of the color image 92. However, the assignment is not limited to these, and the assignment may be changed according to information required by the user.

For example, by assigning a condition in which the a ^* component increases from the left side to the right side of the screen area and the b ^* component increases from the lower side to the upper side of the screen area, , It can be assigned to a divided screen area 95 that is closer. The same applies to other feature amounts.

  In this way, by assigning the conditions with a tendency, the tendency for the impression of the image to be evaluated can be known from the position and concentration of the information displayed on the color image 92.

  For example, when the acquired feature quantity matches the condition 1, condition 102, and condition 202 in FIG. 8 and text information “natural”, “natural”, and “peaceful” is extracted, as shown in FIG. In the divided image areas 96, 97, and 98 to which the condition 1, the condition 102, and the condition 202 of the color image 92 are assigned, “natural”, “natural”, and “peaceful” are displayed, respectively.

  Furthermore, it is preferable to simultaneously display information indicating feature amounts that match the conditions. For example, as shown in FIG. 12, a region 96 proportional to the area of the background region that meets the condition 1 is displayed by being painted with the average color of the background region. Similarly, a region 97 and a region 98 that are proportional to the area of each screen region that meets the conditions 102 and 202 are filled with the average color of the screen region and displayed.

  In this way, by simultaneously displaying the text information indicating the impression of the image and the information indicating the feature amount on the color image 92, the user can determine what feature amount the image impression was evaluated based on. It can be easily recognized in association with the feature amount.

  In addition, in step S4, when expression information is extracted using a condition composed of a combination of a plurality of feature amounts as shown in FIG. 7, the conditions to be assigned to each divided screen area 95 in FIG. It is preferable that the condition is a combination.

  In this case, the average color of the image area from which the combined feature amount is extracted may be displayed together. For example, as shown in FIG. 13, the expression information “has a personality” extracted under condition 1 in FIG. 7 and the average colors of the background area, main area, and accent area used for the extraction are simultaneously displayed on the color image 92. indicate.

  A display unit 93 indicating the average color of the main image area displays the average colors of the background area, the main area, and the accent area.

  In this way, by presenting the result of extracting the feature amount of the main image area of the image to be evaluated, the user can compare with the display of the color image 92 and what kind of feature value of each image area You can clearly see if an impression is given.

<Second Image Impression Evaluation Method>
The second image impression evaluation method will be described below. In the second image impression evaluation method, a color palette including a plurality of colors is prepared in advance, and a database in which expression information of image impressions is assigned to a combination of the colors included in the color palette is prepared and evaluated. A feature amount relating to the color is extracted from the image, and the expression information assigned to the color on the color palette corresponding to the feature amount is selected and displayed.

  Hereinafter, an image impression processing method using a color palette will be described with reference to the drawings. Similar to the first image impression evaluation method, as shown in FIG. 2, an input image to be evaluated (step S1), an image area division (step S2), and a subroutine for acquiring physical feature values (step S3). , Including impression evaluation extraction (step S4) and evaluation result output (step S5), and is executed by sequentially performing each step.

  In steps S1 and S2, processing is performed in the same manner as in the first image impression evaluation method, and a description thereof will be omitted.

  In step S3, a feature amount is calculated for each image area, and the feature amount relating to the color in the image region is associated with the color on the color palette. Step S3 is processed as a subroutine as shown in FIG.

In step S31, the color space of the image data of each image area is converted from the RGB space to the L ^* a ^* b ^* space. Since this process is the same as the first image impression evaluation method, description thereof is omitted.

  In step S32, the image data of each image area subjected to color space conversion is stored and held in the large capacity storage unit 14 or the internal storage unit 12.

  In step S37, the feature quantity of the position, area, color dispersion, and number of colors is extracted for each image area, and the color on the color palette that is closest to the color average feature quantity of each image area is further characterized. Calculate as a quantity.

  Since the calculation method of the feature amount regarding the position, area, color dispersion, and number of colors of each image region is the same as the first image impression evaluation method, description thereof is omitted.

  The feature amount of the color on the color palette is obtained by performing pattern matching based on the color average of each image area calculated in the same manner as the first image impression evaluation method. Find the color.

  In step S38, the base color, sub color, and accent color are calculated based on the color palette color obtained for each image area and the area of the image area. Here, the base color is a color used in the maximum area in the image to be evaluated. The sub color is a color in which the color difference from the base color is not less than a predetermined value and two colors used in a wider area are selected in order. The accent color is a color that is selected from two colors in order from the one in which the used area is equal to or less than a predetermined ratio to the area of the image to be evaluated and the color difference from the base color is larger. FIG. 15 illustrates one selected base color, two sub colors, and two accent colors. However, the color selection conditions are not limited to these, and any color that clearly shows the characteristics of the image to be evaluated may be used.

  In step S4, based on the selected color, that is, the base color, the sub color, and the accent color, information related to the impression given to the human by the evaluated image is extracted. More specifically, a database in which conditions for combining base colors, sub-colors or accent colors and expression information relating to impressions received by humans is created in advance, and the selected base color, sub-color and Expression information associated with a condition that matches the combination of accent colors is extracted.

  Here, a description will be given using the database shown in FIG. This database includes a database on the condition of the combination of the base color and the two sub-colors, and a database on the condition of the combination of the two accent colors. However, the combination conditions of the base color, the sub color, and the accent color are not limited to these, and other combinations may be used as the conditions.

  Referring to these databases, for example, in FIG. 14, text information “bold” and “clear” can be extracted from the base color, sub-color, and accent color selected from the image to be evaluated.

  In step S5, the output unit 16 displays the selected base color, sub color, accent color, and extracted expression information. The output is preferably performed in such a manner that information relating to the image is easily grasped by the user.

  For example, as shown in FIG. 17, an image to be evaluated 160, an image color information display unit 161 that indicates the area of the color on the color palette included in the image to be evaluated, and a color image that displays expression information extracted from the selected color. It is preferable to include a display unit 163 that displays 162 and the selected color.

  Similar to the first image impression evaluation method, the image color information display unit 161 displays the area of the color on the color palette included in the image to be evaluated and the screen area proportional to the area as the color on the color palette. It is displayed filled with.

  The color image 162 divides an output screen area into a plurality of divided screen areas, assigns a condition composed of a combination of a base color, a sub color, and an accent color to each divided screen area, and is used when extracting expression information The expression information extracted from the condition is displayed in the area to which the condition that matches is assigned. In addition, it is also preferable to display the base color, the sub color, and the accent color used for extracting the expression information.

  Since the specific display method is the same as that of the first image impression evaluation method, description thereof is omitted here.

  As described above, according to the first and second image impression evaluation methods, information on the impression that the image gives to the human from the feature amount suitable for evaluating the impression that the image gives to the human and the condition that the combination satisfies. Can be presented automatically.

  Therefore, even a user who has little experience in image creation can obtain information regarding an accurate impression only by inputting image data.

  Moreover, not only information related to the impression that the image gives to humans, but also feature quantities used for evaluation can be presented in a manner that is easy for the user to grasp, and the user can easily grasp general information related to the image. be able to.

<Third image impression evaluation method>
In the case of an image or document in which content such as hypertext format is structured, it is possible to automatically perform image segmentation and feature extraction by analyzing the syntax of text information constituting the content. it can.

  Hereinafter, a processing method for impression evaluation of a structured image will be described with reference to the drawings. Similar to the first image impression evaluation method, the input of the image to be evaluated (step S1), the division of the image area (step S2), the subroutine for acquiring the physical feature amount (step S3), the extraction of the impression evaluation (step S4) and an evaluation result output (step S5), which are executed by sequentially performing each step.

  Since step S1 is processed in the same manner as the first image impression evaluation method, description thereof is omitted here.

  In step S2, the image to be evaluated is divided into a plurality of areas. At this time, the structured image data is analyzed and divided into divided image regions for each structured content.

  When an image described in the HTML format read from the network 26 is an evaluation target, the content bundled with each tag included in the image data is set as one divided image region. For example, a portion between a <head> tag and a </ head> tag can be divided as a header portion.

  In step S3, a feature amount is extracted from each image region divided in step S2. That is, information such as color, size, and arrangement for each content divided as each image area is extracted as a feature amount.

  Hereinafter, in step S4 and step S5, since processing is performed in the same manner as in the first image impression evaluation method, description thereof is omitted.

  As described above, according to the third image impression evaluation method, it is possible to extract feature amounts from structured image data such as a hypertext format and present information related to the impression that the image gives to humans. Further, by combining the image data in the bitmap format of the image to be evaluated and the above syntax analysis, more accurate region division can be performed.

  According to the present embodiment, a plurality of visual feature amounts are acquired from an image to be evaluated, and presented in a form that makes it easy to grasp information related to the impression that the image gives to humans based on the combination of the feature amounts. can do.

  Further, the user can obtain the above information only by inputting image data of an image to be evaluated. Therefore, even a user with little experience in image creation or the like can accurately grasp information related to the impression of the image.

It is a block diagram of the structure of the image impression evaluation apparatus in this Embodiment. It is a figure which shows the flowchart of the 1st image impression evaluation method in this Embodiment. It is a figure which shows the example which divided | segmented the image used as evaluation object into an image area | region. It is a figure which shows the flowchart of step S3 of the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows the Munsell hue ring in uniform color space. It is a figure which shows the example of the feature-value acquired with the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows the example of the database for expression information extraction used with the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows another example of the database for expression information extraction used with the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows the example of an output of the evaluation result of the 1st image impression evaluation method in embodiment of this invention. It is explanatory drawing of the method of displaying the image color information display part of the 1st image impression evaluation method in embodiment of this invention. It is explanatory drawing of the method of displaying the color image of the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows the example of a display of the color image of the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows another example of a display of the evaluation result of the 1st image impression evaluation method in embodiment of this invention. It is a figure which shows the flowchart of the 2nd image impression evaluation method in embodiment of this invention. It is a figure which shows the example of the base color, sub color, and accent color which were acquired with the 2nd image impression evaluation method in embodiment of this invention. It is a figure which shows the example of the database for expression information extraction used with the 2nd image impression evaluation method in embodiment of this invention. It is a figure which shows the example of an output of the evaluation result of the 2nd image impression evaluation method in embodiment of this invention.

Explanation of symbols

  10 control unit, 12 internal storage unit, 14 large capacity storage unit, 16 output unit, 18 standard input unit, 20 image input unit, 22 interface unit, 24 bus, 26 network, 30 header unit, 31 title unit, 32 header unit , 33 Link button part, 34 Image image part, 35 Text part, 90 Evaluation target image (evaluated image), 91 Image color information display part, 92 Color image, 93 Color display part of main area.

Claims (7)

An image impression evaluation method for presenting information on an impression given to a human by the image based on visual information acquired from the image,
A feature amount acquisition step of acquiring at least one feature amount from an image to be evaluated;
Displaying the acquired feature amount on an output screen as information on an impression given to a human by the image to be evaluated,
The area of the output screen is divided into a plurality of divided screen areas, a condition is assigned to each of the divided screen areas, and the acquired feature quantity itself is displayed in the divided area corresponding to the condition that the acquired feature quantity satisfies. An output process to
The image impression evaluation method characterized by performing the process containing these. An image impression evaluation method for presenting information on an impression given to a human by the image based on visual information acquired from the image,
A region dividing step for dividing the image to be evaluated into a plurality of image regions;
A feature amount acquisition step of acquiring at least one feature amount from an image included in each of the image regions;
Displaying the acquired feature amount on an output screen as information on an impression given to a human by the image to be evaluated,
The area of the output screen is divided into a plurality of divided screen areas, a condition is assigned to each of the divided screen areas, and the acquired feature quantity itself is displayed in the divided area corresponding to the condition that the acquired feature quantity satisfies. An output process to
The image impression evaluation method characterized by performing the process containing these. The image impression evaluation method according to claim 2,
The image impression evaluation method, wherein the feature amount includes a feature amount relating to a visual feature difference between the image regions. In the image impression evaluation method according to claim 3,
The feature amount is at least one of a feature amount related to a color difference between an entire image and an image region, a color difference between a background and an image region, or a color difference between an image region and an image region adjacent to the image region. Image impression evaluation method. In the image impression evaluation method according to claim 1 or 2,
The feature amount includes an average color and an area,
The information on the acquired feature amount is image information that displays an average color of the image region in an area of the output screen that is proportional to the area of the image region from which the acquired feature amount is acquired. Characteristic image impression evaluation method. The image impression evaluation method according to claim 2,
The feature amount includes an average color and an area,
The output step includes
Dividing the output screen area into a plurality of divided screen areas;
Assign a different color to each split screen area,
An image including a step of displaying an average color of the image area in an area proportional to the area of the image area in the divided screen area corresponding to the average color of the image area for each image area; Impression evaluation method. In the image impression evaluation method according to claim 1 or 2,
The image impression evaluation method, wherein the feature quantity is at least one of feature quantities relating to brightness, saturation, hue, average color, area, or position.

Images