JP2009118079A - Image evaluating device and image evaluating program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To evaluate the deterioration state of image quality in each frame constituting moving image data. <P>SOLUTION: An image quality evaluating part 103a calculates featured values of each frame in the inputted moving image data, and extracts as the calculation result the distinctive image from the plurality of frames, based on a threshold received from a user on a setting screen. An evaluation result output part 103b displays the calculation result by the image quality evaluating part 103a on the screen by a numerical value (an evaluation value) or a graphic (an indicator). <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to an image evaluation apparatus and an image evaluation program for evaluating input moving image data.

  The following data analysis apparatuses are known. This data analysis apparatus simultaneously displays an image to be evaluated for image quality, a parameter for evaluating image quality, a chart or graph indicating the evaluation result, and various control buttons (for example, Patent Document 1).

JP-A-2005-107766

  However, in the conventional data analysis apparatus, the user cannot arbitrarily set a threshold value used for image evaluation.

An image evaluation apparatus and an image evaluation program according to the present invention calculate a feature amount of each frame of input moving image data, and extract a characteristic image from a plurality of frames constituting the moving image data. A characteristic image is extracted from a plurality of frames based on the feature value calculation result and the received threshold value, and the feature value calculation result is displayed on the screen as a numerical value or a figure. Features.
In the image evaluation apparatus according to the present invention, the characteristic image is preferably any one of a blurred image, a monochromatic image, and a partial monochromatic image including a monochromatic area in a part of the image.
The feature amount representing the blur level is calculated for each frame, and the setting of the minimum value and the maximum value of the feature amount representing the blur level is accepted as a threshold for extracting the blur image. When it is within the range indicated by the minimum value and the maximum value, the frame may be extracted as a blurred image.
A feature value representing a monochromatic image is calculated for each pixel of the frame, and setting of minimum and maximum values of the feature value representing the monochromatic image is accepted as a threshold for extracting the monochromatic image, and all the features in the frame are received. When the feature amount representing the calculated monochromatic tone is within the range indicated by the minimum value and the maximum value in the pixel, the frame may be extracted as a monochromatic image.
A feature amount representing a partial monochromatic image is calculated for each pixel of the frame, and a minimum value and a maximum value setting of the feature amount representing the partial monochromatic image are accepted as a threshold for extracting the partial monochromatic image, and the frame When all of the pixels in at least one region set within are within the range indicated by the minimum value and the maximum value, the frame is extracted as a partial monochromatic image. You may do it.
The first display area that displays the input moving image data, the second display area that displays the extracted feature image, the calculation result of the feature value is displayed as a numerical value or a figure, and whether or not the feature image exists for each frame. The third display area displaying the determination result and the fourth display area displaying the evaluation result of the moving image data in a graph may be displayed on one screen.
You may make it synchronize the display content to each display area of a 1st display area, a 2nd display area, a 3rd display area, and a 4th display area.
Based on an instruction from the user, any one or more of the first display area, the second display area, the third display area, and the fourth display area may be hidden.

  According to the present invention, a user can arbitrarily set a threshold used for image evaluation.

  FIG. 1 is a block diagram showing a configuration of an embodiment of an image evaluation apparatus according to the present embodiment. The image evaluation apparatus 100 is, for example, a personal computer, and includes an operation member 101, a connection IF (interface) 102, a control device 103, an HDD (hard disk drive) 104, and a monitor 105.

  The operation member 101 includes various devices operated by the user, such as a keyboard and a mouse. The connection IF 102 is an interface for connecting an external device such as a digital camera. For example, a USB interface for performing a wired connection with a digital camera or a video camera, a wireless LAN module for performing a wireless connection, or the like is used. The In the present embodiment, for example, moving image data is taken in from a digital camera or a video camera capable of moving image shooting via the connection IF 102.

  The HDD 104 is a recording device for recording moving image data captured via the connection IF 102, various programs executed by the control device 103, and the like. In the present embodiment, it is assumed that the moving image data is recorded in the HDD 104 as a moving image data of a predetermined format, for example, taken by a digital camera with a moving image shooting function or a digital video camera. In the present embodiment, it is assumed that the moving image data format is the YUV format. The monitor 105 is a liquid crystal monitor, for example, and displays display data output from the control device 103.

  The control device 103 includes a CPU, a memory, and other peripheral circuits, and functionally includes an image quality evaluation unit 103a and an evaluation result output unit 103b. The image quality evaluation unit 103 a extracts a characteristic frame (characteristic image) from a plurality of frames constituting the moving image data recorded in the HDD 104. In this embodiment, as a characteristic frame, a blurred image, an image in which the entire frame is monochromatic, and an image in which a part of the area in the frame is monochromatic are extracted.

  Here, the entire frame having a single color tone means an image that can be regarded as a single color image when the entire frame has luminance, color, or density within a predetermined range. An object of the present embodiment is to extract a blackout frame due to a malfunction during encoding from a plurality of frames constituting moving image data. It should be noted that a blacked-out frame generated due to a problem during encoding is not always a single black image, and may be blackish or greenish as a whole image. For this reason, in the present embodiment, as described later, the user can arbitrarily set a threshold for determining as a blackout frame.

  When the pixel values of all the pixels in the frame are within the range set by the threshold value, the image quality evaluation unit 103a is a black-out frame that is a monochrome image as a whole. Judge. An image in which a part of the area in the frame is monochromatic means a frame in which the image in the part of the area in the frame is the above-described monotone image. In the present embodiment, a blurred image is referred to as a blurred image, an image in which the entire frame is monochromatic, a blackout image, and an image in which a part of the frame is monochromatic is referred to as a partial blackout image.

  The evaluation result output unit 103b displays a main screen as shown in FIG. On this main screen, an evaluation image display window 2a for displaying moving image data (input video) to be evaluated and a characteristic image extracted from a frame being displayed in the evaluation image display window 2a are displayed. A feature image display window 2b, an evaluation result list display window 2c for displaying a list of evaluation results of moving image data by the image quality evaluation unit 103a, and a graph of the evaluation result of moving image data by the image quality evaluation unit 103a. An evaluation result graph display window 2d for this purpose is arranged.

  Note that the user can switch which of the above-described blurred image, blackout image, and partial blackout image is displayed in the feature image display window 2b. Further, the user can select any one or more of these windows and set them to non-display. The evaluation result output unit 103b erases and hides the window set to be hidden by the user from the screen.

  The evaluation result output unit 103b synchronizes the display contents of each window on the main screen. That is, when one frame constituting moving image data is displayed in the evaluation image display window 2a, the feature image extracted from the frame is displayed in the feature image display window 2b. Further, the evaluation result list display window 2c displays the evaluation result for the frame, and the graph of the evaluation result graph display window 2d is updated to the one added with the evaluation result for the frame. Then, when the frame displayed in the evaluation image display window 2a is switched to the next frame, the evaluation result output unit 103b switches the display of the other window to the one related to the next frame at the same time.

  In the example shown in FIG. 2, the pixel value display window 2e and the main console 2f are also arranged on the main screen. However, these are not characteristic portions of the present invention, and thus the description thereof is omitted.

  Hereinafter, a method in which the image quality evaluation unit 103a extracts each of (A) a blurred image, (B) a blackout image, and (C) a partial blackout image from a plurality of frames constituting moving image data will be described. In the following description, it is assumed that the image size of each frame is M × N (pixel).

  In the present embodiment, for each frame, the user evaluates the degree of blur for extracting a blurred image, blackout evaluation for extracting a blackout image, and a portion for extracting a partial blackout image. Preset which of the blackout evaluations to perform. For example, the user selects an item to be evaluated from among the evaluation items displayed on the setting screen shown in FIG. 3, operates the operation member 101, and puts a check in the check column 3a. The image quality evaluation unit 103a executes the following processing to evaluate the evaluation item selected by the user on the setting screen of FIG.

  On the setting screen shown in FIG. 3, the user can select an evaluation value calculation method in the evaluation value calculation method selection field 3b. In the present embodiment, as described later, the user calculates an evaluation value based on a threshold (determined from the threshold), calculates a threshold based on a coefficient (determines from the coefficient), and calculates an evaluation value. It is possible to select either not (not required). Further, the user can save the setting contents on this setting screen to a file by pressing the “save to file” button 3c. The user can press the “read from file” button 3d to save the setting contents. You can also read saved files and reflect the settings. When the setting is completed, the user presses the “OK” button 3e to confirm the setting.

(A) Blurred Image Extraction Method The image quality evaluation unit 103a applies a horizontal Sobel filter shown in FIG. 4A to each frame to obtain an image V (i, j) in which a vertical component is detected. . Further, an image H (i, j) in which a horizontal component is detected is obtained by applying a vertical Sobel filter shown in FIG. 4B to the image. Then, an edge image R (i, j) obtained by synthesizing the differential images in the horizontal direction and the vertical direction is calculated based on the image V (i, j) and H (i, j) by the following expression (1). To do.

なお、このエッジ度ＳＩは、エッジ画像Ｒ（ｉ，ｊ）の標準偏差であり、その値が大きいほどぼやけの度合いは低く、その値が大きいほどぼやけの度合いが高くなる。 Then, using the edge image R (i, j), the edge degree SI that is a feature amount indicating the degree of the edge in the frame can be calculated by the following equation (2).

The edge degree SI is a standard deviation of the edge image R (i, j). The larger the value, the lower the degree of blurring, and the larger the value, the higher the degree of blurring.

  Therefore, when the edge degree SI calculated by the equation (2) is within the range determined by the set threshold, the image quality evaluation unit 103a evaluates the frame as a blurred image, and determines the frame as Extract as a blurred image. Note that since the degree of determination as to whether or not to make a blurred image varies depending on the person, the threshold used at this time can be arbitrarily set by the user. For example, the user can input and specify the minimum threshold value U1 and the maximum threshold value U2 determined as a blurred image on the setting screen shown in FIG. The image quality evaluation unit 103a determines that the frame is a blurred image when the calculated edge degree SI is within the range of the threshold values U1 to U2 specified here.

  On the setting screen shown in FIG. 5, the user, as will be described later, threshold values 5a to 5g used by the evaluation result output unit 103b to display the evaluation result of the blur level using an indicator, The evaluation result output unit 103b can set threshold values 5h to 5o used for displaying the evaluation result of the blur level using the evaluation value.

  The evaluation result output unit 103b displays, in the indicator display field 2g in the evaluation result list display window 2c of FIG. 2, an indicator in which the degree of blur is color-coded in a plurality of stages based on the magnitude of the edge degree SI. For this reason, the user sets a boundary value at which the color of the indicator changes as a threshold on the setting screen shown in FIG. In FIG. 5, each of the areas 5p to 5u is displayed in a different color, and the longer the displayed indicator is, the lower the edge degree SI is, that is, the higher the degree of blur of the frame is. Conversely, the shorter the displayed indicator, the higher the edge degree SI, that is, the lower the blurring degree of the frame.

  In the example of FIG. 5, the user sets the minimum value of the region 5p to the threshold value 5a, and sets the boundary between the regions 5p and 5q to the threshold value 5b. Similarly, the boundary between the regions 5q and 5r is set to the threshold value 5c, the boundary between the regions 5r and 5s is set to the threshold value 5d, and the boundary between the regions 5s and 5t is set to the threshold value 5e. Further, the boundary between the regions 5t and 5u is set to the threshold value 5f, and the maximum value of the region 5u is set to the threshold value 5g.

  Further, the user sets a threshold value used for displaying the evaluation result of the blur level as an evaluation value based on the edge degree SI in the threshold values 5h to 5o. The threshold value of the evaluation value is set corresponding to the threshold value of the indicator described above. That is, in the example of FIG. 5, the evaluation value when the edge degree SI is equal to or less than the threshold value 5a is set to the threshold value 5h. The evaluation value when the edge degree SI is not less than the threshold value 5a and less than 5b is set to the threshold value 5i. Similarly, the evaluation value when the edge degree SI is the threshold value 5b or more and less than 5c is the threshold value 5j, the evaluation value when the edge degree SI is the threshold value 5c or more and less than 5d is the threshold value 5k, and the edge degree SI is the threshold value 5d or more and less than 5e. The evaluation value at this time is set to the threshold value 5l. The evaluation value when the edge degree SI is not less than the threshold value 5e and less than 5f is the threshold value 5m, the evaluation value when the edge degree SI is not less than the threshold value 5f and less than 5g is the threshold value 5n, and the evaluation value when the edge degree SI is the threshold value 5g or more. The evaluation value is set to the threshold value 5o.

  When the setting on the setting screen is completed, the user can confirm the setting contents by pressing the “OK” button 5w. Also, by pressing the “Cancel” button 5x, the setting screen can be closed without confirming the setting contents. Further, by pressing the “return to initial value” button 5v, the setting contents can be canceled and the values in the respective input fields can be returned to the initial values.

  The evaluation result output unit 103b displays the determination result as to whether or not each frame is a blurred image by the image quality evaluation unit 103a in the NG determination display field 2h in the evaluation result list display window 2c on the main screen shown in FIG. indicate. For example, the evaluation result output unit 103b displays “NG” in the NG determination display field 2h corresponding to the frame determined to be a blurred image. At this time, the evaluation result output unit 103b may change the background color of the display line of the corresponding frame, change the display color of the character, or blink the character.

  Further, the evaluation result output unit 103b determines the magnitude of the blur level of the frame based on the magnitude of the edge degree SI calculated by the image quality evaluation unit 103a and the threshold values 5a to 5g set on the setting screen of FIG. Is displayed in the indicator display field 2g in the evaluation result list display window 2c shown in FIG. Further, the evaluation result output unit 103b determines the frame based on the magnitude of the edge degree SI calculated by the image quality evaluation unit 103a, the thresholds 5a to 5g and the thresholds 5h to 5o set on the setting screen of FIG. The evaluation value indicating the magnitude of the blur level is displayed in the evaluation value display field 2i in the evaluation result list display window 2c shown in FIG.

  Accordingly, the evaluation result output unit 103b can display the calculation result by the image quality evaluation unit 103a as a graphic (indicator) and a numerical value (evaluation value). In the present embodiment, the example in which the calculation result by the image quality evaluation unit 103a is expressed using the indicator and the evaluation value is described. However, only one of them may be expressed.

(B) Blackout image extraction method When the pixel value of all the pixels of each frame is within the threshold range set by the user on the setting screen described later with reference to FIG. The frame is evaluated as a blackout image, and the frame is extracted as a blackout image. Here, a method for setting a threshold value by the user will be described. FIG. 6 is a setting screen for setting a threshold for extracting a blackout image. Note that the threshold value set on the setting screen of FIG. 6 is also used as a threshold value for extracting a partial blackout image described later in (C). The user can set whether to extract each of the blackout image and the partial blackout image using the set threshold in the NG determination target selection field 6g on the setting screen shown in FIG.

  As described above, since the format of the moving image data is the YUV format, in the setting screen shown in FIG. 6, the user sets threshold values for Y as a luminance component and U and V as color difference components. Set. In the present embodiment, the user can set a plurality of threshold values for Y, U, and V on the setting screen shown in FIG. 6, and can manage by assigning a name to each threshold set.

  As a method for setting the threshold value, a range that can be taken by the threshold value, such as “lower limit value−upper limit value”, is divided and input by “−” (hyphen). At this time, the user can set the lower limit value of the threshold value to 0 by adding “-” in front of the numerical value. For example, when “−16” is input as the threshold, the threshold range can be set to 0 or more and less than 16. Further, by adding “−” after the numerical value, the upper limit value of the threshold value can be set to 256. For example, when “240−” is input as the threshold, the threshold range can be set to 240 or more and less than 256. When “−” is not added before and after the numerical value, the numerical value itself is set as a threshold value.

  Specifically, the user can add a set of named thresholds by pressing the “add” button 6a, and the added content is added to the list on the screen. The user can change the threshold value by selecting the record whose threshold value is to be changed from the list and then pressing the “edit” button 6b. The user can delete a record by selecting a record to be deleted from the list and then pressing the “delete” button 6c.

  For example, in FIG. 6, the user assigns a name “Black” to a set of threshold values for extracting an image (black tone image) that can be regarded as a black monochrome tone as a blackout image, and sets the threshold value. is doing. As threshold values for extracting the black-tone image, 0 or more and less than 16 are set as the Y component threshold, 128 as the U component threshold, and 128 as the V component threshold.

  In addition, the user assigns a name “Green” to a set of thresholds for extracting an image (green tone image) that can be regarded as a single green tone (green tone image) as a blackout image, sets the threshold value, and sets magenta A threshold value is set by assigning the name “Maganda” to a set of threshold values for extracting an image (magenta image) that can be regarded as a single color tone as a blackout image. In addition, since the setting content of the threshold value with respect to each name is as showing in figure, description is abbreviate | omitted.

  After setting the threshold value on the screen set in FIG. 6, the user presses the “reset to initial value” button 6 d to reset the set threshold value and return each value to the initial value. Can do. Further, by pressing the “OK” button 6e, the setting contents of the threshold can be confirmed. On the other hand, by pressing the “cancel” button 6f, the setting contents of the threshold can be canceled and the setting screen can be closed.

  The image quality evaluation unit 103a determines whether each frame is a blackout image based on a threshold set by the user. For this purpose, the image quality evaluation unit 103b executes determination processing using all of the pixels in the frame using the Y component threshold, the U component threshold, and the V component threshold. Specifically, the image quality evaluation unit 103b performs the following process.

  The image quality evaluation unit 103b includes a luminance value (Y component value) of each pixel and a set Y component threshold value, a color difference value (U component value) from the blue component of each pixel and a set U component threshold value, Then, the color difference value (V component value) of the red component of each pixel is compared with the set V component threshold value. At this time, as shown in FIG. 6, when a plurality of sets of threshold values with different names are set, the image quality evaluation unit 103b determines the threshold value of each set, the luminance value of each pixel, and the color difference. Compare the value.

Then, when all the pixels in the frame satisfy the conditions shown in the following equations (3) to (5), the image quality evaluation unit 103b evaluates that the frame is a blackout image, and determines that the frame is black. Extract as an out-image.
V1 ≦ luminance value <V2 (3)
V3 ≦ blue component color difference value <V4 (4)
V5 ≦ color difference value of red component <V6 (5)

  The threshold values V1 and V2 in equation (3) are determined based on the Y component threshold values set on the setting screen in FIG. 6, and the threshold values V3 and V4 in equation (4) are set on the setting screen in FIG. The threshold values V5 and V6 in the equation (5) are determined based on the V component threshold values set on the setting screen of FIG. For example, the threshold value set as “Black” will be described as an example. Since the Y component threshold value set on the setting screen in FIG. 6 is −16, the threshold value V1 = 0 and the threshold value V2 = 16 are determined. Further, since the U component threshold value is 128, the threshold value V3 = 128 and the threshold value V4 = 128 + 1 = 129 are determined. Similarly, since the threshold value of the V component is 128, the threshold value V5 = 128 and the threshold value V6 = 128 + 1 = 129 are determined.

  As described above, in the present embodiment, the user can arbitrarily set the threshold value. Therefore, depending on the threshold setting method, it is possible to extract a white-out image in which the entire frame is completely white. In addition, monochromatic images of other colors can be extracted.

  The evaluation result output unit 103b displays the determination result of whether or not each frame is a blackout image for each frame by the image quality evaluation unit 103a in the blackout display field 2j in the evaluation result list display window on the main screen shown in FIG. indicate. For example, the evaluation result output unit 103b displays “◯” in the blackout display field 2j corresponding to the frame determined to be a blackout image. At this time, the evaluation result output unit 103b may change the background color of the display line of the corresponding frame, change the display color of the character, or blink the character.

(C) Partial Blackout Image Extraction Method The image quality evaluation unit 103a uses the same extraction process as that of a blackout image for a small area of m × n (0 <m ≦ M, 0 <n ≦ N) in a frame. To determine whether each small area is blacked out. If a predetermined number, for example, one blackout area is included in the frame, it is determined that the frame is a partial blackout image.

  The evaluation result output unit 103b displays the result of determination by the image quality evaluation unit 103a as to whether or not the image is a partial blackout image for each frame, in the partial blackout display field 2k in the evaluation result list display window on the main screen shown in FIG. Display within. For example, the evaluation result output unit 103b displays “◯” in the partial blackout display field 2k corresponding to the frame determined to be the partial blackout image. At this time, the evaluation result output unit 103b may change the background color of the display line of the corresponding frame, change the display color of the character, or blink the character.

  FIG. 7 is a flowchart showing the processing of the image evaluation apparatus 100 in the present embodiment. The process shown in FIG. 7 is executed by the control device 103 as a program to be started when the moving image data to be evaluated is designated by the user and the execution of the process is instructed. It is assumed that the selection of the evaluation item on the setting screen shown in FIG. 3 and the setting of the threshold value on each setting screen in FIGS. 5 and 6 are performed in advance by the user.

  In step S10, the image quality evaluation unit 103a reads the threshold set by the user, and proceeds to step S20. In step S20, the image quality evaluation unit 103a reads the first frame of the moving image data, and proceeds to step S30.

  In step S30, the image quality evaluation unit 103a compares the edge degree SI calculated by the equation (2) with the thresholds U1 and U2 set by the user, as described above in (A) Blur image extraction method. Then, it is determined whether or not the current frame is a blurred image. As a result, when it is determined that the image is a blurred image, the frame is extracted as a blurred image. Thereafter, the process proceeds to step S40.

  In step S40, the image quality evaluation unit 103a determines whether or not the current frame is a blackout image based on the equations (3) to (5), as described above in (B) Blackout image extraction method. judge. As a result, when it is determined that the image is a blackout image, the frame is extracted as a blackout image. Thereafter, the process proceeds to step S50.

  In step S50, the image quality evaluation unit 103a determines that the image quality evaluation unit 103a includes at least a plurality of m × n small regions set in the frame, as described above in (C) the partial blackout image extraction method. By determining whether or not one blackout area is included, it is determined whether or not the current frame is a partial blackout image. As a result, when it is determined that the image is a partial blackout image, the frame is extracted as a partial blackout image. Thereafter, the process proceeds to step S60.

  In step S60, the evaluation result output unit 103b updates the display result on each window in the main screen shown in FIG. 2 as described above based on the result of the above processing by the image quality evaluation unit 103a. In other words, the evaluation result output unit 103b updates the display in each window to the latest state reflecting the evaluation result by the image quality evaluation unit 103a. Thereafter, the process proceeds to step S70, and the image quality evaluation unit 103a determines whether or not the currently input frame is the final frame of the moving image data. If a negative determination is made, the process proceeds to step S80, where the image quality evaluation unit 103a reads the next frame of the moving image data and returns to step S30. On the other hand, when an affirmative determination is made, the process ends.

According to the present embodiment described above, the following operational effects can be obtained.
(1) The image quality evaluation unit 103a calculates the feature amount of each frame of the input moving image data, and based on the calculation result and the threshold value received from the user on the setting screen, the image quality evaluation unit 103a Extract characteristic images. The evaluation result output unit 103b displays the calculation result by the image quality evaluation unit 103a on the screen as a numerical value (evaluation value) or a figure (indicator). Thereby, the user can easily identify characteristic images included in a plurality of frames constituting the moving image data. Further, since the user can arbitrarily set the threshold value, an image desired by the user can be extracted as a characteristic image.

(2) The characteristic image is one of a blurred image, a monochromatic image (blackout image), and a partial monochromatic image (partial blackout image) including a monochromatic area in a part of the image. did. As a result, it is possible to extract a frame whose image quality has deteriorated due to a problem during encoding of moving image data.

(3) The image quality evaluation unit 103a calculates the edge degree SI as a feature amount representing the blur level for each frame, accepts the setting of the minimum value and the maximum value of the threshold value of the edge degree on the setting screen, and the edge degree SI is The frame is extracted as a blurred image when it is within the range indicated by the minimum and maximum threshold values. In this way, it is possible to arbitrarily set a range of edge degrees that the user wants to extract as a blurred image, taking into account that the degree of determination as to whether or not to create a blurred image varies depending on the person.

(4) The image quality evaluation unit 103a calculates the values of the Y, U, and V components as feature quantities representing a monochromatic image for each pixel of the frame, and sets the minimum threshold value for each color component on the setting screen. Accepts the setting of the maximum value, and extracts the frame as a blackout image when all the color component values are within the range indicated by the minimum value and the maximum value of all the pixels in the frame. did. As a result, the blackout frame does not necessarily have a single black color for the entire image, and the user can arbitrarily set the threshold in consideration of the fact that the entire image may be blackish or greenish. Can be set to

(5) The image quality evaluation unit 103a calculates the values of the Y, U, and V components as the feature values representing the partial monochromatic image for each pixel of the frame, and the minimum threshold value for each color component on the setting screen When the setting of the maximum value is received and all the color component values are within the range indicated by the minimum value and the maximum value of all the pixels in at least one region set in the frame, the frame Is extracted as a partial blackout image. As a result, a partially blackout frame does not necessarily have a single black color within a predetermined area in the image, and some areas in the image may be blackish or greenish. In addition, the user can arbitrarily set the threshold value.

(6) The evaluation result output unit 103b includes an evaluation image display window 2a for displaying input moving image data (input video), a feature image display window 2b for displaying a characteristic image, and image quality evaluation. An evaluation result list display window 2c for displaying a list of evaluation results of moving image data by the unit 103a, and an evaluation result graph display window 2d for displaying a graph of evaluation results of moving image data by the image quality evaluation unit 103a are displayed on the screen. To be displayed. As a result, the user can confirm necessary information on the same screen.

(7) The evaluation result output unit 103b is configured to synchronize the display contents on the windows. Thereby, every time the frame of the moving image data is switched, the display contents in all the windows can be updated to the latest contents.

(8) The evaluation result output unit 103b does not display any one or more of the windows based on an instruction from the user. As a result, the user can hide any of the windows according to his / her preference.

-Modification-
The image evaluation apparatus according to the above-described embodiment can be modified as follows.
(1) In the above-described embodiment, the image quality evaluation unit 103a compares the Y component, the U component, and the V component of each pixel with the threshold value and extracts the blackout image and the partial blackout image. Explained. However, the image quality evaluation unit 103a may extract a blackout image and a partial blackout image by comparing pixel values of another color space such as RGB with a threshold value.

(2) In the above-described embodiment, an example in which a personal computer is used as the image evaluation apparatus 100 has been described. However, the image evaluation apparatus 100 according to the present invention can also be applied to other devices that can reproduce and display moving image data. For example, when applied to a digital camera or a mobile phone having a moving image playback function, image quality can be evaluated on these devices.

  Note that the present invention is not limited to the configurations in the above-described embodiments as long as the characteristic functions of the present invention are not impaired.

It is a block diagram which shows the structure of one Embodiment of an image evaluation apparatus. It is a figure which shows the specific example of a main screen. It is a figure which shows the specific example of the setting screen for selecting an evaluation item. It is a figure which shows the specific example of a horizontal direction Sobel filter and a vertical direction Sobel filter. It is a figure which shows the specific example of the setting screen for setting the threshold value for extracting a blurred image. It is a figure which shows the specific example of the setting screen for setting the threshold value for extracting a blackout image and a partial blackout image. It is a flowchart figure which shows the process of the image evaluation apparatus.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Image evaluation apparatus, 101 Operation member, 102 Connection IF, 103 Control apparatus, 103a Image quality evaluation part, 103b Evaluation result output part, 104 HDD, 105 Monitor

Claims (9)

Feature amount calculating means for calculating the feature amount of each frame of the input moving image data;
Threshold receiving means for receiving a setting of a threshold for extracting a characteristic image from a plurality of frames constituting the moving image data;
Feature image extraction means for extracting the characteristic image from the plurality of frames based on a calculation result by the feature amount calculation means and a threshold value received by the threshold value reception means;
An image evaluation apparatus comprising: a display control unit that displays a calculation result by the feature amount calculation unit on a screen as a numerical value or a graphic. The image evaluation apparatus according to claim 1,
The image evaluation apparatus according to claim 1, wherein the characteristic image is any one of a blurred image, a monochromatic image, and a partial monochromatic image including a monochromatic area in a part of the image. The image evaluation apparatus according to claim 2,
The feature amount calculating means calculates a feature amount representing a blurring degree for each frame,
The threshold receiving means receives a setting of a minimum value and a maximum value of a feature amount representing the blur level as a threshold for extracting a blurred image;
The feature image extraction unit extracts the frame as the blurred image when the feature amount representing the blur level calculated by the feature amount calculation unit is within a range indicated by the minimum value and the maximum value. An image evaluation apparatus characterized by: The image evaluation apparatus according to claim 2 or 3,
The feature amount calculating means calculates a feature amount representing the monochrome image for each pixel of the frame,
The threshold acceptance means accepts setting of a minimum value and a maximum value of a feature amount representing the monochrome image as a threshold for extracting the monochrome image,
The feature image extraction unit is configured such that, for all pixels in the frame, the feature amount representing the monochromaticity calculated by the feature amount calculation unit is within a range indicated by the minimum value and the maximum value. An image evaluation apparatus, wherein a frame is extracted as the monochromatic image. In the image evaluation apparatus according to any one of claims 2 to 4,
The feature amount calculating means calculates a feature amount representing the partial monochromatic image for each pixel of the frame,
The threshold acceptance means accepts a setting of a minimum value and a maximum value of a feature amount representing the partial monochromatic image as a threshold for extracting the partial monochromatic image;
The feature image extraction unit indicates the feature amount representing the partial monochromaticity calculated by the feature amount calculation unit as the minimum value and the maximum value in all pixels in at least one region set in the frame. When the image is within the range, the frame is extracted as the partial monochromatic image. In the image evaluation apparatus according to any one of claims 1 to 5,
The display control means includes a first display area that displays the input moving image data, a second display area that displays the feature image extracted by the feature image extraction means, and a calculation result by the feature amount calculation means. Is displayed as a numerical value or a figure, and further, a third display area displaying the determination result as to whether or not the image is the feature image for each frame, and a fourth display area displaying the evaluation result of the moving image data as a graph. An image evaluation apparatus characterized by being displayed on a screen. The image evaluation apparatus according to claim 6,
The display control means synchronizes display contents on the display areas of the first display area, the second display area, the third display area, and the fourth display area. Image evaluation device. In the image evaluation apparatus according to claim 6 or 7,
The display control means selects one or more of the first display area, the second display area, the third display area, and the fourth display area based on an instruction from a user. An image evaluation apparatus characterized by being hidden. A feature amount calculation procedure for calculating the feature amount of each frame of the input moving image data;
A threshold acceptance procedure for accepting a threshold setting for extracting a characteristic image from a plurality of frames constituting the moving image data;
A feature image extraction procedure for extracting the characteristic image from the plurality of frames based on a calculation result of the feature amount calculation procedure and a threshold received in the threshold reception procedure;
An image evaluation program for causing a computer to execute a display control procedure for displaying a calculation result of the feature amount calculation procedure on a screen as a numerical value or a graphic.

Images