JP4934380B2 - Image evaluation apparatus and method, and program - Google Patents

Description

  The present invention relates to an image evaluation apparatus and method for evaluating an image, and a program for causing a computer to execute the image evaluation method.

  In recent years, the spread of digital cameras and the increase in the capacity of recording media for recording images have made it possible for users to hold many images in a single recording medium. Yes. On the other hand, there is a trouble of selecting an image to be processed, such as a print order, from a vast number of images, and in order to select an image efficiently, the user finally determines that the image is to be printed. In addition, there is a demand for a function for narrowing an image under a certain condition and a function for selecting an image suitable for printing according to the user's preference.

For example, Patent Document 1 proposes a method of evaluating a plurality of images using focus, exposure amount, blur amount, subject size, contrast, and the like, and displaying the order of the images. Patent Document 2 discloses a method for automatically selecting an image suitable for printing on the basis of any evaluation value of image brightness, acceleration sensor output value, and AF evaluation. According to these methods, an image with a higher evaluation value can be selected as an image suitable for printing based on the evaluation result of the image, so that the burden on the user can be reduced.
JP 2000-137771 A JP 2002-10179 A

  By the way, it is selected when the user himself selects an image suitable for printing from a plurality of images classified into a plurality of groups for each event or a plurality of images classified into a plurality of groups of similar images. Since the determination to prevent the images from being biased to the same group works unconsciously, images can be selected almost uniformly from a plurality of groups.

  However, if an image with a higher evaluation value is selected using the evaluation values calculated using the methods described in Patent Literatures 1 and 2, multiple images of the same event are selected in duplicate or similar. Since a plurality of images are selected in duplicate, there is a problem that the selected images are biased to the same event or similar images.

  The present invention has been made in view of the above circumstances, and an object of the present invention is to evaluate images so that images can be selected while avoiding duplication of images more than necessary.

A first image evaluation apparatus according to the present invention includes an evaluation value acquisition unit that acquires a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups;
Evaluation value determining means for performing an evaluation value determining process for determining the temporary evaluation value of at least one image having a temporary evaluation value serving as a predetermined evaluation standard as an evaluation value of the image;
Evaluation value changing means for performing an evaluation value changing process for changing the temporary evaluation values of all the images of the group into which the images for which the evaluation values have been determined are classified according to the predetermined evaluation criteria;
The evaluation value determining means and the evaluation value determining means using the changed temporary evaluation value and the evaluation value changing process are repeatedly performed until evaluation values for a predetermined number of images are determined. And a control means for controlling the evaluation value changing means.

  “Acquire temporary evaluation value” means that if the evaluation value of the image is calculated in advance, it is acquired as the temporary evaluation value. If the evaluation value is not calculated, the evaluation value of the image is temporarily evaluated. It means obtaining by calculating as a value.

  As the “predetermined evaluation criteria”, for example, the temporary evaluation value is maximized, the sorting order when a plurality of images are sorted in the order of the temporary evaluation value is equal to or greater than a predetermined threshold, and the temporary evaluation value is minimum And the sort order when a plurality of images are sorted in the order of temporary evaluation values is less than a predetermined threshold value. Note that when the plurality of images are sorted in the order of the temporary evaluation values, the sort order being equal to or greater than the predetermined threshold is synonymous with the provisional evaluation value being equal to or greater than the predetermined threshold. The fact that the sorting order when sorted in the order of the provisional evaluation value is less than the predetermined threshold value is synonymous with the provisional evaluation value being less than the predetermined threshold value.

The second image evaluation apparatus according to the present invention includes an evaluation value acquisition unit that acquires a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups according to a plurality of types of classification criteria;
Evaluation value determining means for performing an evaluation value determining process for determining the temporary evaluation value of at least one image having a temporary evaluation value serving as a predetermined evaluation standard as an evaluation value of the image;
Evaluation value change processing for changing the temporary evaluation values of all the images according to the predetermined evaluation criteria for each of a plurality of groups based on a plurality of types of classification criteria in which the images for which the evaluation values are determined are classified Evaluation value changing means for performing
The evaluation value determining means and the evaluation value determining means using the changed temporary evaluation value and the evaluation value changing process are repeatedly performed until evaluation values for a predetermined number of images are determined. And a control means for controlling the evaluation value changing means.

  In the first and second image evaluation apparatuses according to the present invention, the sorting order when the plurality of images are sorted in the order of the temporary evaluation values with respect to the predetermined evaluation criterion is a predetermined threshold value or more. On the contrary, the sorting order when the plurality of images are sorted in the order of the temporary evaluation values may be less than a predetermined threshold based on the predetermined evaluation criterion.

The first image evaluation method according to the present invention obtains a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups,
An evaluation value determination process is performed to determine the temporary evaluation value of at least one image having a temporary evaluation value serving as a predetermined evaluation standard as the evaluation value of the image,
Performing an evaluation value change process for changing the temporary evaluation values of all the images of the group into which the images for which the evaluation values have been determined are classified, according to the predetermined evaluation criteria;
The evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeatedly performed until evaluation values for a predetermined number of images are determined. .

The second image evaluation method according to the present invention obtains a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups according to a plurality of types of classification criteria,
An evaluation value determination process is performed to determine the temporary evaluation value of at least one image having a temporary evaluation value serving as a predetermined evaluation standard as the evaluation value of the image,
Evaluation value change processing for changing the temporary evaluation values of all the images according to the predetermined evaluation criteria for each of a plurality of groups based on a plurality of types of classification criteria in which the images for which the evaluation values are determined are classified And
The evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeatedly performed until evaluation values for a predetermined number of images are determined. .

  In addition, you may provide as a program for making a computer perform the 1st and 2nd image evaluation method by this invention.

  According to the first image evaluation device and method of the present invention, a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups is acquired and used as a predetermined evaluation criterion. An evaluation value determination process is performed to determine a temporary evaluation value of at least one image having a value as an evaluation value of the image. Next, an evaluation value changing process is performed in which the temporary evaluation values of all the images in the group in which the images for which the evaluation values are determined are classified are changed according to a predetermined evaluation criterion. Then, the evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeated until evaluation values for a predetermined number of images are determined.

  For this reason, once the evaluation value of the image is determined, the temporary evaluation value of all images in the group in which the image is classified is changed. Therefore, the temporary evaluation value of the image classified in the group is a predetermined value. While it becomes difficult to satisfy the evaluation standard, the temporary evaluation value of the image classified into a group different from the group easily satisfies a predetermined standard. Therefore, when the evaluation value determination process and the evaluation value change process are repeated, the image whose evaluation value is determined at the next evaluation value determination process is different from the group into which the images whose evaluation values have already been determined are classified. There is a high possibility that the image will be classified into Therefore, until the evaluation values for a predetermined number of images are determined, the evaluation values of the images will be determined almost uniformly in different groups, and as a result, when selecting an image based on the evaluation values, An image can be selected uniformly from different groups. This makes it possible to select images without bias by avoiding unnecessary duplication of images, such as when multiple similar images are selected in duplicate or multiple images of the same event are selected in duplicate. The image can be evaluated.

  According to the second image evaluation apparatus and method of the present invention, a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups based on a plurality of classification criteria is acquired, Evaluation value determination processing is performed in which a temporary evaluation value of at least one image having a temporary evaluation value serving as an evaluation criterion is determined as the evaluation value of the image. Next, for each of the plurality of groups into which the images for which the evaluation values are determined are classified, an evaluation value changing process is performed in which the temporary evaluation values of all the images are changed according to a predetermined evaluation criterion. Then, the evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeated until evaluation values for a predetermined number of images are determined.

  For this reason, once the evaluation value of the image is determined, the temporary evaluation values of all the images of the plurality of types of groups into which the image is classified are changed. While the evaluation value does not easily satisfy a predetermined evaluation criterion, the temporary evaluation values of images classified into a group different from the plurality of groups are likely to satisfy the predetermined criterion. Therefore, when the evaluation value determination process and the evaluation value change process are repeatedly performed, an image whose evaluation value is determined at the next evaluation value determination process is a plurality of groups into which images whose evaluation values have already been determined are classified. There is a high possibility that the images are classified into different groups. Therefore, until the evaluation values for a predetermined number of images are determined, the evaluation values of the images will be determined almost uniformly in different groups, and as a result, when selecting an image based on the evaluation values, An image can be selected uniformly from different groups. This makes it possible to select images without bias by avoiding unnecessary duplication of images, such as when multiple similar images are selected in duplicate or multiple images of the same event are selected in duplicate. Thus, the image can be evaluated.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a schematic block diagram showing the configuration of an image evaluation apparatus according to the first embodiment of the present invention. As shown in FIG. 1, the image evaluation apparatus 1 according to the present embodiment performs image evaluation in order to select an image from a plurality of images, and performs various controls such as image data recording control and display control. A CPU 12 that controls each part of the apparatus 1, a program that operates the CPU 12, viewer software for viewing images, a ROM that records various constants, and a work area when the CPU 12 executes processing. A system memory 14 including a RAM, a display unit 16 including a liquid crystal monitor for performing various displays, a display control unit 18 for controlling the display unit 16, and a keyboard for performing various instructions to the device 1. , An input unit 20 including a mouse and a touch panel, and an input control unit 22 for controlling the input unit 20.

  The image evaluation apparatus 1 controls the image reading unit 24 for reading image data from a medium such as a memory card in which image data representing an image is recorded and for recording image data on the medium, and the image reading unit 24. An image reading control unit 26 that stores the image data, and a hard disk 28 that stores various types of information including image data.

  In addition, the image evaluation apparatus 1 classifies a plurality of images to be evaluated into a plurality of groups based on a predetermined classification criterion, and a temporary evaluation value representing a temporary evaluation result for each of the plurality of images. Evaluation value acquisition unit 32 to be acquired, evaluation value determination unit 34 for performing an evaluation value determination process for determining the temporary evaluation value of one image having the maximum temporary evaluation value as the evaluation value of the image, and the evaluation value is determined And an evaluation value changing unit 36 for performing an evaluation value changing process for changing the temporary evaluation values of all the images of the group into which the classified images are classified.

  Then, the evaluation value determination unit repeats the evaluation value determination process and the evaluation value change process using the changed temporary evaluation value until the CPU 12 determines evaluation values for a predetermined number of images. 34 and the evaluation value changing unit 36 are controlled.

  Here, the image classification unit 30 classifies a plurality of images into a plurality of groups for each event, which is a set of images shot with a series of intentions. Specifically, a plurality of images are sorted into a plurality of groups for each event by using a technique in which a plurality of images are sorted in order of shooting date and time, and an interval between two images whose shooting time difference is equal to or larger than a predetermined value is used. Classify into: Note that the method of classifying a plurality of images into a plurality of groups for each event is not limited to this method, and one shooting location is regarded as one event, and information on the shooting location given to the image is used. Various known methods such as classification into a plurality of groups for each photographing location can be used.

  Note that images to be evaluated may be already classified into a plurality of groups for each of a plurality of events before being read from the image reading unit 24. In such a case, the image classification process by the image classification unit 30 becomes unnecessary. Further, when it is assumed that the images are classified into a plurality of groups, the image classification unit 30 is also unnecessary.

  The evaluation value acquisition unit 32 first acquires a temporary evaluation value by calculating an evaluation value representing an evaluation result of each image as a temporary evaluation value. As a method for calculating the evaluation value, for example, a face is detected from an image, and based on at least one information of a face size, a position on the face image, a face orientation, a face rotation angle, and a face detection score. Thus, a method of calculating an evaluation value using a statistical evaluation result can be used. The method for calculating the evaluation value is not limited to this method, and the image is evaluated based on any of the image brightness, the acceleration sensor output value, and the AF evaluation described in Patent Document 2 above. A method for determining the orientation of a person's face included in the image, and calculating an evaluation value of the image based on the determination result (see Japanese Patent Application Laid-Open No. 2004-361989), a ratio of the face in the image, Any method such as a method of calculating an evaluation value obtained by integrating a plurality of evaluation items such as the degree of opening, face orientation, focus, blur, and brightness (see Japanese Patent Application Laid-Open No. 2002-358522) can be used.

  Further, the evaluation value acquisition unit 32 calculates the importance of the group into which the plurality of images are classified as the evaluation value of each group. Here, in this embodiment, since a plurality of images are classified into a plurality of groups for each event, for example, as described in JP-A-2006-171942, the number of images included in a group, and each Based on information such as the number of groups related to the group, a method of calculating the importance of the group can be used.

  And the evaluation value acquisition part 32 acquires the addition value of the evaluation value of each image, and the evaluation value based on the importance of the group to which each image belongs as a temporary evaluation value of each image. In addition, it is good also considering only the evaluation value of an image as a temporary evaluation value, without using the evaluation value based on the importance of each group.

  When the evaluation of the read image has been completed and the evaluation value is assigned to the image (for example, described in a tag), the evaluation value acquisition unit 32 calculates the evaluation value without calculating the evaluation value. The evaluation value given to the image is acquired as a temporary evaluation value.

  Next, the evaluation value determination process performed by the evaluation value determination unit 34 and the evaluation value change process performed by the evaluation value change unit 36 will be described together with the process performed in the first embodiment. FIG. 2 is a flowchart showing processing performed in the first embodiment. In the first embodiment, it is assumed that the image read by the image reading unit 24 is stored in the hard disk 28. Also, it is assumed that no evaluation value is given to the image and no classification is made. The CPU 12 starts processing when an operator gives an instruction to select N images from images stored in the hard disk 28. First, the image classification unit 30 selects a plurality of images stored in the hard disk 28 for each event. Classify into a plurality of groups (step ST1). Next, the evaluation value acquisition unit 32 acquires temporary evaluation values for all images (step ST2). Note that N is a number arbitrarily selected by the operator, and may be the number of all images stored in the hard disk 28.

  Next, evaluation value determination processing in which the evaluation value determination unit 34 determines the temporary evaluation value as the evaluation value of the image for one image having the maximum temporary evaluation value among all the images for which the evaluation value has not been determined. Is performed (step ST3). Then, the evaluation value changing unit 36 performs an evaluation value changing process for changing the temporary evaluation values of all the images in the group in which the images for which the evaluation values have been determined are classified to a certain amount (step ST4).

  FIG. 3 is a diagram for explaining the evaluation value changing process in the first embodiment. Here, it is assumed that 15 images S1 to S15 are stored in the hard disk 28 and are classified into four groups G1 to G4 for each event as shown in FIG.

  When the image having the maximum temporary evaluation value is the image S7, the evaluation value changing unit 36 decreases the temporary evaluation values of all the other images S5, S6, S8, and S9 of the group G2 to which the image S7 belongs. To do. Specifically, the temporary evaluation value is changed by subtracting a predetermined value from the temporary evaluation value or multiplying the temporary evaluation value by a predetermined value smaller than 1 that is predetermined. The predetermined value may be a predetermined value, and is calculated so as to be smaller than the temporary evaluation value of any image in the other group with reference to the temporary evaluation value of the image of the other group. It may be a value.

  In this case, the degree of change may be different for each of the evaluation value of each image included in the temporary evaluation value and the evaluation value based on the event importance.

  Next, the CPU 12 determines whether or not N image evaluation values have been determined (step ST5). If step ST5 is negative, the CPU 12 returns to step ST3 and repeats the processing after step ST3. If step ST5 is affirmed, the N images for which the evaluation values are determined are displayed as selected images on the display unit 16 together with the evaluation values (step ST6), and the process is terminated. The operator can confirm the selected image on the display unit 16 and place a print order or record it on a medium such as a CD.

  As described above, in the first embodiment, the temporary evaluation values of all the images in the group in which the images for which the evaluation values are determined are classified are reduced, and the evaluation values for the predetermined N images are obtained. Until the determination is made, the evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeatedly performed.

  For this reason, once the evaluation value of the image is determined, the temporary evaluation value of all the images in the group in which the image is classified becomes small. Therefore, the temporary evaluation value of the image classified in the group becomes the maximum value. On the other hand, the provisional evaluation value of an image classified into a group different from the group tends to be the maximum value. Therefore, when the evaluation value determination process and the evaluation value change process are repeated, the image whose evaluation value is determined at the next evaluation value determination process is different from the group into which the images whose evaluation values have already been determined are classified. There is a high possibility that the image will be classified into Therefore, until the evaluation values for the N images are determined, the evaluation values of the images are almost uniformly determined in different groups. As a result, when selecting an image based on the evaluation values, An image can be selected uniformly. This makes it possible to evaluate images so that images can be selected without bias while avoiding unnecessary overlapping of images, such as when multiple images of the same event are selected redundantly.

  In the first embodiment, the image classification unit 30 classifies the plurality of images into a plurality of groups for each event. However, the plurality of images may be classified into a plurality of groups of similar images. Good. In this case, as the importance of the group, a similar image group including more similar images in each group is generated, and the number of similar image groups in each group and / or the number of images included in the similar image group is determined. A method for setting the importance of each group can be used. In this way, when a plurality of images are classified into a plurality of groups consisting of similar images, by evaluating the images according to the present embodiment, a plurality of similar images are not selected redundantly, Image evaluation can be performed so that images can be selected without bias while avoiding unnecessary overlap of similar images.

  Next, a second embodiment of the present invention will be described. The configuration of the image evaluation apparatus according to the second embodiment is the same as that of the image evaluation apparatus 1 according to the first embodiment, and thus detailed description thereof is omitted here. In the first embodiment, a plurality of images are classified into a plurality of groups for each event. In the second embodiment, a plurality of images are classified into a plurality of groups for each event. This is different from the first embodiment in that it is also classified into a plurality of groups.

  FIG. 4 is a diagram for explaining image classification and evaluation value change processing according to the second embodiment. FIG. 4A illustrates image classification for each event similar to FIG. Indicates the classification of similar images. In the second embodiment, the image classification unit 30 classifies the 15 images S1 to S15 into four groups G1 to G4 for each event as shown in FIG. As shown, it is classified into six groups Gs1 to Gs6 consisting of similar images. Here, the group G1 for each event includes images S1 to S4, the group G2 includes images S4 to S9, the group G3 includes images S10 to S12, and the group G4 includes images S13 to S15. On the other hand, the group Gs1 of similar images is the images S1, S2 and S5, the group Gs2 is the images S6 to S8, the group Gs3 is the images S3 and S4, the group Gs4 is the images S9 and S10, the group Gs5 is the image S12, and the group Gs6 is the image S11. ~ S15.

  Next, processing performed in the second embodiment will be described. FIG. 5 is a flowchart showing processing performed in the second embodiment. Also in the second embodiment, it is assumed that the image read by the image reading unit 24 is stored in the hard disk 28. Also, it is assumed that no evaluation value is given to the image and no classification is made. The CPU 12 starts processing when an operator gives an instruction to select N images from images stored in the hard disk 28. First, the image classification unit 30 selects a plurality of images stored in the hard disk 28 for each event. Classification into a plurality of groups and classification into a plurality of groups of similar images (image classification based on two criteria: step ST11). Next, the evaluation value acquisition unit 32 acquires temporary evaluation values for all images (step ST12). Note that N is a number arbitrarily selected by the operator, and may be the number of all images stored in the hard disk 28.

  Next, evaluation value determination processing in which the evaluation value determination unit 34 determines the temporary evaluation value as the evaluation value of the image for one image having the maximum temporary evaluation value among all the images for which the evaluation value has not been determined. Is performed (step ST13). Then, the evaluation value changing unit 36 performs a first evaluation value changing process for changing the temporary evaluation value of all the images in the group for each event in which the image for which the evaluation value is determined to be classified to be reduced by a certain amount ( Step ST14). Further, the evaluation value changing unit 36 performs a second evaluation value changing process for changing the temporary evaluation values of all the images of the group consisting of similar images into which the images for which the evaluation values have been determined are classified to a certain amount. (Step ST15).

  Thus, when the image having the maximum temporary evaluation value is the image S7, the evaluation value changing unit 36 temporarily displays all the other images S5, S6, S8, and S9 of the group G2 for each event to which the image S7 belongs. While reducing the evaluation value, the temporary evaluation values of all other images S6 and S8 of the group Gs2 of similar images to which the image S7 belongs are reduced. In this case, since the images S6 and S8 are classified into both groups G2 and Gs2, the temporary evaluation value is changed to be smaller.

  In this case, there is a degree of change for each of the evaluation value of each image included in the temporary evaluation value, the evaluation value obtained from the importance of the group into which the similar images are classified, and the evaluation value obtained from the event importance. It may be different.

  Next, the CPU 12 determines whether or not N image evaluation values have been determined (step ST16). If step ST16 is negative, the CPU 12 returns to step ST13 and repeats the processing from step ST13 onward. If step ST16 is affirmed, the N images for which the evaluation values have been determined are displayed as selected images on the display unit 16 together with the evaluation values (step ST17), and the process ends. The operator can confirm the selected image on the display unit 16 and place a print order or record it on a medium such as a CD.

  As described above, in the second embodiment, the temporary evaluation values of all the images in the plurality of types of groups into which the images for which the evaluation values are determined are classified are reduced, and the predetermined N images are determined. Until the evaluation value is determined, the evaluation value determination process and the evaluation value change process using the changed temporary evaluation value are repeatedly performed.

  For this reason, once the evaluation value of the image is determined, the temporary evaluation value of all the images in the group in which the image is classified becomes small. Therefore, the temporary evaluation value of the image classified in the group becomes the maximum value. On the other hand, the provisional evaluation value of an image classified into a group different from the group tends to be the maximum value. Therefore, when the evaluation value determination process and the evaluation value change process are repeated, the image whose evaluation value is determined at the next evaluation value determination process is different from the group into which the images whose evaluation values have already been determined are classified. There is a high possibility that the image will be classified into Therefore, until the evaluation values for the N images are determined, the evaluation values of the images are almost uniformly determined in different groups. As a result, when selecting an image based on the evaluation values, An image can be selected uniformly. As a result, multiple images of the same event can be selected redundantly, multiple similar images can be selected redundantly, etc., so that it is possible to select images without bias, avoiding unnecessary overlapping of images. The image can be evaluated.

  In the first and second embodiments, the evaluation value determination unit 34 determines the evaluation value of one image that maximizes the temporary evaluation value. The evaluation value of the image (<N) may be determined. Alternatively, the evaluation values of the upper predetermined number (<N) of images when the images are sorted in the order of temporary evaluation values may be determined. In this case, the evaluation value changing unit 36 changes the temporary evaluation values of the images classified into all groups into which the plurality of images whose evaluation values have been determined are classified.

  In the first and second embodiments, the evaluation value determination unit 34 determines the evaluation value of one image that maximizes the temporary evaluation value, but one image that minimizes the temporary evaluation value. The evaluation value may be determined. In this case, the evaluation value changing unit 36 changes the evaluation value of all the images in the group in which the image for which the evaluation value is determined is classified.

  As a result, for example, when the image evaluation apparatus 1 according to the present embodiment is applied to a digital camera, it is easy to select and delete unnecessary images in ascending order of evaluation values. It is effective in the case. Also in this case, the evaluation values of a plurality (<N) of images whose temporary evaluation values are less than the predetermined value may be determined, and the lower predetermined number (<N) when the images are sorted in the order of the temporary evaluation values. The evaluation value of the image may be determined. In this case, the evaluation value changing unit 36 changes the temporary evaluation values of the images classified into all groups into which the plurality of images whose evaluation values have been determined are classified.

  Although the apparatus 1 according to the embodiment of the present invention has been described above, the computer functions as a unit corresponding to the image classification unit 30, the evaluation value acquisition unit 32, the evaluation value determination unit 34, and the evaluation value change unit 36. A program for performing the processing shown in FIGS. 2 and 5 is one embodiment of the present invention. A computer-readable recording medium in which such a program is recorded is also one embodiment of the present invention.

1 is a schematic block diagram showing the configuration of an image evaluation apparatus according to a first embodiment of the present invention. The flowchart which shows the process performed in 1st Embodiment. The figure for demonstrating the classification and evaluation value change process of the image in 1st Embodiment The figure for demonstrating the classification and evaluation value change process of the image in 2nd Embodiment The flowchart which shows the process performed in 2nd Embodiment.

Explanation of symbols

1 Image evaluation device 12 CPU
DESCRIPTION OF SYMBOLS 14 System memory 16 Display part 18 Display control part 20 Input part 22 Input control part 24 Image reading part 26 Image reading control part 28 Hard disk 30 Image classification part 32 Evaluation value acquisition part 34 Evaluation value determination part 36 Evaluation value change part

Claims (8)

Evaluation value acquisition means for acquiring a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups;
An evaluation value determining means for performing an evaluation value determining process for determining, as an evaluation value of the image, the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation criterion and less than a predetermined number; ,
Evaluation value changing means for performing an evaluation value changing process for reducing the temporary evaluation values of all the images of the group into which the images for which the evaluation values are determined are classified according to the predetermined evaluation criteria;
The evaluation value determining means repeats the evaluation value determination process and the evaluation value change process using the reduced temporary evaluation value until evaluation values for the predetermined number of images are determined. And an image evaluation apparatus comprising control means for controlling the evaluation value changing means. Evaluation value acquisition means for acquiring a temporary evaluation value representing a temporary evaluation result for each of a plurality of images classified into a plurality of groups according to a plurality of types of classification criteria;
An evaluation value determining means for performing an evaluation value determining process for determining, as an evaluation value of the image, the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation criterion and less than a predetermined number; ,
Evaluation value change processing for reducing the provisional evaluation values of all the images according to the predetermined evaluation criteria for each of a plurality of groups based on a plurality of types of classification criteria in which the images for which the evaluation values are determined are classified Evaluation value changing means for performing
The evaluation value determining means repeats the evaluation value determination process and the evaluation value change process using the reduced temporary evaluation value until evaluation values for the predetermined number of images are determined. And an image evaluation apparatus comprising control means for controlling the evaluation value changing means.   The image evaluation according to claim 1, wherein the predetermined evaluation criterion is that a sorting order when the plurality of images are sorted in the order of the temporary evaluation values is equal to or greater than a predetermined threshold value. apparatus.   The image evaluation according to claim 1, wherein the predetermined evaluation criterion is that a sorting order when the plurality of images are sorted in the order of the temporary evaluation values is less than a predetermined threshold value. apparatus. Obtain temporary evaluation values that represent temporary evaluation results for each of multiple images classified into multiple groups,
Performing an evaluation value determination process for determining the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation standard, which is smaller than a predetermined number, as an evaluation value of the image,
Performing an evaluation value changing process for reducing the temporary evaluation values of all the images of the group into which the images for which the evaluation values have been determined are classified according to the predetermined evaluation criteria;
The image evaluation characterized by repeatedly performing the evaluation value determination process and the evaluation value change process using the reduced temporary evaluation value until evaluation values for the predetermined number of images are determined. Method. Obtain temporary evaluation values that represent temporary evaluation results for each of multiple images classified into multiple groups according to multiple types of classification criteria,
Performing an evaluation value determination process for determining the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation standard, which is smaller than a predetermined number, as an evaluation value of the image,
Evaluation value change processing for reducing the provisional evaluation values of all the images according to the predetermined evaluation criteria for each of a plurality of groups based on a plurality of types of classification criteria in which the images for which the evaluation values are determined are classified And
The image evaluation characterized by repeatedly performing the evaluation value determination process and the evaluation value change process using the reduced temporary evaluation value until evaluation values for the predetermined number of images are determined. Method. A procedure for obtaining a provisional evaluation value representing a provisional evaluation result for each of a plurality of images classified into a plurality of groups;
A procedure for performing an evaluation value determination process for determining, as the evaluation value of the image, the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation criterion and less than a predetermined number;
A procedure for performing an evaluation value change process for reducing the temporary evaluation values of all the images of the group into which the images for which the evaluation values have been determined are classified according to the predetermined evaluation criteria;
A step of repeatedly performing the evaluation value determination process and the evaluation value change process using the reduced provisional evaluation value until evaluation values for the predetermined number of images are determined. A program for causing a computer to execute the image evaluation method. A procedure for obtaining a provisional evaluation value representing a provisional evaluation result for each of a plurality of images classified into a plurality of groups according to a plurality of classification criteria;
A procedure for performing an evaluation value determination process for determining, as the evaluation value of the image, the temporary evaluation value of at least one image having a temporary evaluation value that is a predetermined evaluation criterion and less than a predetermined number;
Evaluation value change processing for reducing the provisional evaluation values of all the images according to the predetermined evaluation criteria for each of a plurality of groups based on a plurality of types of classification criteria in which the images for which the evaluation values are determined are classified The steps to do
A step of repeatedly performing the evaluation value determination process and the evaluation value change process using the reduced provisional evaluation value until evaluation values for the predetermined number of images are determined. A program for causing a computer to execute the image evaluation method.

Images